Build a Citation-Verified Policy Brief From Pasted Primary Sources

Turn pasted primary documents into a strict policy brief where every claim carries a verbatim-checked source tag, an evidence grade, and a log of unsupported gaps.

You getSource Registry, executive Summary and verified Findings

Prompt

Prompt
Act as a senior policy analyst and research auditor. I will paste primary source documents right after this message. Build a citation-verified policy brief using strictly the pasted text.

Rules:
1. Ban outside knowledge. Never add facts, dates, or definitions absent from the pasted sources.
2. Label each pasted source in order as (S1), (S2), and so on, and attach the matching ID to every factual claim.
3. Anchor every claim to a short verbatim quote from its source. If a point requires inference, mark it Inferred and state the exact leap.
4. Grade each finding as Strong (direct data or statutory text), Moderate (limited sample or indirect reporting), or Weak (anecdote or unverified claim).
5. Record unanswered questions and missing data in an Unsupported Gaps log instead of guessing.

Output format:
- Source Registry: table with columns ID, Title, Date, and Scope.
- Executive Summary: 3 bullets, each ending with a source ID and evidence grade.
- Verified Findings: thematic bullets pairing each claim with its source ID, verbatim quote, and grade.
- Policy Options: actions supported strictly by the text, including cited trade-offs.
- Unsupported Gaps: numbered list of missing evidence or unresolved conflicts.

End with one line noting source contradictions, truncation risks, or missing context in the pasted material.

Example output

At a glanceTwo sources behind the policy briefSource registry for the Alder Avenue bus-lane review
ItemS1 Pilot EvaluationS2 Merchant Survey
DateMarch 2025February 2025
Data typeGPS transit logs, traffic countsSelf-reported survey
Scope14 blocks38 storefront owners
Key findingPeak bus times down 19%63% saw lower foot traffic
Evidence gradeStrongModerate

Example for: a municipal transit director synthesizing two pasted primary documents—a 2025 city bus-lane pilot report and a downtown merchants association survey—ahead of a city council vote.

Source Registry
IDTitleDateScope
(S1)Alder Avenue Bus-Lane 6-Month Pilot EvaluationMarch 2025Automated GPS transit logs and traffic counts across 14 blocks
(S2)Downtown Merchants Association Curb-Access SurveyFebruary 2025Self-reported survey of 38 storefront owners along Alder Avenue
Executive Summary
  • Peak-hour bus travel times on Alder Avenue fell by 19 percent during the six-month pilot (S1, Strong).
  • Delivery-truck double-parking citations rose 34 percent after curbside loading zones were removed (S1, Strong).
  • A majority of surveyed merchants reported lower weekday foot traffic, though no point-of-sale revenue records were collected (S2, Moderate).
Verified Findings
  • Transit Reliability: Average morning commute bus speeds increased from 9.4 mph to 11.6 mph (S1, Strong). Verbatim anchor: "mean weekday AM speed rose from 9.4 mph to 11.6 mph across 1,420 logged trips."
  • Curbside Freight Friction: Removing 18 metered loading spaces shifted commercial deliveries into side alleys and travel lanes (S1, Strong). Verbatim anchor: "citations for commercial double-parking climbed 34 percent over the prior year baseline."
  • Merchant Sentiment: Twenty-four of 38 respondents reported a perceived drop in weekday walk-in customers (S2, Moderate). Verbatim anchor: "63 percent of participating owners stated weekday foot traffic felt lower than autumn 2024."
Policy Options
  • Retain the bus lane with dedicated off-peak loading windows: Preserves the 19 percent transit speed gain (S1) while directly addressing the 34 percent spike in delivery citations (S1). Trade-off: requires enforcement staffing during peak transition hours (S1).
  • Revert to mixed-traffic lanes: Eliminates curb-access complaints cited by 63 percent of surveyed merchants (S2). Trade-off: forfeits documented bus speed improvements (S1).
Unsupported Gaps
  1. Neither source provides verified sales-tax or point-of-sale revenue data to confirm whether perceived foot-traffic drops reduced merchant income.
  2. Long-term emergency-vehicle response times on Alder Avenue are not reported in either document.
  3. The survey in (S2) does not disclose the total number of eligible storefronts, preventing a response-rate calculation.

Audit note: (S1) and (S2) conflict on downtown commercial vitality because (S2) relies on self-reported perception without revenue records, and neither document covers winter weather impacts.

Written by AI from this prompt. Your results will vary.

Tips and common edits

Why this works

  • Bans outside knowledge so the model cannot blend unverified training data into your primary-source synthesis.
  • Pairs every claim with a verbatim anchor quote and an explicit evidence grade, making hallucinations easy to spot.
  • Forces missing data into an Unsupported Gaps log instead of letting the model smooth over evidentiary holes.

Use this in Claude, Gemini, ChatGPT, or Perplexity when drafting high-stakes memos from raw PDFs, statutes, or survey reports. Paste the full text of your primary documents immediately after the prompt.

Common edits

  • Add a word-count cap to the Executive Summary if you need the brief to fit on a single printed page.
  • Swap the three-tier evidence scale for a domain-specific rubric such as GRADE for clinical or public-health reviews.

Make it repeatable

Keep using this prompt without pasting it in every time.

Keep exploring

More in AI Research