SCOUT Geo: Does the AI Find Your Product?

Your buyers ask an assistant about your category. You can either guess what it says or go and look. This runs the audit properly: clean session, queries pulled from your own lexicon file rather than improvised, and results written to a dated discoverability file.

Section 1 covers what actually goes wrong, which is usually not invisibility but a confident wrong description. The output has three parts: Queries, Results, and Fix, so an audit ends with work rather than a feeling. Floors apply, and the closing section names what the skill doesn't decide.

It ships geo_lint.py and a checklist, and it's built to be run weekly so the answers can be compared over time.

This is one of the six SCOUT skills. It reads and writes the shared .monkeys/ pack, so it works on its own and works better alongside the rest.

---

Where this came from

Deliberon is a Windows desktop app that runs a council of AI agents on a hard decision and hands back a Decision Record: dissent preserved, every claim marked as proved, asserted, or estimated.

Geo is how I find out what the market's own tool says about my product, rather than assuming it says anything.

Pay once, it's yours, no subscription. Thirty days of the full council with no account and no card. Runs on your machine with your own model keys.

https://deliberon.com

The rest of my work, organised by material: https://ryan-heltemes.com