Competitor Landscape Evidence Table with Source Tiers and Gaps

Builds a citation-backed competitor comparison for a specific market decision. It starts with source-discovery queries, tiers sources by reliability, and separates evidence from inference and open questions.

You get: Decision framing and assumptions, search queries to run and comparison table

More like this

The prompt

competitor-landscape-evidence-table-with-source-tiers-and-gaps.md
ROLE: You are a careful competitive intelligence analyst working inside Perplexity. You prioritize primary and recent sources over summaries and opinion.

CONTEXT: I am researching how {brand} compares with {competitors} in {market}. The answer must support this decision: {decision}. My audience for the findings is {audience}. Time window for relevance: {time_window}.

TASK: Produce a source-backed competitor analysis that helps me make the decision above. If search or browsing is not active in this session, say so plainly, provide only the search queries and a source checklist, and do not present anything as verified.

Inputs (ask me for any that are missing before analysis, then list your assumptions separately):
- Brand and competitor names, plus the product lines in scope
- Target customer segment and geography
- Comparison dimensions (default: pricing model, core features, target customers, positioning, integrations, security/compliance, recent launches, customer sentiment)
- Known facts I already hold, labelled as my own claims
- Sources to exclude, if any

Workflow:
1. Restate the job-to-be-done and the decision in two sentences. List assumptions separately.
2. Source discovery: give 8-12 search queries I can run online. Include site-restricted queries for each competitor's official pricing, docs, changelog, press, and investor or regulatory filings, plus queries for independent reviews and analyst commentary. In Perplexity, use Pro Search or Web focus for company pages and Academic focus only if peer-reviewed market research is relevant.
3. Source tiering: Tier 1 = primary (official pages, filings, documentation, changelogs, regulatory records). Tier 2 = reputable independent (established trade press, analyst reports, peer-reviewed work). Tier 3 = user-generated or opinion (forums, reviews, social posts). Prefer Tier 1, and label every source with its tier.
4. Extract facts per competitor per dimension. Record the exact source title, publisher, URL, publication date, and date checked. Write 'not found' rather than guessing.
5. Separate Evidence (directly stated by a source), Inference (your reasoning, with the evidence it rests on), Contradictions (where sources disagree, with both citations), and Unanswered questions.
6. Assess the decision: which findings most affect it, and how confident you are (High, Medium, or Low) with a one-line reason.

Constraints:
- Cite every factual claim inline with a number that maps to the citation table.
- Do not invent pricing, features, or statistics. Flag anything older than {time_window} as possibly stale.
- Do not rely on a single Tier 3 source for any material claim.
- Keep marketing language out of the findings.

Output format:
1. Decision framing and assumptions
2. Search queries to run (table: query, purpose, expected source type)
3. Comparison table (rows = dimensions, columns = brand and competitors; each cell has a short fact plus a citation number)
4. Evidence vs Inference vs Contradictions vs Unanswered questions (four labelled lists)
5. Citation table (number, source title, publisher, URL, publication date, date checked, tier)
6. Risks and missing information
7. Recommended next actions (max 5, each tied to the decision and with an owner role and effort level)

Acceptance criteria:
- Every table cell is either cited or marked 'not found'.
- At least 60% of citations are Tier 1 or Tier 2 where such sources exist.
- Inference is never mixed into the Evidence list.
- Next actions directly reduce uncertainty about {decision}.

Quality checks (run before finalizing and report the results in a short checklist):
- Do all URLs, dates, and publishers appear in the citation table?
- Are there claims without citations? Remove or flag them.
- Are any sources outdated relative to {time_window}?
- Did I state what I could not verify?
- Is the confidence rating justified?

Example output

AI-written example

Search status: browsing is not active in this session. I can't verify anything, so no comparison table, citations, or confidence rating is included. Below are the framing, queries, and a source checklist to run online.

1. Decision framing and assumptions

Brightledger needs to know how Tallyforge, Ledgerly, and Invoxa price and package accounts payable automation for US mid-market manufacturers (100-1,000 employees). This will inform whether the pricing committee should launch a usage-based pricing tier in Q3. Evidence should be from the last 12 months.

Assumptions: the product lines in scope are core AP automation only (not payments or spend management), the geography is the US, default comparison dimensions apply, and I hold no prior facts from you.

2. Search queries to run

#QueryPurposeExpected source
1site:tallyforge.example pricing OR plansPricing modelTier 1
2site:ledgerly.example pricing per invoice OR "per user"Usage vs seat pricingTier 1
3site:invoxa.example pricing OR "contact sales"Price transparencyTier 1
4site:tallyforge.example changelog OR "release notes"Recent launchesTier 1
5site:docs.ledgerly.example integrations ERPIntegration depthTier 1
6site:invoxa.example security SOC 2 OR trustComplianceTier 1
7Tallyforge OR Ledgerly OR Invoxa funding OR acquisition OR press release (past 12 months)Strategy shiftsTier 1/2
8accounts payable automation mid-market manufacturing pricing analyst reportMarket benchmarksTier 2
9Tallyforge OR Ledgerly OR Invoxa review pricing complaintsSentiment (corroborate only)Tier 3

Use Pro Search or Web focus. Academic focus isn't needed here.

3. Source checklist (record for each source)

  • [ ] Exact title, publisher, URL
  • [ ] Publication date and date checked
  • [ ] Tier (1 = official, filings, docs, changelogs; 2 = trade press, analysts; 3 = reviews, forums)
  • [ ] Older than 12 months? Flag as possibly stale
  • [ ] Material claims backed by at least one Tier 1 or 2 source (never a single Tier 3 source)
  • [ ] Target: at least 60% of citations Tier 1 or 2

4. Items to confirm once browsing is on

  • Whether each competitor publishes list pricing or gates it behind sales
  • Whether any competitor already offers per-invoice or consumption pricing
  • Which ERPs each supports natively (NetSuite, SAP, Microsoft Dynamics)
  • Any
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Run in Perplexity Pro Search with Web focus, then verify key figures by opening the Tier 1 links yourself. Use a Perplexity Space to keep the competitor list and exclusions persistent. If the tool returns no citations, treat the output as a search plan only.

Questions about this prompt

More in AI Research

Audience Research Source Discovery and Evidence Synthesis for Segment Prioritization

Guides you to plan source discovery, review the evidence you collect, build a citation table, and synthesize findings into a segment prioritization decision, without pretending the model browsed the web.

Competitor Landscape Research Plan with Source Discovery and Citation Table

Builds a source discovery plan, evidence review, citation table, and decision-ready synthesis for a competitor or market question, without pretending live browsing occurred.

Competitor Landscape Scan with Source-Backed Citation Table

Runs a structured competitor scan that starts with search queries, ranks sources by reliability, and ends with a cited comparison table and a positioning recommendation.

Two-to-Three Model Comparison Test Plan with 10 Prompts and Scoring Rubric

Creates a side-by-side test plan for choosing an AI model for your use case, with 10 test prompts, a scoring rubric and a blank results table.

Vendor Shortlist Decision Memo with Weighted Scoring and Source Citations

Guides a source-backed evaluation of software or service vendors against weighted criteria. Ends with a decision memo covering risks, open questions, and verification steps before purchase.

AI Paper Explainer with Evidence Table and Practical Takeaways

Turns a pasted AI paper abstract or text into a plain-language explanation of what is new, how it was tested, its limits and what to do with it.

Claim Verification Review with Contradiction Log and Confidence Rating

Tests a specific claim or statistic against primary and peer-reviewed sources. Produces an evidence grid, a contradiction log, and a calibrated confidence rating with explicit unknowns.

Weekly AI Tools Brief for a Team Lead with Dated Sources and One Experiment

Produces a dated, linked summary of the past week's AI model and tool releases that matter to your team, plus one experiment to run.

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.

Evidence Review Plan for a Classroom Teaching Strategy Decision

Guides source discovery, evidence review, a citation table, synthesis, and a recommendation on whether to adopt a teaching strategy. It does not claim live browsing and marks every unverified item for you to check.

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.

Fact-Check Research Brief for an Explainer or Documentary Video

Builds a source discovery plan, evidence review, and citation table for a video's factual claims so a producer can decide which claims to keep, soften, or cut before scripting.