Deep Research Report Framework
Produce a report whose "conclusions are trustworthy, process is traceable, and the unknowns are explicitly marked." The quality floor of research is set by its sources, not its prose.
Workflow
- Define the question: write in one sentence what the report must answer. Add at most 3 sub-questions. Starting before the question is clear guarantees the research will sprawl.
- Tier your sources (tier before you search, so you don't believe whatever you find first):
- Primary: official docs, original papers, original filings, protocol/legal texts, measured data.
- Secondary: reputable press, industry reports, expert interviews.
- Tertiary: social-media posts, forum threads, aggregator sites — leads only, never evidence.
- Cross-verify: key conclusions need two or more independent sources. Two sources quoting the same origin don't count as independent. If no second source exists, downgrade the conclusion to "single-source claim" and mark it as such.
- Writing structure (conclusion first):
- Opening: 3–5 lines stating the core conclusions.
- Body: one section per sub-question, each in "conclusion → evidence → sources" order.
- Closing: uncertainty statement — "what wasn't found, what's speculation, under what conditions the conclusions change."
- Timestamps: date every key fact ("as of Sep 2026"). Undated information is treated as "possibly stale" by default.
Rules
- Mark speculation as speculation. Use "may", "likely", "unverified" — never dress speculation up with "clearly" or "it is well known".
- No tertiary source supports a core conclusion. A forum thread can point a direction, never serve as evidence.
- Every number in the report has a source. A number without a source is deleted, not rewritten.
- State "what you don't know" before "what you know" — honest uncertainty beats pretty certainty.
Minimal example (report outline template)
# Research Report: <Topic> (example outline)
**Core conclusions** (3–5 lines): …
## 1. Sub-question one
- Conclusion: …
- Evidence: … (source: primary/secondary, as of …)
- Evidence: … (second independent source)
## 2. Sub-question two
…
## Uncertainty statement
- Not found: …
- Single-source claims: … (one source only, pending verification)
- Invalidation conditions: if … changes, conclusion X in this report needs reassessment.
Anti-patterns
- ❌ Single-source verdicts: one social-media post becomes "research shows".
- ❌ Speculation as fact: "clearly" and "it is well known" are the most dangerous words in a research report.
- ❌ Undated facts: 2023 data presented as the current state; the conclusion quietly expires.
- ❌ Evidence pile with no conclusion: 20 sources listed, and the reader still can't tell what the author believes.
- ❌ Hiding the unknowns: burying what wasn't found makes the report look omniscient and plants landmines.
1---2name: deep-research-framework3description: Framework for deep research reports: define the question and tier sources first, cross-verify, then write conclusion-first reports with explicit uncertainty statements. Use when the user asks for a research report, topic investigation, or competitive analysis.4license: MIT5---67# Deep Research Report Framework89Produce a report whose "conclusions are trustworthy, process is traceable, and the unknowns are explicitly marked." The quality floor of research is set by its sources, not its prose.1011## Workflow12131. **Define the question**: write in one sentence what the report must answer. Add at most 3 sub-questions. Starting before the question is clear guarantees the research will sprawl.142. **Tier your sources** (tier before you search, so you don't believe whatever you find first):15 - Primary: official docs, original papers, original filings, protocol/legal texts, measured data.16 - Secondary: reputable press, industry reports, expert interviews.17 - Tertiary: social-media posts, forum threads, aggregator sites — leads only, never evidence.183. **Cross-verify**: key conclusions need two or more independent sources. Two sources quoting the same origin don't count as independent. If no second source exists, downgrade the conclusion to "single-source claim" and mark it as such.194. **Writing structure** (conclusion first):20 - Opening: 3–5 lines stating the core conclusions.21 - Body: one section per sub-question, each in "conclusion → evidence → sources" order.22 - Closing: uncertainty statement — "what wasn't found, what's speculation, under what conditions the conclusions change."235. **Timestamps**: date every key fact ("as of Sep 2026"). Undated information is treated as "possibly stale" by default.2425## Rules2627- Mark speculation as speculation. Use "may", "likely", "unverified" — never dress speculation up with "clearly" or "it is well known".28- No tertiary source supports a core conclusion. A forum thread can point a direction, never serve as evidence.29- Every number in the report has a source. A number without a source is deleted, not rewritten.30- State "what you don't know" before "what you know" — honest uncertainty beats pretty certainty.3132## Minimal example (report outline template)3334```markdown35# Research Report: <Topic> (example outline)3637**Core conclusions** (3–5 lines): …3839## 1. Sub-question one40- Conclusion: …41- Evidence: … (source: primary/secondary, as of …)42- Evidence: … (second independent source)4344## 2. Sub-question two45…4647## Uncertainty statement48- Not found: …49- Single-source claims: … (one source only, pending verification)50- Invalidation conditions: if … changes, conclusion X in this report needs reassessment.51```5253## Anti-patterns5455- ❌ Single-source verdicts: one social-media post becomes "research shows".56- ❌ Speculation as fact: "clearly" and "it is well known" are the most dangerous words in a research report.57- ❌ Undated facts: 2023 data presented as the current state; the conclusion quietly expires.58- ❌ Evidence pile with no conclusion: 20 sources listed, and the reader still can't tell what the author believes.59- ❌ Hiding the unknowns: burying what wasn't found makes the report look omniscient and plants landmines.
alapha888