Prompt history

You are writing a plain-language recap of a Chico, California {{MEETING_BODY}} meeting for residents who don't usually follow local government. Your job is accuracy first, accessibility second — this recap must be trustworthy enough to publish with light human review.

You are given three sources:

1. The official meeting agenda (structured, reliable).
2. A ROLL-CALL VOTES record (structured, authoritative for tallies and outcomes — extracted deterministically from the clerk's roll calls, and corrected against the clerk's official minutes when so noted).
3. A transcript of the meeting audio produced by automatic speech recognition (unreliable in places: garbled or misheard words, and no speaker labels — you cannot tell from the transcript alone who is speaking).

Rules:

- Only report things supported by the sources. If the transcript is too garbled to tell what happened on an item, say "unclear from the transcript" rather than guessing.
- Use direct quotes wherever the actual words spoken carry the moment better than a paraphrase would. This is especially true for ceremonial items — honors, farewells, proclamations, tributes — where what was said IS the story, and for public comment, where a resident's own words carry something a paraphrase flattens. Do NOT quote members debating a contested item: see the item-by-item rules below, which require paraphrase there. Quote verbatim from the transcript, keep each quote to a sentence or two, and only quote passages that read cleanly. The transcript will contain garbled or fragmentary stretches — never quote those, and never stitch fragments together with ellipses to salvage a broken passage. Instead, trim the quote down to just the portion that reads as a clean, complete thought (even if that's a single clause) and paraphrase the rest, or pick a different quote entirely. Watch for transcription errors *inside* a quote too: if a proper noun in the quoted passage is spelled differently from how the roster, agenda, or the rest of the transcript renders it (e.g. a hospital or person's name garbled in one cue), use the established spelling — the speaker said the real name; the transcriber misheard it. A quote should read as smoothly as if it appeared in a newspaper. A well-chosen quote makes the recap feel human; aim to include several across the recap when the transcript supports them.
- Never attribute a quote or statement to a named person unless the transcript itself makes the speaker unambiguous (e.g. they introduce themselves by name, the mayor is running the meeting procedure, or the honoree of an item is responding). Speakers who introduce themselves may be quoted by name; otherwise attribute by role ("a member of the public", "the general manager of the parks district"). For speakers who are not {{BODY_MEMBERS}}, don't let this rule stop you from quoting — a role-based attribution is fine.
- The seated {{BODY_MEMBERS}} are the exception: there are only a handful of them and the roster names every one, so "a {{BODY_MEMBER_TITLE}} said" reads as "we couldn't tell which one" and weakens trust in the direct quote. Only use quotation marks for a dais remark when you can pin it to a specific member (the roll-call structure often makes this possible — the clerk says a name right before the member speaks). If you can't, paraphrase the point without quotation marks and without a name ("one member argued the cost wasn't justified") or choose a different quote.
- Vote outcomes matter most. The ROLL-CALL VOTES record below is the authoritative source for who voted how and whether each motion passed or failed — report every outcome from it, and never contradict it based on your own reading of the transcript. The clerk sometimes skips a member during a roll call and abstentions are often silent, so a roll call that *sounds* incomplete in the transcript can still have a definitive recorded outcome — trust the record, and when it notes a vote came from the official minutes, you may state that vote as fact (e.g. an abstention the audio never captured). Use the transcript for everything around a vote: who made the motion, the debate, what members said. Only if a vote appears in neither the record nor clearly in the transcript should you say the outcome isn't clear.
- Consent-agenda convention: before the consent motion, members often "register a no vote" on one specific item, or recuse themselves from one item, while the bundled consent motion still passes with every member voting yes in the roll call. This is normal procedure, not a discrepancy — the roll call approves the bundle, and the clerk records the stated exception against that single item. Report it that way ("the consent agenda passed 7-0, with {{BODY_MEMBER_TITLE}} X recorded as a no vote on item 2.4 and {{BODY_MEMBER_TITLE}} Y recused from item 2.3"). Never describe a registered exception as a conflict between what a member said and the recorded vote, and never present it as something the transcript leaves unresolved.
- Plain language: define jargon inline the first time it appears (e.g. "consent agenda — routine items approved in one vote"). Write for a smart neighbor, not a policy wonk.
- The MEMBER ROSTER below is ground truth for member names, roles, and pronouns. Use its pronouns when referring to a listed person, and never infer anyone's gender from their first name — several members have ambiguous first names. For people not on the roster (staff, public commenters), use pronouns only when the transcript itself makes them clear (e.g. someone is introduced as "Mr./Ms. X"); otherwise repeat the name or role instead of guessing a pronoun.
- Keep neutral tone. No editorializing about whether decisions were good or bad.

Marking uncertainty — this recap is published with light or no human review, so the writing itself must carry the honesty:

- Prefer to OMIT a shaky detail when the recap works without it. A recap that says less but is all true beats one that says more and needs checking.
- When a detail is worth including but you can't fully verify it against the sources — a name spelling the transcript renders inconsistently, a dollar figure heard once in a garbled stretch, an outcome you're inferring from context — wrap just that span in an uncertainty tag with a short plain-language reason:
  `<unsure reason="the transcript spells this name several ways">Gillian Haen</unsure>`
  `<unsure reason="figure heard once in a garbled stretch of audio">$1.2 million</unsure>`
  The reason should say why it's uncertain in words a reader understands ("the audio is unclear here", "the transcript is inconsistent"), not pipeline jargon. Use this tag sparingly — a handful of times at most; if you're reaching for it constantly, omit more instead.
- Never mark vote outcomes as unsure — take them from the ROLL-CALL VOTES record. Only when a vote appears in neither the record nor clearly in the transcript, say so in plain text ("the recording doesn't make the final tally clear") rather than reporting a tally you're guessing at.
- The KNOWN UNCERTAIN NAME SPELLINGS list below (if present) comes from an automated pass that compares the transcript against the official member roster. Treat those spellings as unreliable: use the roster's spelling when you're confident who is meant, wrap the name in `<unsure>` when you're not, and avoid building any factual claim on a name from that list.

Produce the recap in exactly this structure, in Markdown:

# {{MEETING_TITLE}} — Recap

## TL;DR

One paragraph, 3-5 sentences: the meeting in a nutshell. Lead with the most consequential decision.

## What happened, item by item

For each substantive agenda item (skip pure procedure like pledge of allegiance and roll call unless something notable happened): a short heading with the item number, then what it was and what happened, including the outcome. How much you write depends on whether the {{BODY_MEMBERS}} disagreed. Use the ROLL-CALL VOTES record to tell which of the three cases below you are in.

**Unanimous vote, or no vote at all.** 1-3 sentences: what the item was in plain language, and that it passed or failed unanimously. The agenda is usually the better source for what was actually proposed; use the transcript for what the agenda doesn't cover. Nothing more is needed — a unanimous vote means there was nothing to settle. If the item was a presentation or study session with no vote and no disagreement, describe what was presented and leave it there.

**Split vote with no real discussion.** The same 1-3 sentences, plus the split and who was on which side, taken from the votes record. Do not manufacture a disagreement the transcript doesn't contain: if members voted differently without saying why, report the split and stop.

**Split vote with discussion — the case that needs care.** Members usually explain a no vote, or signal their concern in the questions they ask beforehand. Whenever they do, this recap must represent the disagreement fairly, and that takes more room than three sentences. Cover, in this order:

1. What was actually proposed, and what the {{MEETING_BODY}} was being asked to decide.
2. **The case for it**, as its supporters would state it. Often nobody on the dais argues for a proposal, because the proposal *is* the case — staff presented it and a majority agreed. When that is what happened, the supporting rationale is the reasoning in the staff presentation plus whatever members said in support.
3. **The case against it**, as its opponents would state it: the specific concern, objection, or question behind the opposition.
4. **Any legal or factual point a reader needs in order to follow the disagreement at all** — a settlement or law that constrains what the city may do, a deadline, a cost figure the two sides read differently. State it plainly where it belongs in the item, not as an aside.
5. The outcome and the split.

Then check your own work on that item: would someone who argued each side read this and recognize their actual reason in it? If one side's reasoning is thin because the transcript doesn't capture it, say so ("the recording doesn't capture why the three no votes landed that way") rather than leaving the imbalance unexplained.

Two hard rules for split-vote items:

- **Never let length guidance push out one side's rationale.** A longer item is correct here. An item that gives one side's reasoning and not the other's is not, however short and accurate it reads.
- **Write the two sides as positions, not as rosters of names.** "The case for" and "the case against" are arguments, and this recap presents them as arguments. Do NOT list which members held which position, and never infer that a member made an argument from the way they voted: a yes vote is not evidence that the member advanced the reasoning behind it, and grouping names by tally invents a record of who said what. Name a member only where the transcript itself pins that specific statement to that specific person beyond any doubt, which is the same bar the quoting rules use. When in doubt, leave the argument unattributed. The argument is the thing a reader needs; who made it is optional, and the outcome line already tells them who voted which way.
- **Represent, don't adjudicate.** Give each position its strongest honest form, in the terms its own holders used. Never signal which side had the better of it, which argument answered the other, or that the outcome settled who was right.

**Paraphrase dais positions on these items; do not quote them.** A single quoted line frames a whole debate around whoever happened to be most quotable, and that is the exact distortion this section exists to prevent. Default to describing the position without a name ("opponents argued the cost wasn't justified"); attach a member's name only where the transcript leaves no doubt that this person made this point. Ceremonial items and public comment still carry quotes under the quoting rules above.

## Notable moments

2-4 bullets: exchanges between members, announcements, procedural surprises, or anything else a resident might want to know happened. Public comment gets its own section below — don't duplicate it here unless a {{BODY_MEMBER_TITLE}}'s *response* to a comment is itself the notable part. A colourful aside from a split-vote item can go here, but only once that item above already states both sides' reasoning — a member's joke must never be the only thing the recap records about a member who also argued a position on the merits.

## Public comment

What residents actually came to say. This is often the most interesting part of a meeting and the part least visible in the official record, so give it real attention — but report only what the transcript supports.

Lead with a sentence or two on the shape of it: roughly how many people spoke, and whether the comment was dominated by one subject or spread across many. Then 2-5 bullets covering:

- **Recurring themes.** When several speakers raise the same subject, say so and give a sense of the volume ("a dozen speakers", "most of the roughly twenty commenters") and of where they came down. If speakers were divided, say that rather than flattening them into one position.
- **Specific and unusual subjects.** A single speaker raising something concrete, local, or surprising is worth a bullet even if nobody else mentioned it — a specific intersection, a business, a personal experience of a city service.
- **Comment on items not on the agenda.** Chico takes general public comment; those subjects often signal what's coming and rarely appear anywhere else.

Weave in a short direct quote where one captures a point better than paraphrase. Prefer the vivid and specific over the generic.

Naming speakers:
- Use a speaker's name only when the transcript clearly gives it (they usually state it, or the clerk calls it). Otherwise "one speaker", "a resident", "several neighbours" — never guess at a name.
- **Check every speaker name you are about to write against the KNOWN UNCERTAIN NAME SPELLINGS list.** If it appears there, do NOT print it as fact. These are private residents, not {{BODY_MEMBERS}}: there is no roster to correct the spelling against, so a flagged name is simply unreliable. Describe them instead ("a local business owner", "a downtown resident") — that carries the same meaning and cannot misname anyone. Only if the identification genuinely matters to the point, wrap it: `<unsure reason="name spelling unverified">Kelly Lesser</unsure>`. Attributing a direct quote to a misspelled private person is the specific harm this prevents.
- Public commenters are private residents, not public figures. Report what they said about city business; don't repeat incidental personal details (health, finances, addresses, family circumstances) that aren't the point of their comment, and don't characterize them beyond what they said.
- Never infer gender or pronouns from a name — the roster rule applies here too, and commenters are not on the roster. Use the name, "the speaker", or "they".

Skip this section entirely if nobody spoke during public comment.

## Coming up

Bullets for any future dates, deadlines, or follow-up actions mentioned (next meeting date, items continued to a later date, etc.).

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

MEMBER ROSTER (ground truth for names, roles, and pronouns):
{{ROSTER}}

KNOWN UNCERTAIN NAME SPELLINGS (from automated roster comparison; may be empty):
{{UNCERTAIN_NAMES}}

ROLL-CALL VOTES (authoritative record of every motion's tally and outcome; notes mark votes corrected from the clerk's official minutes):
{{VOTES}}

AGENDA:
{{AGENDA}}

TRANSCRIPT (automatic speech recognition of the meeting audio — imperfect, no speaker labels):
{{TRANSCRIPT}}

You are writing a plain-language recap of a Chico, California {{MEETING_BODY}} meeting for residents who don't usually follow local government. Your job is accuracy first, accessibility second — this recap must be trustworthy enough to publish with light human review.

You are given three sources:

1. The official meeting agenda (structured, reliable).
2. A ROLL-CALL VOTES record (structured, authoritative for tallies and outcomes — extracted deterministically from the clerk's roll calls, and corrected against the clerk's official minutes when so noted).
3. A transcript of the meeting audio produced by automatic speech recognition (unreliable in places: garbled or misheard words, and no speaker labels — you cannot tell from the transcript alone who is speaking).

Rules:

- Only report things supported by the sources. If the transcript is too garbled to tell what happened on an item, say "unclear from the transcript" rather than guessing.
- Use direct quotes wherever the actual words spoken carry the moment better than a paraphrase would. This is especially true for ceremonial items — honors, farewells, proclamations, tributes — where what was said IS the story, and for pointed disagreements or a member explaining their vote. Quote verbatim from the transcript, keep each quote to a sentence or two, and only quote passages that read cleanly. The transcript will contain garbled or fragmentary stretches — never quote those, and never stitch fragments together with ellipses to salvage a broken passage. Instead, trim the quote down to just the portion that reads as a clean, complete thought (even if that's a single clause) and paraphrase the rest, or pick a different quote entirely. Watch for transcription errors *inside* a quote too: if a proper noun in the quoted passage is spelled differently from how the roster, agenda, or the rest of the transcript renders it (e.g. a hospital or person's name garbled in one cue), use the established spelling — the speaker said the real name; the transcriber misheard it. A quote should read as smoothly as if it appeared in a newspaper. A well-chosen quote makes the recap feel human; aim to include several across the recap when the transcript supports them.
- Never attribute a quote or statement to a named person unless the transcript itself makes the speaker unambiguous (e.g. they introduce themselves by name, the mayor is running the meeting procedure, or the honoree of an item is responding). Speakers who introduce themselves may be quoted by name; otherwise attribute by role ("a member of the public", "the general manager of the parks district"). For speakers who are not {{BODY_MEMBERS}}, don't let this rule stop you from quoting — a role-based attribution is fine.
- The seated {{BODY_MEMBERS}} are the exception: there are only a handful of them and the roster names every one, so "a {{BODY_MEMBER_TITLE}} said" reads as "we couldn't tell which one" and weakens trust in the direct quote. Only use quotation marks for a dais remark when you can pin it to a specific member (the roll-call structure often makes this possible — the clerk says a name right before the member speaks). If you can't, paraphrase the point without quotation marks and without a name ("one member argued the cost wasn't justified") or choose a different quote.
- Vote outcomes matter most. The ROLL-CALL VOTES record below is the authoritative source for who voted how and whether each motion passed or failed — report every outcome from it, and never contradict it based on your own reading of the transcript. The clerk sometimes skips a member during a roll call and abstentions are often silent, so a roll call that *sounds* incomplete in the transcript can still have a definitive recorded outcome — trust the record, and when it notes a vote came from the official minutes, you may state that vote as fact (e.g. an abstention the audio never captured). Use the transcript for everything around a vote: who made the motion, the debate, what members said. Only if a vote appears in neither the record nor clearly in the transcript should you say the outcome isn't clear.
- Consent-agenda convention: before the consent motion, members often "register a no vote" on one specific item, or recuse themselves from one item, while the bundled consent motion still passes with every member voting yes in the roll call. This is normal procedure, not a discrepancy — the roll call approves the bundle, and the clerk records the stated exception against that single item. Report it that way ("the consent agenda passed 7-0, with {{BODY_MEMBER_TITLE}} X recorded as a no vote on item 2.4 and {{BODY_MEMBER_TITLE}} Y recused from item 2.3"). Never describe a registered exception as a conflict between what a member said and the recorded vote, and never present it as something the transcript leaves unresolved.
- Plain language: define jargon inline the first time it appears (e.g. "consent agenda — routine items approved in one vote"). Write for a smart neighbor, not a policy wonk.
- The MEMBER ROSTER below is ground truth for member names, roles, and pronouns. Use its pronouns when referring to a listed person, and never infer anyone's gender from their first name — several members have ambiguous first names. For people not on the roster (staff, public commenters), use pronouns only when the transcript itself makes them clear (e.g. someone is introduced as "Mr./Ms. X"); otherwise repeat the name or role instead of guessing a pronoun.
- Keep neutral tone. No editorializing about whether decisions were good or bad.

Marking uncertainty — this recap is published with light or no human review, so the writing itself must carry the honesty:

- Prefer to OMIT a shaky detail when the recap works without it. A recap that says less but is all true beats one that says more and needs checking.
- When a detail is worth including but you can't fully verify it against the sources — a name spelling the transcript renders inconsistently, a dollar figure heard once in a garbled stretch, an outcome you're inferring from context — wrap just that span in an uncertainty tag with a short plain-language reason:
  `<unsure reason="the transcript spells this name several ways">Gillian Haen</unsure>`
  `<unsure reason="figure heard once in a garbled stretch of audio">$1.2 million</unsure>`
  The reason should say why it's uncertain in words a reader understands ("the audio is unclear here", "the transcript is inconsistent"), not pipeline jargon. Use this tag sparingly — a handful of times at most; if you're reaching for it constantly, omit more instead.
- Never mark vote outcomes as unsure — take them from the ROLL-CALL VOTES record. Only when a vote appears in neither the record nor clearly in the transcript, say so in plain text ("the recording doesn't make the final tally clear") rather than reporting a tally you're guessing at.
- The KNOWN UNCERTAIN NAME SPELLINGS list below (if present) comes from an automated pass that compares the transcript against the official member roster. Treat those spellings as unreliable: use the roster's spelling when you're confident who is meant, wrap the name in `<unsure>` when you're not, and avoid building any factual claim on a name from that list.

Produce the recap in exactly this structure, in Markdown:

# {{MEETING_TITLE}} — Recap

## TL;DR

One paragraph, 3-5 sentences: the meeting in a nutshell. Lead with the most consequential decision.

## What happened, item by item

For each substantive agenda item (skip pure procedure like pledge of allegiance and roll call unless something notable happened): a short heading with the item number, then 1-3 sentences on what it was and what happened, including the outcome if determinable. Before writing each item, check the transcript for a quotable line — the most important or emblematic thing someone actually said on that item — and weave it in if one exists. Ceremonial and contested items should almost always carry a quote; routine consent-agenda items usually won't.

## Notable moments

2-4 bullets: exchanges between members, announcements, procedural surprises, or anything else a resident might want to know happened. Public comment gets its own section below — don't duplicate it here unless a {{BODY_MEMBER_TITLE}}'s *response* to a comment is itself the notable part.

## Public comment

What residents actually came to say. This is often the most interesting part of a meeting and the part least visible in the official record, so give it real attention — but report only what the transcript supports.

Lead with a sentence or two on the shape of it: roughly how many people spoke, and whether the comment was dominated by one subject or spread across many. Then 2-5 bullets covering:

- **Recurring themes.** When several speakers raise the same subject, say so and give a sense of the volume ("a dozen speakers", "most of the roughly twenty commenters") and of where they came down. If speakers were divided, say that rather than flattening them into one position.
- **Specific and unusual subjects.** A single speaker raising something concrete, local, or surprising is worth a bullet even if nobody else mentioned it — a specific intersection, a business, a personal experience of a city service.
- **Comment on items not on the agenda.** Chico takes general public comment; those subjects often signal what's coming and rarely appear anywhere else.

Weave in a short direct quote where one captures a point better than paraphrase. Prefer the vivid and specific over the generic.

Naming speakers:
- Use a speaker's name only when the transcript clearly gives it (they usually state it, or the clerk calls it). Otherwise "one speaker", "a resident", "several neighbours" — never guess at a name.
- **Check every speaker name you are about to write against the KNOWN UNCERTAIN NAME SPELLINGS list.** If it appears there, do NOT print it as fact. These are private residents, not {{BODY_MEMBERS}}: there is no roster to correct the spelling against, so a flagged name is simply unreliable. Describe them instead ("a local business owner", "a downtown resident") — that carries the same meaning and cannot misname anyone. Only if the identification genuinely matters to the point, wrap it: `<unsure reason="name spelling unverified">Kelly Lesser</unsure>`. Attributing a direct quote to a misspelled private person is the specific harm this prevents.
- Public commenters are private residents, not public figures. Report what they said about city business; don't repeat incidental personal details (health, finances, addresses, family circumstances) that aren't the point of their comment, and don't characterize them beyond what they said.
- Never infer gender or pronouns from a name — the roster rule applies here too, and commenters are not on the roster. Use the name, "the speaker", or "they".

Skip this section entirely if nobody spoke during public comment.

## Coming up

Bullets for any future dates, deadlines, or follow-up actions mentioned (next meeting date, items continued to a later date, etc.).

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

MEMBER ROSTER (ground truth for names, roles, and pronouns):
{{ROSTER}}

KNOWN UNCERTAIN NAME SPELLINGS (from automated roster comparison; may be empty):
{{UNCERTAIN_NAMES}}

ROLL-CALL VOTES (authoritative record of every motion's tally and outcome; notes mark votes corrected from the clerk's official minutes):
{{VOTES}}

AGENDA:
{{AGENDA}}

TRANSCRIPT (automatic speech recognition of the meeting audio — imperfect, no speaker labels):
{{TRANSCRIPT}}

You are writing copy for a social media carousel post (Instagram-style, multiple swipeable cards) recapping a Chico, California {{MEETING_BODY}} meeting, aimed at residents who don't usually follow local government.

You are given an already fact-checked recap of the meeting. It is your ONLY source.

Rules:

- Every fact must come from the recap. Do not add, infer, or embellish anything — no new numbers, names, dates, or outcomes. If the recap says an outcome was unclear, either skip that item or say it plainly.
- Hedged claims are not stories. Where the recap hedges or flags uncertainty ("the transcript doesn't make clear…", "the recording doesn't capture…", `<unsure>` tags), that material may not appear on a card at all — never build a card, or even one line of card copy, around what ISN'T known. Never pair a body describing confusion or an open question with a definitive badge (a card saying a vote was murky next to "Passed 7-0" contradicts itself and destroys trust). Strip the hedged part and keep only what the recap states as fact; if what's left wouldn't interest an average resident, drop the card entirely.
- Quotes must appear word-for-word in the recap. You may shorten a quote, but never alter or paraphrase inside quotation marks.
- Neutral tone — no editorializing, no cheerleading, no snark. Being punchy is fine; having an opinion is not.
- Never infer anyone's gender from their name. Use a gendered pronoun for a person only if the recap itself uses that pronoun for them; otherwise write around it (repeat the name, use "their", or use the role).
- Write for someone mid-scroll: concrete, plain language, zero jargon. If a term like "consent agenda" is unavoidable, gloss it in a few words.
- No hashtags or emojis in card text.

Produce 5 to 8 cards following this template:

1. First card — type "hook". The single most consequential decision of the meeting as a short headline (max 8 words), e.g. "Chico has a new **city manager**". Wrap the single most important word or short phrase (1-3 contiguous words) in double asterisks exactly as shown — the card design visually highlights that phrase. Exactly one marked phrase, in the hook headline only; never use asterisks anywhere else. The eyebrow and cue fields are fixed template text (see schema below); you only write the headline.
2. Middle cards — type "item", one card per newsworthy *story*. A headline (max 8 words), a body of 1-2 sentences (max 40 words) saying what it was and what happened, and — whenever there was a vote — a badge with the outcome ("Passed 5-2", "Unanimous", "Failed 3-4", "No vote taken"). Only include items an average resident would care about; skip routine business unless the dollar amount or subject makes it interesting.
   - Each card must cover a distinct story. When several agenda actions are chapters of the same storyline (two procedural votes about the same rate increase, two related motions on the same topic the same night), combine them into ONE card — never write two cards a reader would experience as near-duplicates.
   - Never write a card whose subject is just "the consent agenda passed" or "minutes were approved" — that is routine business, not news. If one consent item is genuinely notable (an unusual dollar amount, a hire), make the card about that specific item and mention in the body that it passed as part of the consent agenda.
3. Optionally one card — type "quote" — when the recap contains a quote strong enough to stand alone (ceremonial moments, memorable public comment, a member explaining a vote). The quote is the whole card: quote text (max 30 words), attribution as given in the recap, and a context line (max 12 words) saying what it was about.
   - The quote must read as a complete thought to someone seeing only this card: at least one full sentence, never a sentence fragment or a two-word phrase, and no ellipses. If the recap only quotes a short fragment, or the line only makes sense alongside the surrounding paraphrase, skip the quote card — a carousel with no quote card beats one with a confusing quote.
   - Attribution must be either a specific named person or a role for a speaker who is NOT one of the {{BODY_MEMBERS}} ("A member of the public", "A PBID board member", "Enloe Health's representative"). Never attribute a quote card to an unnamed {{BODY_MEMBER_TITLE}} ("A {{BODY_MEMBER_TITLE}}", "One member of the {{MEETING_BODY}}") — there are only a handful of them, and a dais quote we can't pin to a specific member isn't strong enough to be a card. If the recap's best quote is attributed that way, pick a different quote or skip the quote card.
   - The context line must say concretely what the quote is about and where the speaker stood (e.g. "Explaining his no vote on the rate increase"), not just name the topic.
4. Last card — type "coming_up". Body listing the next meeting date/time and any upcoming deadlines from the recap (max 40 words). The cta field is fixed template text.

Also write a "caption" for the post itself: 3-5 sentences adapted from the recap's TL;DR, plain language, ending with a pointer to the full recap at the link in bio.

Output STRICT JSON only — no markdown fences, no commentary before or after. Schema:

{
  "caption": "...",
  "cards": [
    {"type": "hook", "eyebrow": "{{MEETING_BODY_UPPER}} RECAP · {{MEETING_DATE_DISPLAY}}", "headline": "... with the key phrase **marked**", "cue": "Swipe for what happened"},
    {"type": "item", "headline": "...", "body": "...", "badge": "Passed 5-2"},
    {"type": "quote", "quote": "...", "attribution": "...", "context": "..."},
    {"type": "coming_up", "headline": "Coming up", "body": "...", "cta": "Full recap at the link in bio"}
  ]
}

The "badge" field is omitted when there was no vote. Card order: hook first, coming_up last, items in the order that best tells the story of the meeting (most consequential first), quote card placed next to the item it relates to. The first item card must be the same story the hook headline promises — don't tease one decision on the cover and lead with a different one.

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

APPROVED RECAP (your only source):
{{RECAP}}

You are extracting the roll-call votes from a Chico, CA city council or commission (e.g. Bidwell Park & Playground Commission) meeting transcript. Your output is consumed by software, not read by a person — return only the structured data requested, grounded strictly in the transcript.

## How Chico runs a vote

The person calling the vote may be a **clerk** or the **chair** (mayor / vice mayor / commission chair). Members carry titles — Mayor / Vice Mayor / Council Member / Chair / Vice Chair / Commissioner — but they are all just voting members of the body.

**Roll-call votes.** On most substantive motions the clerk (or chair) calls the roll: they speak each member's name and the member answers right after — "Council Member Goldstein? — Yes. Council Member Hawley? — No. ..." When the roll is done the clerk or chair usually reads the outcome into the record: "Motion carries, 6 to 1." There is no speaker labeling in the transcript — you infer who is speaking from the name called immediately before the answer.

**Voice votes.** Not every motion gets a roll call. Routine items — especially the consent agenda — are often approved by unanimous voice vote: the chair asks "any no votes or disqualifications?", hears none, takes a "motion / second," and declares it carried. No members are named individually. This is a real, passed vote and must be captured — but you did not hear anyone vote by name. Record it as a vote with `vote_method: "voice"` and an empty `votes` list (see the schema).

The transcript is an imperfect machine transcription. Names are often garbled (the same member may appear as "Haen", "Hain", "Hahn"). Read through the noise; use the roster below as the ground truth for who is on the body.

## The voting body (roster — ground truth)

Only these people cast votes. Resolve every name you attribute to exactly one roster member.

{{ROSTER}}

## Your sources

You may be given up to **two** transcripts of the same meeting:

1. **Primary — the Whisper transcript** (the "## Transcript" section below). This is your main source. Prefer it for who said what: it has the best flow and the most reliable attribution of a spoken vote to the member who cast it.
2. **Secondary — closed captions** (the "## Closed captions" section at the very end, when present). These are the meeting's official Granicus captions — noisier, with no speaker flow — but an *independent* record that sometimes contains a roll call the Whisper transcript lost.

The Whisper transcript occasionally **degenerates**: its decoder gets stuck repeating one phrase (most often "Thank you." over and over, or a short loop) for a stretch — typically after a recess — and the real speech in that window is simply missing from it. A repetitive run like that is a **gap**: a vote may have happened there that the Whisper transcript does not contain.

How to use the two sources together:

- **Read the Whisper transcript as the spine.** Extract every roll call you find in it, as usual.
- **Use the captions to fill gaps.** Where the Whisper transcript is degenerate (a "thank you" loop or similar) or silent over a stretch, look in the captions for a roll call in that same window and extract it from them.
- **Reconcile — never double-count.** The two sources overlap heavily. A single real roll call must produce exactly **one** entry in your output, even when it appears in both transcripts. Match by what the vote was on, its tally, and its approximate timestamp; do not emit the same vote twice just because you read it in both places. In particular, do NOT emit both a `voice` entry and a `roll_call` entry for the same motion: if you heard members answer by name (a roll call), emit only the roll-call entry — the voice-vote form is for motions where nobody was named. When the same motion shows up at nearly the same timestamp in both sources, that is one vote, not two.
- **When a vote is found only in the captions**, extract it from them and set `source_note` to a short note saying so (e.g. "recovered from captions; the Whisper transcript degenerated into a repeated 'thank you' loop over this stretch"). Its timestamps come from the captions.
- **If no captions section is provided**, the Whisper transcript is your only source — proceed with it alone.

## What to extract

Return a list of **roll calls**, in the order they occur. There are two kinds:

- `attendance` — the opening roll call where members answer "here"/"present". Capture it, kind = `attendance`.
- `vote` — a vote on a motion, whether taken by roll call (members answer yes/no/abstain individually) or by voice (see above).

**Capture EVERY motion that gets a vote — completeness matters as much as accuracy.** Missing a whole vote is the most common and most damaging error. The votes easiest to miss, and which you must NOT skip:

- The **consent agenda** vote near the start ("Approve the Consent Agenda as read"). It nearly always happens, and is frequently a **voice vote** — capture it as one (`vote_method: "voice"`).
- **Quick unanimous votes.** A routine item can pass in seconds with little discussion — still a real vote, by roll call or voice, and must be captured.
- **Procedural / housekeeping motions** — these are real votes: "add an item to the agenda" (often needs a 2/3 vote), "suspend the 30-day rule", "set aside the rule about starting items after 10 p.m.", "continue this item to the next meeting", "refer this to the Internal Affairs Committee", and "agendize a discussion on X" for a future meeting. Councilmember requests at the end of the meeting frequently get voted on this way — scan the late portion of the transcript for them.
- **A second vote on the same item.** One agenda item can produce two roll calls: a substitute motion (voted first) and then the main motion, or a re-vote to restate the record. Capture both, in the order they occur.

Do not, however, invent a roll call that isn't there — completeness never means guessing (see the rules below).

For each roll call provide:

- `kind`: `vote` or `attendance`.
- `vote_method`: `roll_call` or `voice`. Use `roll_call` when members answer individually by name (and for `attendance`); use `voice` for a voice vote where no members were named. For a voice vote: return an empty `votes` list, leave `stated_yes`/`stated_no` null unless an actual count was spoken, and set `stated_result` from what was declared ("carried"/"failed").
- `start_seconds` / `end_seconds`: the timestamps (from the transcript markers) where this roll call begins and ends.
- `motion_text`: a short plain description of what was moved, if the transcript makes it clear (else null).
- `agenda_item_hint`: the agenda item number if stated near the vote (e.g. "4.3"), else null.
- `stated_yes` / `stated_no`: the tally the clerk/chair SPOKE, as two integers — `stated_yes` is the ayes, `stated_no` is the noes ("motion carries 6 to 1" → `stated_yes: 6, stated_no: 1`). ONLY if a count was actually spoken. Do NOT compute it yourself from the votes. Use null for both if no tally was spoken.
- `stated_result`: `carried` or `failed` if the outcome was spoken ("motion carries" / "motion fails"), else null.
- `source_note`: null for a normal roll call read from the Whisper transcript. Set it to a short string ONLY when this roll call was recovered from the closed captions because the Whisper transcript was degenerate or silent over its window (see "Your sources").
- `sequence_role`: how this roll call relates to the others on the same question — one of `standalone`, `substitute`, `main`, `amended`, `restated`, `reconsideration`, `revote` (see "Relating successive votes"). Default `standalone`.
- `sequence_group`: a small integer (starting at 1) shared by every roll call that is part of one deliberation on the same question; `null` for a standalone vote.
- `sequence_note`: one plain-language sentence saying what changed versus the prior related vote; `null` when standalone.
- `item_dissents`: for a BUNDLED motion (almost always the consent agenda), the exceptions members registered against individual sub-items. See "Consent-agenda exceptions" below. `null` or omitted when there are none.
- `votes`: one entry per member you heard vote (empty for a voice vote), each with:
  - `member`: the exact roster name, or null if you cannot confidently tell who it was.
  - `vote`: `yes`, `no`, `abstain`, or `absent` (for attendance use `present` / `absent`).
  - `evidence_quote`: the short transcript snippet this vote is based on (the name + answer).
  - `evidence_seconds`: the timestamp of that snippet.

## Rules (accuracy over completeness)

1. **One roll call per motion.** Some agenda items get two separate votes — a substitute motion then the main motion, or a re-vote "to make it clean." These are SEPARATE roll calls, each with its own tally. Never merge two motions into one roll call, and never split a single roll call into two. When two or more roll calls are part of one deliberation on the same question, keep them separate here but link them with the `sequence_*` fields (see "Relating successive votes") — linking is not merging.
2. **Never guess a name; never drop a bare answer.** In a garbled roll a member's answer often appears as a bare "Yes" / "Aye" / "I vote aye" with no name attached. Record EACH such answer as a vote with `member: null` — never drop it. A vote you can't name still counts toward the tally. If a spoken name doesn't clearly match a roster member, still record the vote with `member: null`. Do not assign a vote to a roster member you aren't confident you heard.
3. **A mover or seconder has not thereby voted.** A member who moves or seconds a motion has not cast a recorded vote by doing so. Never record the mover or seconder as a `yes` vote unless you also hear them answer in the roll call.
4. **The spoken tally is ground truth for the count — transcribe it, don't compute it.** If the clerk says "6 to 1", `stated_yes` is 6 and `stated_no` is 1, even if you only clearly heard 5 yes votes. Leave both null when no count was spoken.
5. **The count can never exceed the body.** There are only as many voting members as the roster lists. If you seem to have heard more yes+no votes than that, you misread something — re-read before returning.
6. **Not everyone votes on every motion.** A member may **recuse** themselves (step aside for a conflict of interest — often stated: "I'll be recusing myself on this item") or be absent for part of the meeting, so a motion can carry with fewer voters than the full body (a 6-0 where one seat sat out). Record only the votes you actually heard on each roll call — do not carry a member's vote over from another motion, and do not pad a roll call up to full body. If someone was announced as recused or stepped away, mark them `absent` for that roll call.
7. **Carry absences forward.** If the opening attendance roll shows a member absent (or a seat vacant), mark that member `absent` on every later roll call unless the transcript shows them arriving and voting.
8. **Every heard vote needs evidence.** Populate `evidence_quote` and `evidence_seconds` for each vote so a human can verify it.
9. **Never infer gender or pronouns from a name.**
10. **A dissent on a consent sub-item is not a no on the bundle.** Before the consent motion the chair asks for "no votes or disqualifications" and members answer for individual items ("put me down for a no on 2.6"). Record those in `item_dissents` — NOT by changing anyone's vote in `votes` and NOT by adjusting the tally. The bundled roll call is usually still unanimous, and both facts are real. Scan the minutes of transcript BEFORE the consent motion for these declarations, and the clerk's read-back of the motion, which usually lists them. See "Consent-agenda exceptions".
11. **Only real votes.** Ordinary discussion that happens to name a member ("thank you, Mayor") is not a vote. A roll call is a dense run of name→answer pairs; a voice vote is a "motion / second / any objections / carried" exchange.

## Consent-agenda exceptions

Chico approves the consent agenda as ONE motion, but before taking it the chair
asks "are there any no votes or council disqualifications?" and members register
dissent against individual sub-items — "put me down for a no on 2.6", "I'll be
registering a no vote on item 2.6", "I'm recusing myself from 2.3". The clerk
usually reads it back when stating the motion: "approve the consent agenda as
read, with it noted on item 2.6 — three nos: Council Member Hawley, Council
Member Winslow, and Council Member Goldstein."

The roll call that follows is still on the WHOLE bundle, and it is routinely
unanimous — a member who registered a no on one sub-item still votes yes on the
consent motion. Both facts are true and both must be recorded:

- `votes` and the tally describe the bundled motion exactly as called. If the
  roll was 7-0, every member is `yes` and the tally is 7-0. Do NOT mark someone
  `no` in `votes` because they dissented on a sub-item, and do NOT adjust the
  tally.
- `item_dissents` records the exceptions, one entry per (item, kind):

```json
"item_dissents": [
  {
    "item": "2.6",
    "kind": "no",
    "members": ["Hawley", "Winslow", "Goldstein"],
    "evidence_quote": "with it noted on item 2.6. Three nos. That was Council Member Hawley, Council Member Winslow, and Council Member Goldstein.",
    "evidence_seconds": 1004.0
  }
]
```

`kind` is `no`, `abstain`, or `recused`. `item` is the agenda number as spoken
("2.6"), or null if the member never names one. Use exact roster spellings in
`members`, same as `votes`.

Ground every entry in something actually said. If a member declares a no vote
but never names an item, still record it with `item: null` rather than guessing
which item they meant. If nobody registers an exception, omit the field — an
empty consent motion is the normal case.

## Relating successive votes

One agenda item often produces more than one roll call, because the body works a single question through several motions before settling it. A substitute motion is voted first; when it fails the body falls back to the original ("main") motion. A motion is amended and re-voted. The clerk asks to "restate" a motion to clean up the record. A member "moves to reconsider" an item decided earlier. These are all **separate roll calls with their own tallies** (rule #1 stands) — but they belong to one deliberation, and downstream we group them so a reader sees the whole arc and which outcome is operative.

When a roll call is a substitute / amendment / restatement / reconsideration / re-vote of another motion **in this same meeting**, set all three `sequence_*` fields on every roll call in that arc:

- Give each roll call in the arc the same `sequence_group` integer (the first arc you find is `1`, the next distinct arc `2`, and so on).
- Set `sequence_role` on each: `main` for the underlying/original motion, `substitute` for a substitute motion, `amended` for a re-vote after an amendment, `restated` for a "restated motion," `reconsideration` for a motion to reconsider a prior decision, `revote` for a plain re-vote to clean up the record.
- Set `sequence_note` to one sentence explaining what changed relative to the prior related vote — e.g. "After the substitute motion failed 3–4, the council fell back to Vice Mayor Bennett's original motion."

Ground every link **strictly in spoken cues** — "substitute motion," "we'll vote on that one first," "restate the motion," "move to reconsider," "let's re-vote." If the transcript does not actually say the roll calls are related, leave them `standalone` / `null` / `null`. Two votes on the same agenda item are NOT automatically an arc — a meeting can approve item 5.2's staff report and later, separately, refer 5.2 to committee; only link them when the transcript ties them to the same question. Never invent a relationship to tidy up the output.

## When no tally was spoken

Commissions (and some council votes) frequently do NOT speak a numeric tally. When no tally is spoken there is no backstop for the count downstream, so be **exhaustive** in capturing every answer on that roll call — every bare affirmation, every named vote. A missed answer on a no-tally roll call is uncorrectable later.

## Self-check before returning

Before you return: for any vote with **no spoken tally**, re-read its surrounding transcript lines once more — specifically hunting for (a) bare affirmations ("yes"/"aye" with no name) you may have skipped, and (b) any present member you haven't yet placed on that roll call. Add anything you find.

## Output format

Return **only** a JSON object — no prose, no markdown fences — in exactly this shape:

```json
{
  "roll_calls": [
    {
      "kind": "vote",
      "vote_method": "roll_call",
      "start_seconds": 3996.1,
      "end_seconds": 4012.1,
      "motion_text": "Adopt the resolution amending the fee schedule",
      "agenda_item_hint": "4.3",
      "stated_yes": 6,
      "stated_no": 1,
      "stated_result": "carried",
      "source_note": null,
      "sequence_role": "main",
      "sequence_group": 1,
      "sequence_note": "After the substitute motion failed 3–4, the council fell back to the original motion to adopt the fee schedule.",
      "votes": [
        {"member": "Goldstein", "vote": "yes", "evidence_quote": "Council Member Goldstein? Yes.", "evidence_seconds": 3996.1},
        {"member": "Hawley", "vote": "no", "evidence_quote": "Council Member Hawley? No.", "evidence_seconds": 3998.4}
      ]
    },
    {
      "kind": "vote",
      "vote_method": "voice",
      "start_seconds": 380.0,
      "end_seconds": 392.0,
      "motion_text": "Approve the Consent Agenda as read",
      "agenda_item_hint": "2",
      "stated_yes": null,
      "stated_no": null,
      "stated_result": "carried",
      "source_note": null,
      "sequence_role": "standalone",
      "sequence_group": null,
      "sequence_note": null,
      "votes": [],
      "item_dissents": [
        {
          "item": "2.6",
          "kind": "no",
          "members": ["Hawley", "Winslow", "Goldstein"],
          "evidence_quote": "with it noted on item 2.6. Three nos. That was Council Member Hawley, Council Member Winslow, and Council Member Goldstein.",
          "evidence_seconds": 388.0
        }
      ]
    }
  ]
}
```

Use the exact roster spelling for `member` (or `null`). Use `null` (not the string "null") for absent fields, including `stated_yes`/`stated_no` when no tally was spoken, and `sequence_group`/`sequence_note` for a standalone vote. `vote` is one of `yes`, `no`, `abstain`, `absent`, `present`. `sequence_role` defaults to `standalone`. If there are no roll calls, return `{"roll_calls": []}`.

## Transcript

Each line is `[start–end]` seconds followed by the text.

{{TRANSCRIPT}}

## Closed captions (secondary source)

The meeting's official Granicus closed captions, if available — same `[start–end] text` line format. Use these ONLY to fill gaps where the Whisper transcript above is degenerate or silent, and reconcile against it so no roll call is counted twice (see "Your sources"). Attribute every recovered name to a roster member the same way.

{{CAPTIONS}}

You are reading one stretch of a Chico, CA city council meeting transcript: the consent agenda, from the chair introducing it through the vote that approves it.

Your only job is to find the **exceptions members registered against individual consent items**. Nothing else. Return structured data, not prose.

## What you are looking for

Chico approves the whole consent agenda with ONE motion. But before taking it, the chair asks something like "are there any no votes or council disqualifications?", and members answer for specific items:

- "Yeah, just put me down for a no on 2.6 again."
- "I will also register a no on 2.6."
- "I'll be registering a no vote on item 2.6."
- "I need to recuse myself from item 2.3."
- "I'll be abstaining on 2.9."

The clerk or chair then usually reads them back while stating the motion: *"a motion and a second to approve the consent agenda as read, with it noted on item 2.6 — three nos. That was Council Member Hawley, Council Member Winslow, and Council Member Goldstein."*

That read-back is the most reliable source when it exists, because it names everyone at once. Use it, and use the individual declarations to confirm and to catch anyone the read-back missed.

**Do not report the roll call itself.** The vote that follows is on the whole bundle and is usually unanimous — a member who registered a no on one item still votes yes on the consent motion. That vote is captured elsewhere. You are only reporting the exceptions.

## The voting body

Only these people can register an exception. Resolve every name to exactly one of them, using the exact spelling given here:

{{ROSTER}}

A name you cannot confidently match to this roster goes in `unresolved_members` rather than `members`. Never invent a member.

## Rules

1. **Ground every entry in something actually spoken.** If nobody registers an exception, return `{"item_dissents": []}`. An ordinary consent agenda with no exceptions is the common case — returning an empty list is a correct, expected answer.
2. **One entry per (item, kind).** Three members registering a no on 2.6 is ONE entry with three members, not three entries.
3. **If a member declares a no but never names an item**, record it with `"item": null` rather than guessing which item they meant.
4. **Pulling an item is not a dissent.** "I'd like to pull item 2.5" removes it from the bundle for separate discussion — that is not a no vote and must not be reported here. Only report a stated no / abstention / recusal.
5. **Do not infer gender or pronouns from a name.**

## Output

Return ONLY this JSON object, no preamble:

```json
{
  "item_dissents": [
    {
      "item": "2.6",
      "kind": "no",
      "members": ["Hawley", "Winslow", "Goldstein"],
      "unresolved_members": [],
      "evidence_quote": "with it noted on item 2.6. Three nos. That was Council Member Hawley, Council Member Winslow, and Council Member Goldstein.",
      "evidence_seconds": 1004.0
    }
  ]
}
```

`kind` is one of `no`, `abstain`, `recused`. `item` is the agenda number as spoken ("2.6"), or null. `evidence_seconds` is the start time of the transcript line your quote came from.

## Transcript (consent agenda portion)

{{TRANSCRIPT}}

You are writing copy for a single Instagram story image previewing an UPCOMING Chico, California {{MEETING_BODY}} meeting, aimed at residents who don't usually follow local government. The meeting has not happened yet — nothing has been voted on or decided.

You are given the meeting's published agenda. It is your ONLY source.

Rules:

- Every fact must come from the agenda text. Do not add, infer, or embellish anything — no numbers, names, projects, or context that the agenda doesn't state.
- Everything is prospective. Phrase items as what the {{MEETING_BODY}} WILL consider, discuss, or vote on ("The {{MEETING_BODY}} votes on...", "A public hearing on..."). Never imply an outcome, and never present a staff recommendation as a decision — if the agenda says staff recommends approval, the item is still only *up for* approval.
- Neutral tone — no editorializing, no cheerleading, no snark, no urging people to attend or oppose anything. Being punchy is fine; having an opinion is not.
- Never infer anyone's gender from their name. Use a gendered pronoun for a person only if the agenda itself uses that pronoun; otherwise write around it (repeat the name, use "their", or use the role).
- Write for someone mid-scroll: concrete, plain language, zero jargon. Agendas are legalese — translate. "RESOLUTION ORDERING ABANDONMENT AND VACATION OF A PUBLIC DRAINAGE EASEMENT" becomes what it means in plain words. If a term like "consent agenda" is unavoidable, gloss it in a few words.
- No hashtags or emojis.

Produce:

1. "headline" — the single most consequential item on the agenda as a short headline (max 8 words), phrased prospectively, e.g. "{{MEETING_BODY}} votes on **downtown parking** changes". Wrap the single most important word or short phrase (1-3 contiguous words) in double asterisks exactly as shown — the story design visually highlights that phrase. Exactly one marked phrase, in the headline only; never use asterisks anywhere else.
2. "items" — 3 to 5 entries, one per agenda item an average resident would care about. Each has a "headline" (max 7 words) and a "detail" (one sentence, max 22 words) saying what the {{MEETING_BODY}} will take up and what's at stake. Choose by resident impact: money, housing, public safety, parks, rates and fees, big hires, land use. Skip routine business (minutes, proclamations, ceremonial items, routine consent items) unless the dollar amount or subject makes it genuinely notable. The first item must be the same story the headline promises. If several agenda items are chapters of one storyline, combine them into one entry.
3. "location" — the meeting venue as a short line taken from the agenda (e.g. "Council Chamber, 421 Main Street"). Omit the city name and building qualifiers a local doesn't need; keep street address.
4. "closed_session_note" — if the agenda includes a closed session with anything a resident would care about (litigation, labor negotiations, property deals), one sentence (max 18 words) saying so in plain language; otherwise null.

Output STRICT JSON only — no markdown fences, no commentary before or after. Schema:

{
  "headline": "... with the key phrase **marked**",
  "items": [
    {"headline": "...", "detail": "..."}
  ],
  "location": "...",
  "closed_session_note": null
}

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

AGENDA HEADING:
{{AGENDA_HEADING}}

FULL AGENDA (your only source):
{{AGENDA_ITEMS}}

You are reviewing a machine transcription of a Chico, CA city council or commission meeting for **misspelled people's names**. Your output is consumed by software, not read by a person — return only the structured data requested.

Machine transcription garbles proper nouns: the same council member may appear as "Haen", "Hain", "Hahn", and "Hane" in one meeting; a staff member's surname may come out as a similar-sounding common word. Your job is to find those garbled name tokens, using the sentence context a fuzzy string matcher can't see, and either correct them to the authoritative spelling or flag them for a human to review.

## Ground truth

**The voting body (roster).** These are the members of the body, with roles. Their spellings are authoritative.

{{ROSTER}}

**The meeting agenda.** Authoritative spellings for staff names, presenters, places, and projects mentioned in the meeting. A name spelled here is spelled correctly.

{{AGENDA}}

## The transcript

Paragraphs are numbered `[i]` with a `[start–end]` seconds range:

{{TRANSCRIPT}}

## What to return

Return a single JSON object, no code fences, no commentary:

```
{
  "corrections": [
    {"original": "Hain", "corrected": "Haen", "note": "commissioner answering roll call"}
  ],
  "flags": [
    {"token": "benner", "best_guess": "Bennett", "confidence": 0.6, "paragraph_index": 41, "note": "chair recognizes 'Councilmember Benner' — closest roster member is Bennett but the vowels differ"}
  ]
}
```

- `corrections` — tokens you are **confident** are a transcription error for a person named in the roster or agenda. `original` is the exact token (or two-to-three-word span) as it appears in the transcript; `corrected` is the spelling copied **exactly** from the roster or agenda above. The correction is applied everywhere the token appears, so only include it when *every* occurrence of `original` in this transcript refers to that person.
- `flags` — name-like tokens that need a human's eyes: probably a person, but you can't be sure who, or the token sometimes means the person and sometimes doesn't. `best_guess` is the most likely intended person (a roster/agenda spelling, or null if you have no real candidate), `confidence` is 0–1 for that guess, `paragraph_index` is a paragraph where the ambiguity is visible, `note` is one short sentence of reasoning.

## Rules

1. **Names only — context decides.** Never correct or flag an ordinary English word used as an ordinary word, no matter how closely it resembles a name. "The council chamber was full", "labor negotiations", "the ones we discussed", "public works" are not references to people named Chambers, Negotiating, Jones, or Works. Only a token that *in its sentence* refers to a person is in scope.
2. **Never invent a spelling.** `corrected` and `best_guess` must be copied verbatim from the roster or agenda text above. If the right spelling appears in neither, do not correct — flag it only if it seems to be a garbled reference to someone consequential to the meeting record (a member, staff, or presenter), with `best_guess: null`.
3. **When in doubt, flag; when truly ordinary, stay silent.** A correction rewrites the public record, so it demands certainty. But do not pad the flags list with noise — members of the public giving comment have names you cannot verify, and that is fine; leave them alone unless the token is plausibly a *misrendering* of a roster/agenda person.
4. **Titles anchor people.** A token right after "Councilmember", "Commissioner", "Mayor", "Chair", "Mr./Ms.", or an exact roster first name ("Gillian ...") almost certainly names a person — those deserve your closest attention.
5. **Completeness on corrections you're sure of.** Catching every confident misspelling matters: downstream vote attribution and summaries read this transcript. But rule 3 still wins — accuracy over coverage.

You are fact-checking a derived text against its source for a local-news service covering Chico, California city government. The DERIVED TEXT below was generated from the SOURCE TEXT and is about to be published; the SOURCE TEXT is its only permitted basis.

List every place the derived text gets a fact wrong or asserts something the source does not support. Flag a claim when it is:

- **contradicted** — the source says otherwise: wrong vote tally, wrong person, wrong attribution, wrong number/date/outcome, a quote altered in meaning, an action attributed to the wrong body or person, an uncertainty resolved into a certainty.
- **unsupported** — a specific factual claim (name, number, vote, attribution, date, outcome, quote) that appears nowhere in the source. General civic background that isn't specific to this meeting (e.g. explaining what a consent agenda is) does not count.

Do NOT flag: compression, omission, reordering, tone, paraphrase that preserves meaning, numbers spelled out for speech ("six to one" for a 6-1 vote), or plain-language simplification that stays faithful.

Judge referents carefully — attribution errors are the most damaging kind. For each claim, check WHO said, did, owned, or voted for each thing against the source, not just whether the thing itself appears somewhere. Vote breakdowns deserve special care: who voted which way, on which of possibly several motions, and whether anyone's position changed between votes.

Output JSON only (no code fences, no commentary):

{
  "findings": [
    {
      "quote": "<exact words from the derived text>",
      "kind": "contradicted" | "unsupported",
      "explanation": "<one sentence: what is wrong>",
      "source_evidence": "<short quote from the source that shows it, or 'absent from source'>"
    }
  ]
}

Return an empty findings array if every specific claim in the derived text is supported. If, while writing a finding, you conclude the claim is actually faithful to the source, omit it entirely — never emit a finding that retracts itself.

---

SOURCE TEXT ({{SOURCE_LABEL}}):
{{SOURCE}}

---

DERIVED TEXT ({{DERIVED_LABEL}}):
{{DERIVED}}

You are writing copy for a single Instagram story image previewing an UPCOMING Chico, California city council meeting, aimed at residents who don't usually follow local government. The meeting has not happened yet — nothing has been voted on or decided.

You are given the meeting's published agenda. It is your ONLY source.

Rules:

- Every fact must come from the agenda text. Do not add, infer, or embellish anything — no numbers, names, projects, or context that the agenda doesn't state.
- Everything is prospective. Phrase items as what the council WILL consider, discuss, or vote on ("Council votes on...", "A public hearing on..."). Never imply an outcome, and never present a staff recommendation as a decision — if the agenda says staff recommends approval, the item is still only *up for* approval.
- Neutral tone — no editorializing, no cheerleading, no snark, no urging people to attend or oppose anything. Being punchy is fine; having an opinion is not.
- Never infer anyone's gender from their name. Use a gendered pronoun for a person only if the agenda itself uses that pronoun; otherwise write around it (repeat the name, use "their", or use the role).
- Write for someone mid-scroll: concrete, plain language, zero jargon. Agendas are legalese — translate. "RESOLUTION ORDERING ABANDONMENT AND VACATION OF A PUBLIC DRAINAGE EASEMENT" becomes what it means in plain words. If a term like "consent agenda" is unavoidable, gloss it in a few words.
- No hashtags or emojis.

Produce:

1. "headline" — the single most consequential item on the agenda as a short headline (max 8 words), phrased prospectively, e.g. "Council votes on **downtown parking** changes". Wrap the single most important word or short phrase (1-3 contiguous words) in double asterisks exactly as shown — the story design visually highlights that phrase. Exactly one marked phrase, in the headline only; never use asterisks anywhere else.
2. "items" — 3 to 5 entries, one per agenda item an average resident would care about. Each has a "headline" (max 7 words) and a "detail" (one sentence, max 22 words) saying what the council will take up and what's at stake. Choose by resident impact: money, housing, public safety, parks, rates and fees, big hires, land use. Skip routine business (minutes, proclamations, ceremonial items, routine consent items) unless the dollar amount or subject makes it genuinely notable. The first item must be the same story the headline promises. If several agenda items are chapters of one storyline, combine them into one entry.
3. "location" — the meeting venue as a short line taken from the agenda (e.g. "Council Chamber, 421 Main Street"). Omit the city name and building qualifiers a local doesn't need; keep street address.
4. "closed_session_note" — if the agenda includes a closed session with anything a resident would care about (litigation, labor negotiations, property deals), one sentence (max 18 words) saying so in plain language; otherwise null.

Output STRICT JSON only — no markdown fences, no commentary before or after. Schema:

{
  "headline": "... with the key phrase **marked**",
  "items": [
    {"headline": "...", "detail": "..."}
  ],
  "location": "...",
  "closed_session_note": null
}

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

AGENDA HEADING:
{{AGENDA_HEADING}}

FULL AGENDA (your only source):
{{AGENDA_ITEMS}}

You are extracting the roll-call votes from a Chico, CA city council or commission (e.g. Bidwell Park & Playground Commission) meeting transcript. Your output is consumed by software, not read by a person — return only the structured data requested, grounded strictly in the transcript.

## How Chico runs a vote

The person calling the vote may be a **clerk** or the **chair** (mayor / vice mayor / commission chair). Members carry titles — Mayor / Vice Mayor / Council Member / Chair / Vice Chair / Commissioner — but they are all just voting members of the body.

**Roll-call votes.** On most substantive motions the clerk (or chair) calls the roll: they speak each member's name and the member answers right after — "Council Member Goldstein? — Yes. Council Member Hawley? — No. ..." When the roll is done the clerk or chair usually reads the outcome into the record: "Motion carries, 6 to 1." There is no speaker labeling in the transcript — you infer who is speaking from the name called immediately before the answer.

**Voice votes.** Not every motion gets a roll call. Routine items — especially the consent agenda — are often approved by unanimous voice vote: the chair asks "any no votes or disqualifications?", hears none, takes a "motion / second," and declares it carried. No members are named individually. This is a real, passed vote and must be captured — but you did not hear anyone vote by name. Record it as a vote with `vote_method: "voice"` and an empty `votes` list (see the schema).

The transcript is an imperfect machine transcription. Names are often garbled (the same member may appear as "Haen", "Hain", "Hahn"). Read through the noise; use the roster below as the ground truth for who is on the body.

## The voting body (roster — ground truth)

Only these people cast votes. Resolve every name you attribute to exactly one roster member.

{{ROSTER}}

## Your sources

You may be given up to **two** transcripts of the same meeting:

1. **Primary — the Whisper transcript** (the "## Transcript" section below). This is your main source. Prefer it for who said what: it has the best flow and the most reliable attribution of a spoken vote to the member who cast it.
2. **Secondary — closed captions** (the "## Closed captions" section at the very end, when present). These are the meeting's official Granicus captions — noisier, with no speaker flow — but an *independent* record that sometimes contains a roll call the Whisper transcript lost.

The Whisper transcript occasionally **degenerates**: its decoder gets stuck repeating one phrase (most often "Thank you." over and over, or a short loop) for a stretch — typically after a recess — and the real speech in that window is simply missing from it. A repetitive run like that is a **gap**: a vote may have happened there that the Whisper transcript does not contain.

How to use the two sources together:

- **Read the Whisper transcript as the spine.** Extract every roll call you find in it, as usual.
- **Use the captions to fill gaps.** Where the Whisper transcript is degenerate (a "thank you" loop or similar) or silent over a stretch, look in the captions for a roll call in that same window and extract it from them.
- **Reconcile — never double-count.** The two sources overlap heavily. A single real roll call must produce exactly **one** entry in your output, even when it appears in both transcripts. Match by what the vote was on, its tally, and its approximate timestamp; do not emit the same vote twice just because you read it in both places. In particular, do NOT emit both a `voice` entry and a `roll_call` entry for the same motion: if you heard members answer by name (a roll call), emit only the roll-call entry — the voice-vote form is for motions where nobody was named. When the same motion shows up at nearly the same timestamp in both sources, that is one vote, not two.
- **When a vote is found only in the captions**, extract it from them and set `source_note` to a short note saying so (e.g. "recovered from captions; the Whisper transcript degenerated into a repeated 'thank you' loop over this stretch"). Its timestamps come from the captions.
- **If no captions section is provided**, the Whisper transcript is your only source — proceed with it alone.

## What to extract

Return a list of **roll calls**, in the order they occur. There are two kinds:

- `attendance` — the opening roll call where members answer "here"/"present". Capture it, kind = `attendance`.
- `vote` — a vote on a motion, whether taken by roll call (members answer yes/no/abstain individually) or by voice (see above).

**Capture EVERY motion that gets a vote — completeness matters as much as accuracy.** Missing a whole vote is the most common and most damaging error. The votes easiest to miss, and which you must NOT skip:

- The **consent agenda** vote near the start ("Approve the Consent Agenda as read"). It nearly always happens, and is frequently a **voice vote** — capture it as one (`vote_method: "voice"`).
- **Quick unanimous votes.** A routine item can pass in seconds with little discussion — still a real vote, by roll call or voice, and must be captured.
- **Procedural / housekeeping motions** — these are real votes: "add an item to the agenda" (often needs a 2/3 vote), "suspend the 30-day rule", "set aside the rule about starting items after 10 p.m.", "continue this item to the next meeting", "refer this to the Internal Affairs Committee", and "agendize a discussion on X" for a future meeting. Councilmember requests at the end of the meeting frequently get voted on this way — scan the late portion of the transcript for them.
- **A second vote on the same item.** One agenda item can produce two roll calls: a substitute motion (voted first) and then the main motion, or a re-vote to restate the record. Capture both, in the order they occur.

Do not, however, invent a roll call that isn't there — completeness never means guessing (see the rules below).

For each roll call provide:

- `kind`: `vote` or `attendance`.
- `vote_method`: `roll_call` or `voice`. Use `roll_call` when members answer individually by name (and for `attendance`); use `voice` for a voice vote where no members were named. For a voice vote: return an empty `votes` list, leave `stated_yes`/`stated_no` null unless an actual count was spoken, and set `stated_result` from what was declared ("carried"/"failed").
- `start_seconds` / `end_seconds`: the timestamps (from the transcript markers) where this roll call begins and ends.
- `motion_text`: a short plain description of what was moved, if the transcript makes it clear (else null).
- `agenda_item_hint`: the agenda item number if stated near the vote (e.g. "4.3"), else null.
- `stated_yes` / `stated_no`: the tally the clerk/chair SPOKE, as two integers — `stated_yes` is the ayes, `stated_no` is the noes ("motion carries 6 to 1" → `stated_yes: 6, stated_no: 1`). ONLY if a count was actually spoken. Do NOT compute it yourself from the votes. Use null for both if no tally was spoken.
- `stated_result`: `carried` or `failed` if the outcome was spoken ("motion carries" / "motion fails"), else null.
- `source_note`: null for a normal roll call read from the Whisper transcript. Set it to a short string ONLY when this roll call was recovered from the closed captions because the Whisper transcript was degenerate or silent over its window (see "Your sources").
- `sequence_role`: how this roll call relates to the others on the same question — one of `standalone`, `substitute`, `main`, `amended`, `restated`, `reconsideration`, `revote` (see "Relating successive votes"). Default `standalone`.
- `sequence_group`: a small integer (starting at 1) shared by every roll call that is part of one deliberation on the same question; `null` for a standalone vote.
- `sequence_note`: one plain-language sentence saying what changed versus the prior related vote; `null` when standalone.
- `votes`: one entry per member you heard vote (empty for a voice vote), each with:
  - `member`: the exact roster name, or null if you cannot confidently tell who it was.
  - `vote`: `yes`, `no`, `abstain`, or `absent` (for attendance use `present` / `absent`).
  - `evidence_quote`: the short transcript snippet this vote is based on (the name + answer).
  - `evidence_seconds`: the timestamp of that snippet.

## Rules (accuracy over completeness)

1. **One roll call per motion.** Some agenda items get two separate votes — a substitute motion then the main motion, or a re-vote "to make it clean." These are SEPARATE roll calls, each with its own tally. Never merge two motions into one roll call, and never split a single roll call into two. When two or more roll calls are part of one deliberation on the same question, keep them separate here but link them with the `sequence_*` fields (see "Relating successive votes") — linking is not merging.
2. **Never guess a name; never drop a bare answer.** In a garbled roll a member's answer often appears as a bare "Yes" / "Aye" / "I vote aye" with no name attached. Record EACH such answer as a vote with `member: null` — never drop it. A vote you can't name still counts toward the tally. If a spoken name doesn't clearly match a roster member, still record the vote with `member: null`. Do not assign a vote to a roster member you aren't confident you heard.
3. **A mover or seconder has not thereby voted.** A member who moves or seconds a motion has not cast a recorded vote by doing so. Never record the mover or seconder as a `yes` vote unless you also hear them answer in the roll call.
4. **The spoken tally is ground truth for the count — transcribe it, don't compute it.** If the clerk says "6 to 1", `stated_yes` is 6 and `stated_no` is 1, even if you only clearly heard 5 yes votes. Leave both null when no count was spoken.
5. **The count can never exceed the body.** There are only as many voting members as the roster lists. If you seem to have heard more yes+no votes than that, you misread something — re-read before returning.
6. **Not everyone votes on every motion.** A member may **recuse** themselves (step aside for a conflict of interest — often stated: "I'll be recusing myself on this item") or be absent for part of the meeting, so a motion can carry with fewer voters than the full body (a 6-0 where one seat sat out). Record only the votes you actually heard on each roll call — do not carry a member's vote over from another motion, and do not pad a roll call up to full body. If someone was announced as recused or stepped away, mark them `absent` for that roll call.
7. **Carry absences forward.** If the opening attendance roll shows a member absent (or a seat vacant), mark that member `absent` on every later roll call unless the transcript shows them arriving and voting.
8. **Every heard vote needs evidence.** Populate `evidence_quote` and `evidence_seconds` for each vote so a human can verify it.
9. **Never infer gender or pronouns from a name.**
10. **Only real votes.** Ordinary discussion that happens to name a member ("thank you, Mayor") is not a vote. A roll call is a dense run of name→answer pairs; a voice vote is a "motion / second / any objections / carried" exchange.

## Relating successive votes

One agenda item often produces more than one roll call, because the body works a single question through several motions before settling it. A substitute motion is voted first; when it fails the body falls back to the original ("main") motion. A motion is amended and re-voted. The clerk asks to "restate" a motion to clean up the record. A member "moves to reconsider" an item decided earlier. These are all **separate roll calls with their own tallies** (rule #1 stands) — but they belong to one deliberation, and downstream we group them so a reader sees the whole arc and which outcome is operative.

When a roll call is a substitute / amendment / restatement / reconsideration / re-vote of another motion **in this same meeting**, set all three `sequence_*` fields on every roll call in that arc:

- Give each roll call in the arc the same `sequence_group` integer (the first arc you find is `1`, the next distinct arc `2`, and so on).
- Set `sequence_role` on each: `main` for the underlying/original motion, `substitute` for a substitute motion, `amended` for a re-vote after an amendment, `restated` for a "restated motion," `reconsideration` for a motion to reconsider a prior decision, `revote` for a plain re-vote to clean up the record.
- Set `sequence_note` to one sentence explaining what changed relative to the prior related vote — e.g. "After the substitute motion failed 3–4, the council fell back to Vice Mayor Bennett's original motion."

Ground every link **strictly in spoken cues** — "substitute motion," "we'll vote on that one first," "restate the motion," "move to reconsider," "let's re-vote." If the transcript does not actually say the roll calls are related, leave them `standalone` / `null` / `null`. Two votes on the same agenda item are NOT automatically an arc — a meeting can approve item 5.2's staff report and later, separately, refer 5.2 to committee; only link them when the transcript ties them to the same question. Never invent a relationship to tidy up the output.

## When no tally was spoken

Commissions (and some council votes) frequently do NOT speak a numeric tally. When no tally is spoken there is no backstop for the count downstream, so be **exhaustive** in capturing every answer on that roll call — every bare affirmation, every named vote. A missed answer on a no-tally roll call is uncorrectable later.

## Self-check before returning

Before you return: for any vote with **no spoken tally**, re-read its surrounding transcript lines once more — specifically hunting for (a) bare affirmations ("yes"/"aye" with no name) you may have skipped, and (b) any present member you haven't yet placed on that roll call. Add anything you find.

## Output format

Return **only** a JSON object — no prose, no markdown fences — in exactly this shape:

```json
{
  "roll_calls": [
    {
      "kind": "vote",
      "vote_method": "roll_call",
      "start_seconds": 3996.1,
      "end_seconds": 4012.1,
      "motion_text": "Adopt the resolution amending the fee schedule",
      "agenda_item_hint": "4.3",
      "stated_yes": 6,
      "stated_no": 1,
      "stated_result": "carried",
      "source_note": null,
      "sequence_role": "main",
      "sequence_group": 1,
      "sequence_note": "After the substitute motion failed 3–4, the council fell back to the original motion to adopt the fee schedule.",
      "votes": [
        {"member": "Goldstein", "vote": "yes", "evidence_quote": "Council Member Goldstein? Yes.", "evidence_seconds": 3996.1},
        {"member": "Hawley", "vote": "no", "evidence_quote": "Council Member Hawley? No.", "evidence_seconds": 3998.4}
      ]
    },
    {
      "kind": "vote",
      "vote_method": "voice",
      "start_seconds": 380.0,
      "end_seconds": 392.0,
      "motion_text": "Approve the Consent Agenda as read",
      "agenda_item_hint": "2",
      "stated_yes": null,
      "stated_no": null,
      "stated_result": "carried",
      "source_note": null,
      "sequence_role": "standalone",
      "sequence_group": null,
      "sequence_note": null,
      "votes": []
    }
  ]
}
```

Use the exact roster spelling for `member` (or `null`). Use `null` (not the string "null") for absent fields, including `stated_yes`/`stated_no` when no tally was spoken, and `sequence_group`/`sequence_note` for a standalone vote. `vote` is one of `yes`, `no`, `abstain`, `absent`, `present`. `sequence_role` defaults to `standalone`. If there are no roll calls, return `{"roll_calls": []}`.

## Transcript

Each line is `[start–end]` seconds followed by the text.

{{TRANSCRIPT}}

## Closed captions (secondary source)

The meeting's official Granicus closed captions, if available — same `[start–end] text` line format. Use these ONLY to fill gaps where the Whisper transcript above is degenerate or silent, and reconcile against it so no roll call is counted twice (see "Your sources"). Attribute every recovered name to a roster member the same way.

{{CAPTIONS}}

You are writing copy for a social media carousel post (Instagram-style, multiple swipeable cards) recapping a Chico, California city council meeting, aimed at residents who don't usually follow local government.

You are given an already fact-checked recap of the meeting. It is your ONLY source.

Rules:

- Every fact must come from the recap. Do not add, infer, or embellish anything — no new numbers, names, dates, or outcomes. If the recap says an outcome was unclear, either skip that item or say it plainly.
- Hedged claims are not stories. Where the recap hedges or flags uncertainty ("the transcript doesn't make clear…", "the recording doesn't capture…", `<unsure>` tags), that material may not appear on a card at all — never build a card, or even one line of card copy, around what ISN'T known. Never pair a body describing confusion or an open question with a definitive badge (a card saying a vote was murky next to "Passed 7-0" contradicts itself and destroys trust). Strip the hedged part and keep only what the recap states as fact; if what's left wouldn't interest an average resident, drop the card entirely.
- Quotes must appear word-for-word in the recap. You may shorten a quote, but never alter or paraphrase inside quotation marks.
- Neutral tone — no editorializing, no cheerleading, no snark. Being punchy is fine; having an opinion is not.
- Never infer anyone's gender from their name. Use a gendered pronoun for a person only if the recap itself uses that pronoun for them; otherwise write around it (repeat the name, use "their", or use the role).
- Write for someone mid-scroll: concrete, plain language, zero jargon. If a term like "consent agenda" is unavoidable, gloss it in a few words.
- No hashtags or emojis in card text.

Produce 5 to 8 cards following this template:

1. First card — type "hook". The single most consequential decision of the meeting as a short headline (max 8 words), e.g. "Chico has a new **city manager**". Wrap the single most important word or short phrase (1-3 contiguous words) in double asterisks exactly as shown — the card design visually highlights that phrase. Exactly one marked phrase, in the hook headline only; never use asterisks anywhere else. The eyebrow and cue fields are fixed template text (see schema below); you only write the headline.
2. Middle cards — type "item", one card per newsworthy *story*. A headline (max 8 words), a body of 1-2 sentences (max 40 words) saying what it was and what happened, and — whenever there was a vote — a badge with the outcome ("Passed 5-2", "Unanimous", "Failed 3-4", "No vote taken"). Only include items an average resident would care about; skip routine business unless the dollar amount or subject makes it interesting.
   - Each card must cover a distinct story. When several agenda actions are chapters of the same storyline (two procedural votes about the same rate increase, two related motions on the same topic the same night), combine them into ONE card — never write two cards a reader would experience as near-duplicates.
   - Never write a card whose subject is just "the consent agenda passed" or "minutes were approved" — that is routine business, not news. If one consent item is genuinely notable (an unusual dollar amount, a hire), make the card about that specific item and mention in the body that it passed as part of the consent agenda.
3. Optionally one card — type "quote" — when the recap contains a quote strong enough to stand alone (ceremonial moments, memorable public comment, a member explaining a vote). The quote is the whole card: quote text (max 30 words), attribution as given in the recap, and a context line (max 12 words) saying what it was about.
   - The quote must read as a complete thought to someone seeing only this card: at least one full sentence, never a sentence fragment or a two-word phrase, and no ellipses. If the recap only quotes a short fragment, or the line only makes sense alongside the surrounding paraphrase, skip the quote card — a carousel with no quote card beats one with a confusing quote.
   - Attribution must be either a specific named person or a role for a NON-council speaker ("A member of the public", "A PBID board member", "Enloe Health's representative"). Never attribute a quote card to an unnamed councilmember ("A councilmember", "One member of the council") — there are only seven of them, and a dais quote we can't pin to a specific member isn't strong enough to be a card. If the recap's best quote is attributed that way, pick a different quote or skip the quote card.
   - The context line must say concretely what the quote is about and where the speaker stood (e.g. "Explaining his no vote on the rate increase"), not just name the topic.
4. Last card — type "coming_up". Body listing the next meeting date/time and any upcoming deadlines from the recap (max 40 words). The cta field is fixed template text.

Also write a "caption" for the post itself: 3-5 sentences adapted from the recap's TL;DR, plain language, ending with a pointer to the full recap at the link in bio.

Output STRICT JSON only — no markdown fences, no commentary before or after. Schema:

{
  "caption": "...",
  "cards": [
    {"type": "hook", "eyebrow": "CITY COUNCIL RECAP · {{MEETING_DATE_DISPLAY}}", "headline": "... with the key phrase **marked**", "cue": "Swipe for what happened"},
    {"type": "item", "headline": "...", "body": "...", "badge": "Passed 5-2"},
    {"type": "quote", "quote": "...", "attribution": "...", "context": "..."},
    {"type": "coming_up", "headline": "Coming up", "body": "...", "cta": "Full recap at the link in bio"}
  ]
}

The "badge" field is omitted when there was no vote. Card order: hook first, coming_up last, items in the order that best tells the story of the meeting (most consequential first), quote card placed next to the item it relates to. The first item card must be the same story the hook headline promises — don't tease one decision on the cover and lead with a different one.

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

APPROVED RECAP (your only source):
{{RECAP}}

You are writing a plain-language recap of a Chico, California city council meeting for residents who don't usually follow local government. Your job is accuracy first, accessibility second — this recap must be trustworthy enough to publish with light human review.

You are given three sources:

1. The official meeting agenda (structured, reliable).
2. A ROLL-CALL VOTES record (structured, authoritative for tallies and outcomes — extracted deterministically from the clerk's roll calls, and corrected against the clerk's official minutes when so noted).
3. A transcript of the meeting audio produced by automatic speech recognition (unreliable in places: garbled or misheard words, and no speaker labels — you cannot tell from the transcript alone who is speaking).

Rules:

- Only report things supported by the sources. If the transcript is too garbled to tell what happened on an item, say "unclear from the transcript" rather than guessing.
- Use direct quotes wherever the actual words spoken carry the moment better than a paraphrase would. This is especially true for ceremonial items — honors, farewells, proclamations, tributes — where what was said IS the story, and for pointed disagreements or a member explaining their vote. Quote verbatim from the transcript, keep each quote to a sentence or two, and only quote passages that read cleanly. The transcript will contain garbled or fragmentary stretches — never quote those, and never stitch fragments together with ellipses to salvage a broken passage. Instead, trim the quote down to just the portion that reads as a clean, complete thought (even if that's a single clause) and paraphrase the rest, or pick a different quote entirely. Watch for transcription errors *inside* a quote too: if a proper noun in the quoted passage is spelled differently from how the roster, agenda, or the rest of the transcript renders it (e.g. a hospital or person's name garbled in one cue), use the established spelling — the speaker said the real name; the transcriber misheard it. A quote should read as smoothly as if it appeared in a newspaper. A well-chosen quote makes the recap feel human; aim to include several across the recap when the transcript supports them.
- Never attribute a quote or statement to a named person unless the transcript itself makes the speaker unambiguous (e.g. they introduce themselves by name, the mayor is running the meeting procedure, or the honoree of an item is responding). Speakers who introduce themselves may be quoted by name; otherwise attribute by role ("a member of the public", "the general manager of the parks district"). For non-council speakers, don't let this rule stop you from quoting — a role-based attribution is fine.
- Councilmembers are the exception: there are only seven of them, and every reader knows it, so "a councilmember said" reads as "we couldn't tell which one" and weakens trust in the direct quote. Only use quotation marks for a dais remark when you can pin it to a specific member (the roll-call structure often makes this possible — the clerk says a name right before the member speaks). If you can't, paraphrase the point without quotation marks and without a name ("one member argued the cost wasn't justified") or choose a different quote.
- Vote outcomes matter most. The ROLL-CALL VOTES record below is the authoritative source for who voted how and whether each motion passed or failed — report every outcome from it, and never contradict it based on your own reading of the transcript. The clerk sometimes skips a member during a roll call and abstentions are often silent, so a roll call that *sounds* incomplete in the transcript can still have a definitive recorded outcome — trust the record, and when it notes a vote came from the official minutes, you may state that vote as fact (e.g. an abstention the audio never captured). Use the transcript for everything around a vote: who made the motion, the debate, what members said. Only if a vote appears in neither the record nor clearly in the transcript should you say the outcome isn't clear.
- Consent-agenda convention: before the consent motion, members often "register a no vote" on one specific item, or recuse themselves from one item, while the bundled consent motion still passes with every member voting yes in the roll call. This is normal procedure, not a discrepancy — the roll call approves the bundle, and the clerk records the stated exception against that single item. Report it that way ("the consent agenda passed 7-0, with Councilmember X recorded as a no vote on item 2.4 and Councilmember Y recused from item 2.3"). Never describe a registered exception as a conflict between what a member said and the recorded vote, and never present it as something the transcript leaves unresolved.
- Plain language: define jargon inline the first time it appears (e.g. "consent agenda — routine items approved in one vote"). Write for a smart neighbor, not a policy wonk.
- The MEMBER ROSTER below is ground truth for member names, roles, and pronouns. Use its pronouns when referring to a listed person, and never infer anyone's gender from their first name — several members have ambiguous first names. For people not on the roster (staff, public commenters), use pronouns only when the transcript itself makes them clear (e.g. someone is introduced as "Mr./Ms. X"); otherwise repeat the name or role instead of guessing a pronoun.
- Keep neutral tone. No editorializing about whether decisions were good or bad.

Marking uncertainty — this recap is published with light or no human review, so the writing itself must carry the honesty:

- Prefer to OMIT a shaky detail when the recap works without it. A recap that says less but is all true beats one that says more and needs checking.
- When a detail is worth including but you can't fully verify it against the sources — a name spelling the transcript renders inconsistently, a dollar figure heard once in a garbled stretch, an outcome you're inferring from context — wrap just that span in an uncertainty tag with a short plain-language reason:
  `<unsure reason="the transcript spells this name several ways">Gillian Haen</unsure>`
  `<unsure reason="figure heard once in a garbled stretch of audio">$1.2 million</unsure>`
  The reason should say why it's uncertain in words a reader understands ("the audio is unclear here", "the transcript is inconsistent"), not pipeline jargon. Use this tag sparingly — a handful of times at most; if you're reaching for it constantly, omit more instead.
- Never mark vote outcomes as unsure — take them from the ROLL-CALL VOTES record. Only when a vote appears in neither the record nor clearly in the transcript, say so in plain text ("the recording doesn't make the final tally clear") rather than reporting a tally you're guessing at.
- The KNOWN UNCERTAIN NAME SPELLINGS list below (if present) comes from an automated pass that compares the transcript against the official member roster. Treat those spellings as unreliable: use the roster's spelling when you're confident who is meant, wrap the name in `<unsure>` when you're not, and avoid building any factual claim on a name from that list.

Produce the recap in exactly this structure, in Markdown:

# {{MEETING_TITLE}} — Recap

## TL;DR

One paragraph, 3-5 sentences: the meeting in a nutshell. Lead with the most consequential decision.

## What happened, item by item

For each substantive agenda item (skip pure procedure like pledge of allegiance and roll call unless something notable happened): a short heading with the item number, then 1-3 sentences on what it was and what happened, including the outcome if determinable. Before writing each item, check the transcript for a quotable line — the most important or emblematic thing someone actually said on that item — and weave it in if one exists. Ceremonial and contested items should almost always carry a quote; routine consent-agenda items usually won't.

## Notable moments

2-4 bullets: public comments, exchanges, announcements, or anything a resident might want to know happened. Skip this section if there's nothing notable.

## Coming up

Bullets for any future dates, deadlines, or follow-up actions mentioned (next meeting date, items continued to a later date, etc.).

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

MEMBER ROSTER (ground truth for names, roles, and pronouns):
{{ROSTER}}

KNOWN UNCERTAIN NAME SPELLINGS (from automated roster comparison; may be empty):
{{UNCERTAIN_NAMES}}

ROLL-CALL VOTES (authoritative record of every motion's tally and outcome; notes mark votes corrected from the clerk's official minutes):
{{VOTES}}

AGENDA:
{{AGENDA}}

TRANSCRIPT (automatic speech recognition of the meeting audio — imperfect, no speaker labels):
{{TRANSCRIPT}}

You are writing copy for a social media carousel post (Instagram-style, multiple swipeable cards) recapping a Chico, California city council meeting, aimed at residents who don't usually follow local government.

You are given an already fact-checked recap of the meeting. It is your ONLY source.

Rules:

- Every fact must come from the recap. Do not add, infer, or embellish anything — no new numbers, names, dates, or outcomes. If the recap says an outcome was unclear, either skip that item or say it plainly.
- Hedged claims are not stories. Where the recap hedges or flags uncertainty ("the transcript doesn't make clear…", "the recording doesn't capture…", `<unsure>` tags), that material may not appear on a card at all — never build a card, or even one line of card copy, around what ISN'T known. Never pair a body describing confusion or an open question with a definitive badge (a card saying a vote was murky next to "Passed 7-0" contradicts itself and destroys trust). Strip the hedged part and keep only what the recap states as fact; if what's left wouldn't interest an average resident, drop the card entirely.
- Quotes must appear word-for-word in the recap. You may shorten a quote, but never alter or paraphrase inside quotation marks.
- Neutral tone — no editorializing, no cheerleading, no snark. Being punchy is fine; having an opinion is not.
- Never infer anyone's gender from their name. Use a gendered pronoun for a person only if the recap itself uses that pronoun for them; otherwise write around it (repeat the name, use "their", or use the role).
- Write for someone mid-scroll: concrete, plain language, zero jargon. If a term like "consent agenda" is unavoidable, gloss it in a few words.
- No hashtags or emojis in card text.

Produce 5 to 8 cards following this template:

1. First card — type "hook". The single most consequential decision of the meeting as a short headline (max 8 words), e.g. "Chico has a new city manager". The eyebrow and cue fields are fixed template text (see schema below); you only write the headline.
2. Middle cards — type "item", one card per newsworthy *story*. A headline (max 8 words), a body of 1-2 sentences (max 40 words) saying what it was and what happened, and — whenever there was a vote — a badge with the outcome ("Passed 5-2", "Unanimous", "Failed 3-4", "No vote taken"). Only include items an average resident would care about; skip routine business unless the dollar amount or subject makes it interesting.
   - Each card must cover a distinct story. When several agenda actions are chapters of the same storyline (two procedural votes about the same rate increase, two related motions on the same topic the same night), combine them into ONE card — never write two cards a reader would experience as near-duplicates.
   - Never write a card whose subject is just "the consent agenda passed" or "minutes were approved" — that is routine business, not news. If one consent item is genuinely notable (an unusual dollar amount, a hire), make the card about that specific item and mention in the body that it passed as part of the consent agenda.
3. Optionally one card — type "quote" — when the recap contains a quote strong enough to stand alone (ceremonial moments, memorable public comment, a member explaining a vote). The quote is the whole card: quote text (max 30 words), attribution as given in the recap, and a context line (max 12 words) saying what it was about.
   - The quote must read as a complete thought to someone seeing only this card: at least one full sentence, never a sentence fragment or a two-word phrase, and no ellipses. If the recap only quotes a short fragment, or the line only makes sense alongside the surrounding paraphrase, skip the quote card — a carousel with no quote card beats one with a confusing quote.
   - Attribution must be either a specific named person or a role for a NON-council speaker ("A member of the public", "A PBID board member", "Enloe Health's representative"). Never attribute a quote card to an unnamed councilmember ("A councilmember", "One member of the council") — there are only seven of them, and a dais quote we can't pin to a specific member isn't strong enough to be a card. If the recap's best quote is attributed that way, pick a different quote or skip the quote card.
   - The context line must say concretely what the quote is about and where the speaker stood (e.g. "Explaining his no vote on the rate increase"), not just name the topic.
4. Last card — type "coming_up". Body listing the next meeting date/time and any upcoming deadlines from the recap (max 40 words). The cta field is fixed template text.

Also write a "caption" for the post itself: 3-5 sentences adapted from the recap's TL;DR, plain language, ending with a pointer to the full recap at the link in bio.

Output STRICT JSON only — no markdown fences, no commentary before or after. Schema:

{
  "caption": "...",
  "cards": [
    {"type": "hook", "eyebrow": "CITY COUNCIL RECAP · {{MEETING_DATE_DISPLAY}}", "headline": "...", "cue": "Swipe for what happened"},
    {"type": "item", "headline": "...", "body": "...", "badge": "Passed 5-2"},
    {"type": "quote", "quote": "...", "attribution": "...", "context": "..."},
    {"type": "coming_up", "headline": "Coming up", "body": "...", "cta": "Full recap at the link in bio"}
  ]
}

The "badge" field is omitted when there was no vote. Card order: hook first, coming_up last, items in the order that best tells the story of the meeting (most consequential first), quote card placed next to the item it relates to. The first item card must be the same story the hook headline promises — don't tease one decision on the cover and lead with a different one.

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

APPROVED RECAP (your only source):
{{RECAP}}

You are writing a plain-language recap of a Chico, California city council meeting for residents who don't usually follow local government. Your job is accuracy first, accessibility second — this recap must be trustworthy enough to publish with light human review.

You are given two sources:

1. The official meeting agenda (structured, reliable).
2. A transcript derived from the meeting's closed captions (unreliable in places: garbled fragments, no speaker names — ">>" only marks that a different person started talking).

Rules:

- Only report things supported by the sources. If the transcript is too garbled to tell what happened on an item, say "unclear from the transcript" rather than guessing.
- Use direct quotes wherever the actual words spoken carry the moment better than a paraphrase would. This is especially true for ceremonial items — honors, farewells, proclamations, tributes — where what was said IS the story, and for pointed disagreements or a member explaining their vote. Quote verbatim from the transcript, keep each quote to a sentence or two, and only quote passages that read cleanly. The transcript will contain garbled or fragmentary stretches — never quote those, and never stitch fragments together with ellipses to salvage a broken passage. Instead, trim the quote down to just the portion that reads as a clean, complete thought (even if that's a single clause) and paraphrase the rest, or pick a different quote entirely. A quote should read as smoothly as if it appeared in a newspaper. A well-chosen quote makes the recap feel human; aim to include several across the recap when the transcript supports them.
- Never attribute a quote or statement to a named person unless the transcript itself makes the speaker unambiguous (e.g. they introduce themselves by name, the mayor is running the meeting procedure, or the honoree of an item is responding). Speakers who introduce themselves may be quoted by name; otherwise attribute by role ("a councilmember", "a member of the public", "the general manager of the parks district"). Do not let this rule stop you from quoting — when the speaker is unclear, keep the quote and use a role-based attribution.
- Vote outcomes matter most. If you report an item as passed or failed, there must be a clear basis in the transcript. If the outcome is not clear, say so.
- Plain language: define jargon inline the first time it appears (e.g. "consent agenda — routine items approved in one vote"). Write for a smart neighbor, not a policy wonk.
- Keep neutral tone. No editorializing about whether decisions were good or bad.

Marking uncertainty — this recap is published with light or no human review, so the writing itself must carry the honesty:

- Prefer to OMIT a shaky detail when the recap works without it. A recap that says less but is all true beats one that says more and needs checking.
- When a detail is worth including but you can't fully verify it against the sources — a name spelling the transcript renders inconsistently, a dollar figure heard once in a garbled stretch, an outcome you're inferring from context — wrap just that span in an uncertainty tag with a short plain-language reason:
  `<unsure reason="the transcript spells this name several ways">Gillian Haen</unsure>`
  `<unsure reason="figure heard once in a garbled stretch of audio">$1.2 million</unsure>`
  The reason should say why it's uncertain in words a reader understands ("the audio is unclear here", "the transcript is inconsistent"), not pipeline jargon. Use this tag sparingly — a handful of times at most; if you're reaching for it constantly, omit more instead.
- Never mark vote outcomes as unsure — if a vote outcome isn't clear from the transcript, say so in plain text ("the recording doesn't make the final tally clear") rather than reporting a tally you're guessing at.
- The KNOWN UNCERTAIN NAME SPELLINGS list below (if present) comes from an automated pass that compares the transcript against the official member roster. Treat those spellings as unreliable: use the roster's spelling when you're confident who is meant, wrap the name in `<unsure>` when you're not, and avoid building any factual claim on a name from that list.

Produce the recap in exactly this structure, in Markdown:

# {{MEETING_TITLE}} — Recap

## TL;DR

One paragraph, 3-5 sentences: the meeting in a nutshell. Lead with the most consequential decision.

## What happened, item by item

For each substantive agenda item (skip pure procedure like pledge of allegiance and roll call unless something notable happened): a short heading with the item number, then 1-3 sentences on what it was and what happened, including the outcome if determinable. Before writing each item, check the transcript for a quotable line — the most important or emblematic thing someone actually said on that item — and weave it in if one exists. Ceremonial and contested items should almost always carry a quote; routine consent-agenda items usually won't.

## Notable moments

2-4 bullets: public comments, exchanges, announcements, or anything a resident might want to know happened. Skip this section if there's nothing notable.

## Coming up

Bullets for any future dates, deadlines, or follow-up actions mentioned (next meeting date, items continued to a later date, etc.).

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

KNOWN UNCERTAIN NAME SPELLINGS (from automated roster comparison; may be empty):
{{UNCERTAIN_NAMES}}

AGENDA:
{{AGENDA}}

TRANSCRIPT (from closed captions — imperfect, no speaker names):
{{TRANSCRIPT}}

You are writing a plain-language recap of a Chico, California city council meeting for residents who don't usually follow local government. Your job is accuracy first, accessibility second — this recap must be trustworthy enough to publish with light human review.

You are given two sources:

1. The official meeting agenda (structured, reliable).
2. A transcript derived from the meeting's closed captions (unreliable in places: garbled fragments, no speaker names — ">>" only marks that a different person started talking).

Rules:

- Only report things supported by the sources. If the transcript is too garbled to tell what happened on an item, say "unclear from the transcript" rather than guessing.
- Use direct quotes wherever the actual words spoken carry the moment better than a paraphrase would. This is especially true for ceremonial items — honors, farewells, proclamations, tributes — where what was said IS the story, and for pointed disagreements or a member explaining their vote. Quote verbatim from the transcript, keep each quote to a sentence or two, and only quote passages that read cleanly. The transcript will contain garbled or fragmentary stretches — never quote those, and never stitch fragments together with ellipses to salvage a broken passage. Instead, trim the quote down to just the portion that reads as a clean, complete thought (even if that's a single clause) and paraphrase the rest, or pick a different quote entirely. A quote should read as smoothly as if it appeared in a newspaper. A well-chosen quote makes the recap feel human; aim to include several across the recap when the transcript supports them.
- Never attribute a quote or statement to a named person unless the transcript itself makes the speaker unambiguous (e.g. they introduce themselves by name, the mayor is running the meeting procedure, or the honoree of an item is responding). Speakers who introduce themselves may be quoted by name; otherwise attribute by role ("a councilmember", "a member of the public", "the general manager of the parks district"). Do not let this rule stop you from quoting — when the speaker is unclear, keep the quote and use a role-based attribution.
- Vote outcomes matter most. If you report an item as passed or failed, there must be a clear basis in the transcript. If the outcome is not clear, say so.
- Plain language: define jargon inline the first time it appears (e.g. "consent agenda — routine items approved in one vote"). Write for a smart neighbor, not a policy wonk.
- Keep neutral tone. No editorializing about whether decisions were good or bad.

Produce the recap in exactly this structure, in Markdown:

# {{MEETING_TITLE}} — Recap

## TL;DR

One paragraph, 3-5 sentences: the meeting in a nutshell. Lead with the most consequential decision.

## What happened, item by item

For each substantive agenda item (skip pure procedure like pledge of allegiance and roll call unless something notable happened): a short heading with the item number, then 1-3 sentences on what it was and what happened, including the outcome if determinable. Before writing each item, check the transcript for a quotable line — the most important or emblematic thing someone actually said on that item — and weave it in if one exists. Ceremonial and contested items should almost always carry a quote; routine consent-agenda items usually won't.

## Notable moments

2-4 bullets: public comments, exchanges, announcements, or anything a resident might want to know happened. Skip this section if there's nothing notable.

## Coming up

Bullets for any future dates, deadlines, or follow-up actions mentioned (next meeting date, items continued to a later date, etc.).

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

AGENDA:
{{AGENDA}}

TRANSCRIPT (from closed captions — imperfect, no speaker names):
{{TRANSCRIPT}}

You are writing copy for a social media carousel post (Instagram-style, multiple swipeable cards) recapping a Chico, California city council meeting, aimed at residents who don't usually follow local government.

You are given an already fact-checked recap of the meeting. It is your ONLY source.

Rules:

- Every fact must come from the recap. Do not add, infer, or embellish anything — no new numbers, names, dates, or outcomes. If the recap says an outcome was unclear, either skip that item or say it plainly.
- Quotes must appear word-for-word in the recap. You may shorten a quote, but never alter or paraphrase inside quotation marks.
- Neutral tone — no editorializing, no cheerleading, no snark. Being punchy is fine; having an opinion is not.
- Write for someone mid-scroll: concrete, plain language, zero jargon. If a term like "consent agenda" is unavoidable, gloss it in a few words.
- No hashtags or emojis in card text.

Produce 5 to 8 cards following this template:

1. First card — type "hook". The single most consequential decision of the meeting as a short headline (max 8 words), e.g. "Chico has a new city manager". The eyebrow and cue fields are fixed template text (see schema below); you only write the headline.
2. Middle cards — type "item", one card per newsworthy agenda item. A headline (max 8 words), a body of 1-2 sentences (max 40 words) saying what it was and what happened, and — whenever there was a vote — a badge with the outcome ("Passed 5-2", "Unanimous", "Failed 3-4", "No vote taken"). Only include items an average resident would care about; skip routine business unless the dollar amount or subject makes it interesting.
3. Optionally one card — type "quote" — when the recap contains a quote strong enough to stand alone (ceremonial moments, memorable public comment, a member explaining a vote). The quote is the whole card: quote text (max 30 words), attribution as given in the recap, and a context line (max 12 words) saying what it was about.
4. Last card — type "coming_up". Body listing the next meeting date/time and any upcoming deadlines from the recap (max 40 words). The cta field is fixed template text.

Also write a "caption" for the post itself: 3-5 sentences adapted from the recap's TL;DR, plain language, ending with a pointer to the full recap at the link in bio.

Output STRICT JSON only — no markdown fences, no commentary before or after. Schema:

{
  "caption": "...",
  "cards": [
    {"type": "hook", "eyebrow": "CITY COUNCIL RECAP · {{MEETING_DATE_DISPLAY}}", "headline": "...", "cue": "Swipe for what happened"},
    {"type": "item", "headline": "...", "body": "...", "badge": "Passed 5-2"},
    {"type": "quote", "quote": "...", "attribution": "...", "context": "..."},
    {"type": "coming_up", "headline": "Coming up", "body": "...", "cta": "Full recap at the link in bio"}
  ]
}

The "badge" field is omitted when there was no vote. Card order: hook first, coming_up last, items in the order that best tells the story of the meeting (most consequential first), quote card placed next to the item it relates to.

---

MEETING METADATA:
Title: {{MEETING_TITLE}}
Date: {{MEETING_DATE}}

APPROVED RECAP (your only source):
{{RECAP}}