AI agent for director of strategies
Competitive Claim Verification Agent
A competitive brief where every claim is dated, sourced and fairly compared.
What it does
Competitive comparisons often repeat what competitors claim on their websites without checking. Teams then make decisions or claims based on marketing copy. This agent lists the material claims per competitor, starting with those that would change the comparison. It traces each claim to primary evidence and looks for corroboration in permitted sources. It checks whether each competitor defines the measure the same way. If not, it searches another source or writes a qualified comparison instead of forcing a ranking. It keeps a dated evidence ledger. A researcher approves the brief before any external use. Edge case: a claim backed only by the competitor's own press release is labeled as self-reported.
How it works
Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.
Read the steps as a list
- Comparison requested
- List material claims per competitor
- Trace each claim to primary evidence
- Is the claim corroborated and defined like ours?If not: search another source or qualify the comparison. Back to step 3.
- Update the evidence ledger with dates
- Researcher approves before any external useThe agent waits here for your OK.
- Dated competitive evidence brief
How it decides
It investigates the claims that matter most to the comparison first, seeks a second independent source, and qualifies comparisons when definitions differ.
- Which claims first: those that would change the comparison.
- Qualify or rank: qualify when definitions or dates differ.
- Self-reported: label claims backed only by the competitor's own material.
- Stale evidence: older than 12 months is shown with its date.
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Permitted sources (default public filings, independent tests, product docs)
- Competitors in scope
- Age limit before evidence is marked stale (default 12 months)
- Brief format (default claim table with definition, source and date)
- Who approves before external use (default the lead researcher)
What keeps you in control
It always asks you first
- External publication
- Any allegation about a competitor
Hard limits
- No unverified allegations.
It stops when
- Done: all material claims traced.
Set it up
We guide you through the set-up, step by step
Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.
- One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
- The agent then walks you through connecting your own data, one source at a time
- A downloadable copy with the flow chart, the rules and the full guide
An example run
More agents for director of strategies
Strategic Assumption Watch Agent
Leadership always knows which strategic assumptions still hold and what changes when one breaks.
Strategy Experiment Coordination Agent
Every strategic experiment reaches a decision at its checkpoint, based on its original rules.
Market Entry Evidence Gap Agent
A market-entry brief that shows which evidence supports the decision and which gaps remain.
Business Model Sensitivity Agent
Founders know exactly which assumptions make or break their model.