Hypothesis-Tested Entity Dossier
Get a sourced dossier that tests your assumptions about an entity, weighs contrary evidence, and identifies decision-critical gaps.
Before & after
Same prompt, same agent — the only difference is the skill.
I can help you research a venture capital firm. I'd look at their portfolio companies, partners, investment thesis, and recent activity. You could find information from their website, press releases, and news articles. I'd put together a summary of what they invest in, how much they typically raise, and any relevant news about them. That would help you understand what they're looking for. Do you want me to include anything specific like their LinkedIn profiles or recent funding announcements? This would give you some background, though the research will be general.
DOSSIER: TechVenture Capital Research Date: 2026-07-31 | Confidence: HIGH HYPOTHESIS (yours to test): "TechVenture invests in infrastructure plays, not applications; they will pass on a B2B SaaS Series A." VERDICT: MOSTLY TRUE (8/10 confidence) Portfolio is 73% infrastructure (data, APIs, dev tools) vs 27% applications. But they made 2 app investments in 2025 when founders had engineering backgrounds. Your pitch risks misalignment. ORGANIZATION FACTS Founded: 2016 | AUM: 340M | Typical Check: 2-5M | SaaS: 31% of portfolio | Sectors: DevTools 42%, Data 31%, AI 18%, Fintech 9% 12-MONTH ACTIVITY TIMELINE Jan 2026: Led Series B for DataFlow (API platform, 15M) Mar 2026: Joined Series A for NeuroSync (AI research, 8M) May 2026: Launched Climate Tech Fund (50M) Jul 2026: Passed on 3 B2B SaaS pitches (public feedback: "too many competitors") KEY PARTNERS & BETS • Sarah Chen (general partner, focus: developer tools) — 8 board seats, all infrastructure • Marcus Kumar (analyst, focus: AI + data) — covers recent SaaS exceptions • Fund II (closed 2024): Weighted 60% infrastructure, only 3 app companies NETWORK & REPUTATION ✓ Strong exits: 5 portfolio companies acquired by Google, Meta, Stripe ✓ Network depth: CEO relationships with 40+ enterprise IT leaders ✗ Red flag: Passed on 2 AI SaaS pitches (2025, 2026) citing "market saturation" ✗ Weak consumer tech track record: 1 consumer investment (2017), returned 0.3x REALTED FLAGS 1. Diversity: 3 of 6 partners are ex-Stripe (may favor payments/fintech) 2. Founder type: All funded founders have PhD or C-suite background (you: bootcamp grad → risk) 3. Lead times: Typical decision window 8-12 weeks (long for A round) 4. Valuation bias: Median Series A marked at 20M (vs. market 15M) CONVERSATION HOOKS • Ask Sarah about her developer tool thesis (she leads this) • Lead with: "We're infrastructure for engineering teams, not just another SaaS app" • Mention: Their DevTools pattern matching your category • Avoid: Comparing to their SaaS losers (NeuroSync positioning) PREP CHECKLIST ☐ Research their 3 most recent Series A exits (check Crunchbase for outcomes) ☐ Prep answer: "Why infrastructure, not SaaS?" with 2-minute elevator pitch ☐ Know Sarah's 8 board seats (her companies, her preferences) ☐ Prepare for 10-week decision window (not a quick yes) SOURCES AUDITED: ✓ Crunchbase (6 deals verified) ✓ LinkedIn (partner profiles, connections) ✓ SEC EDGAR (any LP relationships, filings) ✓ News: PitchBook + TechCrunch (2025-2026) ✗ Insider interviews unavailable (timing)
About this skill
You need to know whether a potential partner, vendor, acquisition target, or meeting counterpart supports the story you have been told. This produces a dossier that tests that story, separates verified facts from promotional claims, and shows which unanswered questions could change your decision.
What it does
- Resolves the correct entity, jurisdiction, subsidiaries, and similarly named organizations before attributing findings.
- Turns your working belief into a testable hypothesis with explicit supporting and contradicting evidence.
- Builds a sourced 12-month activity timeline while preserving older facts that still affect the decision.
- Evaluates affiliations, reputation signals, and red flags without treating connections or allegations as proof.
- Links findings to precise questions, document requests, and meeting conversation hooks.
- Records claim-level sources, dates, limitations, and unresolved access gaps for review.
What you get
An editable dossier with a hypothesis verdict, identity facts, material findings, timeline, network and reputation assessment, next steps, and source audit. Depth adapts to the request; Word output is provided when file-generation tools are available, with copy-ready Markdown otherwise.
Best for
Founders, partnership leads, procurement teams, researchers, and deal teams investigating a specific company, professional counterpart, nonprofit, or government organization before a consequential conversation or decision.
SKILL.md preview
---
name: hypothesis-tested-entity-dossier
description: >-
Produces a decision-focused dossier on a company, person, nonprofit, or government organization by resolving identity, testing a hypothesis against supporting and contrary evidence, and tracing findings to dated sources. Use when the user says "prep me for a meeting with this company", "do due diligence on this vendor", "check this person's professional background", "is this potential partner credible?", "verify their growth claims", "this profile is all marketing fluff", or "I keep finding conflicting information about this organization".
---
# Hypothesis-Tested Entity Dossier
… (sign up to view the full skill)More research & data skills
View all Research & Data skills →Source-Reconciled Research Brief
Turn supplied links into a concise brief with claim-level citations, reconciled source conflicts, and explicit evidence gaps.
Source-Traced Research Bundle
Compile many sources into one bundle where every claim is atomic, sourced, dated, tiered, and conflict-checked, in Markdown or JSON.
A/B Test Power and Validity Designer
Exact A/B sample sizes and MDE with math shown, plus the traps: unit mismatch, multiple variants, peeking, guardrail power, and SRM.
Research Routing and Cited Briefings
Route research to the right method, then produce a cited briefing with evidence gaps, disagreements, and a source audit.