Long-Form Article Brief With Source Discovery Plan and Citation Table

Creates an editorial brief and outline for a researched article. It includes a source discovery plan, an evidence review template, and a citation table, without pretending any live browsing took place.

You get: Brief summary, thesis comparison table and source discovery plan

More like this

The prompt

long-form-article-brief-with-source-discovery-plan-and-citation-table.md
Role: You are an editorial researcher and managing editor preparing a brief for a long-form article.

Context: I am writing about {topic} for {audience} at {publication_or_brand}. The job to be done is to decide whether the article is worth commissioning or writing, which thesis to pursue, and what evidence is needed before drafting. You have no live web access in this conversation unless I state otherwise, so do not claim to have searched or verified anything.

Task: Produce an article brief, a source discovery plan I can run myself, an evidence review template, a citation table, and a recommendation.

Inputs:
- Topic and angle: {topic}
- Audience and what they already know: {audience}
- Goal of the piece: {goal}
- Target length and deadline: {length_and_deadline}
- Sources I already have (title, author, date, link, key point): {existing_sources}
- Constraints (legal, brand, sensitivities): {constraints}
If inputs are missing, list them first and continue with labeled assumptions.

Workflow:
1. Define the reader's question and the decision the article should help them make.
2. List assumptions separately from provided facts.
3. Offer 3 candidate theses with strengths, weaknesses, and the evidence each would require.
4. Build a source discovery plan: source types to look for (primary data, peer-reviewed work, official reports, practitioner interviews, counterexamples), 8-12 search queries, and where to run them (such as Google Scholar, government or industry databases, and library catalogs). Mark every query as 'not yet run'.
5. Create an evidence review table for me to fill in, plus a scoring rubric for source quality (authority, recency, method transparency, conflicts of interest).
6. Score the sources I supplied using the rubric and show the reasoning.
7. Draft an outline with section goals and the evidence each section needs.
8. Recommend proceed, narrow, or pause, with reasons.

Constraints: Do not fabricate sources, quotes, statistics, or URLs. Use placeholders like 'to be found' for unknown citations. Separate what sources say from your interpretation. Note where evidence is thin or contested.

Output format:
1. Brief summary (reader question, decision, chosen thesis)
2. Assumptions and missing information
3. Thesis comparison table
4. Source discovery plan (query table: query, source type, where to run, status)
5. Citation table (ref id, source, claim supported, quality score, caveat)
6. Outline with evidence needs per section
7. Risks, gaps, and next actions (ordered, with time estimates)
8. Recommendation

Acceptance criteria:
- No citation appears that I did not supply, and unknown ones are marked 'to be found'.
- Each outline section lists the specific evidence required.
- At least one counterargument and how to handle it is included.
- The recommendation follows from the scoring and gaps.

Quality checks: Confirm every claim in the brief is tagged as sourced or assumed. Check the queries are specific enough to run. Check the thesis is falsifiable. State the biggest weakness of the plan.

Tool notes: In ChatGPT, if browsing is enabled, tell it to label results with the retrieval date and keep the tables separate from the narrative. In Claude, paste source text inside <source> tags for scoring. In Perplexity, run the query table one query at a time and paste the results back for scoring.

Example output

AI-written example

1. Brief summary

  • Reader question: Do four-day school weeks in rural districts save money without hurting learning?
  • Decision: Whether a school board member should back a pilot.
  • Chosen thesis (T2): Savings are small and real, while achievement effects vary by district, so boards should pilot with preset metrics. [assumed]

2. Assumptions and missing information

  • Provided: 3,500 words, due in 5 weeks, audience of rural school board members, brand is Prairie Ledger.
  • Assumed: Readers know budgets but not the research. No legal constraints beyond fair treatment of named districts.
  • Missing: Budget for interviews, and whether data journalism support is available.

3. Thesis comparison

ThesisStrengthWeaknessEvidence needed
T1: Saves little, harms learningClearLikely overstatedMulti-district outcome data
T2: Small savings, mixed effectsDefensibleLess punchyCost data plus outcome studies
T3: Works if paired with enrichmentActionableHard to falsifyComparisons of districts with and without enrichment

4. Source discovery plan (all: not yet run)

QueryTypeWhere
"four-day school week" achievement ruralPeer-reviewedGoogle Scholar
"four-day week" district cost savings auditOfficial reportState auditor sites
Four-day week attendance and teacher retentionPrimary dataState education dept. databases
Four-day week critiques, childcare burdenCounterexamplesLibrary catalog, news archives
Superintendent interview, 4-day adoptersPractitionerDirect outreach

(Full plan would list 8–12 queries.)

5. Citation table

RefSourceClaim supportedScore (/20)Caveat
R1Prairie Ledger reader survey, n=412, 2024Board members' top concern is childcare11Self-selected sample; method unclear
R2Facilities manager interview notes, 2025Utility savings are modest8Single anecdote; unverified figures
R3–R6To be foundAchievement, cost, retentionn/an/a

Scoring: authority, recency, method transparency, and conflicts of interest, each 0–5.

6. Outline with evidence needs

  1. Hook: a board vote scene. Needs one on-record board member.
  2. What boards hope for. Needs R1 plus cost audits (to be found).
  3. What the research says. Needs 2–3 peer-reviewed studies (to be found).
  4. Counterargument: "Savings justify any learning risk." Handle by quantifying savings against outcome ranges.
  5. Pilot design checklist. Needs expert interview.

7. Risks, gaps, next actions

  1. Run the query table, 3 hours.
  2. Score the results, 2 hours.
  3. Book two interviews, 1 week.
  • Biggest weakness: the thesis rests on studies not yet found.

8. Recommendation
Narrow. Only two weak sources are in hand, so limit the scope to cost and achievement until R3–R6 are scored at 14 or higher.

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

Tips and common edits

Use this before drafting. Run the discovery queries yourself, or enable a browsing tool and say so in the inputs, then return the results for the evidence review. Check every citation against the original source.

Questions about this prompt

More in Writing

AI Visibility Audit: Brand Mention and Citation Test Plan for AI Answer Engines

Design and analyze a repeatable prompt test set that checks how AI answer engines mention and cite your brand. It turns results into a citation table, evidence-based gap findings, and prioritized page and entity fixes.

Competitor and Audience Evidence Review with Citation Table and Go/No-Go Brief

A research workflow that plans online source discovery, scores evidence, builds a citation table, and ends with a decision brief, without pretending live browsing happened.

Competitor UX Pattern Research Plan with Evidence Table and Design Recommendation

Builds a source discovery plan, evidence log, citation table, and synthesis for comparing UX patterns across competitors, without claiming live browsing.

GEO Page Audit: Citation Likelihood Score and Rewrites for AI Answers

Get a scored estimate of how citable your page is to ChatGPT, Gemini and Perplexity, plus a summary box, question headings, fact prompts and an FAQ.

Pre-Outreach Account Research Brief with Source Plan and Citation Table

Turns pasted account material and a source discovery plan into a evidence-labeled research brief. It helps a rep decide whether to pursue an account, which persona to target, and which outreach angle to use.

Productivity Tool Selection: Source Discovery, Evidence Review, and Citation Table

A research workflow to choose between candidate productivity or automation tools. It plans online source discovery, structures evidence review in a citation table, and ends in a decision memo without claiming live browsing took place.

Software Vendor Due Diligence Brief with Cited Evidence Review

Guides a vendor shortlist review: finds primary sources like docs, security pages, and pricing, scores vendors on your criteria, and flags risks and open questions before purchase.

Trending

Developmental Edit Memo for an Essay Draft With Revise-or-Cut Decisions

Gives a draft essay a structured developmental edit: thesis check, paragraph-by-paragraph audit, and a prioritized revision plan so you can decide what to keep, rewrite, or cut before line editing.

ATS Resume Tailor: Keyword Match Without Exaggeration

Rewrites resume bullets to mirror a job posting's keywords only where they are true, and lists the requirements you cannot honestly claim.

Cut 30 Percent: Tighten Text and Show What Was Removed

Tightens an overlong text by about 30 percent without losing meaning, then lists what was cut and why.

Firm but Kind Reply to a Difficult Email

Drafts a calm, polite reply that holds your stated boundary and is hard to misread, with a short version and a misread check.

LinkedIn Headline and About Rewrite Around Measurable Results

Rewrites your LinkedIn About section around measurable achievements for a target role and offers three headline options.