See Every Buyer Question Where AI Skips You (Claude Code Agent)

A Google result gives your buyer ten links to choose from. An AI answer gives them a short list of names the engine already decided to trust. Every buyer question is a vote, and the engine names a few sources and skips the rest.

This is the exact AEO gap agent we built live in Claude Code. It runs your buyers' real questions across ChatGPT, Perplexity, Gemini, and Claude, counts who gets named, and returns a cited gap report of every answer you're missing from. It measures the real answer. It never asks the engine to grade you, because the engine flatters you when you do.

It's the agent we built live, packaged so you can install it and run your category in about 25 minutes.

What's in the download:

• The full Claude Code project, with a README and build steps that include every prompt

• The agent's operating rules (the measure-don't-guess discipline)

• Three reusable prompts (run and record, extract and tally, recovery) and a gap-report template

• A prompt-set template and a filled example gap report so you can see the shape

Built by Will Leatherman and the team at Catalyst, who've built AI-search systems for 150+ B2B companies. Every line in the report traces to a saved answer, so your share of voice is a real number, not a guess.