Check competitor research notes for weak evidence, unsupported claims, stale data, and hallucination risk.
This is a working analyst brief. Sources go in. Patterns, risks, and decisions come out.
You are a skeptical research editor.
Audit this competitor research draft for verification risk.
Draft:
{{sources}}
Context:
{{market}}
Return:
1. Claims that are supported by evidence.
2. Claims that need a source.
3. Claims that look like AI overreach.
4. Claims that may be stale.
5. Numbers, dates, or pricing details to re-check manually.
6. Suggested edits to make the draft more honest.
7. A final pass/fail readiness note.
Rules:
- Be strict.
- Do not add new claims.
- If the draft lacks sources, say so plainly.
Advanced AI technique settings:
- Source-grounded context pack: Build a source table first with source, date checked, claim, confidence, and business meaning. Use only that table for the final recommendations.
- Cited answer-engine check: Run a cited search pass for current facts. Keep URLs, dates checked, and quoted claims separate from your own pasted evidence, then downgrade anything without a reliable source.
- Source notebook workflow: If the source set is large, create a source notebook first. Ask only questions answerable from that notebook, export the source-backed claims, and paste those claims into the final prompt.
- Evidence rubric: Score each important finding by evidence strength, relevance, business impact, and reversibility before recommending an action.
- Structured output contract: Return the main output as tables or labeled sections with fixed columns: finding, evidence, confidence, risk, action, and verification needed.
- Cross-model or second-pass review: Run the output through a separate verifier pass, or compare it with an independent model or reviewer, then keep only findings supported by the source pack.Copy the prompt. Fill the variables. Then check the output for real.
These are selected for this specific competitor research job. Use the prompt-ready instruction when it helps, and skip it when the condition does not fit.
Use when: Use when the answer depends on competitor pages, screenshots, ads, pricing, SEO exports, or reviews.
Prompt move: Build a source table first with source, date checked, claim, confidence, and business meaning. Use only that table for the final recommendations.
Skip when: Skip only for brainstorming with no factual claims.
Use when: Use when the prompt depends on current web facts, public pricing, recently changed pages, search results, product releases, or market claims.
Prompt move: Run a cited search pass for current facts. Keep URLs, dates checked, and quoted claims separate from your own pasted evidence, then downgrade anything without a reliable source.
Skip when: Skip when all evidence is private, pasted, or already date-stamped.
Use when: Use when you have a stable pack of competitor pages, PDFs, call notes, screenshots, exports, or long research notes.
Prompt move: If the source set is large, create a source notebook first. Ask only questions answerable from that notebook, export the source-backed claims, and paste those claims into the final prompt.
Skip when: Skip when you only have one or two short sources.
Use when: Use when recommendations could change strategy, positioning, pricing, ads, or product priorities.
Prompt move: Score each important finding by evidence strength, relevance, business impact, and reversibility before recommending an action.
Skip when: Skip for prompts that only organize notes without recommending action.
Use when: Use when the output must be compared, reviewed, or turned into tasks.
Prompt move: Return the main output as tables or labeled sections with fixed columns: finding, evidence, confidence, risk, action, and verification needed.
Skip when: Skip when the desired output is narrative copy.
Use when: Use for high-stakes reports, pricing decisions, client deliverables, or public claims.
Prompt move: Run the output through a separate verifier pass, or compare it with an independent model or reviewer, then keep only findings supported by the source pack.
Skip when: Skip for fast internal drafts.
| Variable | Meaning | Type | Example |
|---|---|---|---|
{{sources}} | The draft output and any attached source notes | text | Competitor report draft plus links |
{{market}} | Market or research context | string | AI sales coaching tools |
The output below is fictional. It shows the shape you are looking for, not a real competitor result.
market = AI sales coaching tools
sources = competitor report draft with links and screenshot notesFictional example output:
Supported:
- Competitor added a new "Call scoring" page, source URL included.
Needs source:
- "They are targeting enterprise teams now."
AI overreach risk:
- The report says the new page "will improve conversion." There is no conversion evidence.
Readiness:
Fail for external sharing until pricing and enterprise-positioning claims are re-checked.It changes the AI's job from writer to skeptic.
It protects the team from clean but unsupported claims.
It gives a pass/fail note instead of vague edits.
Paste the page copy, ad screenshots, pricing table, SEO notes, or transcript first.
Paste the source URLs, screenshots, and dates next to the draft.
Ask it to flag what you need to check manually.
Re-check time-sensitive claims before publishing.
Every factual claim has a source or is marked as unverified.
Pricing, dates, and product claims were checked on the original source.
The output separates observation from interpretation.
The output gives actions you can reject, edit, or test.
Nothing is treated as final just because an AI tool wrote it.
Paste your draft and sources into the prompt.
Fix or remove every unsupported claim.
Only share the report when the pass/fail note is clean enough.