SCOUT Intake: Grade the Chatbot Dump

Research arrives as a pasted transcript or a chatbot summary more often than as something you gathered. It reads as finished work and it usually isn't. This grades it, and the grading is where the value is.

It audits the session before grading anything, because a dump's provenance decides how much weight it can carry. Then it opens every link and records four things while each one is open, walks the thread rather than quoting one comment, and goes where the chatbot can't reach. Section 6 qualifies every competitor, on the ground that a name is not a competitor. Section 7 adds four cheap metrics that frequently overturn the dump's own conclusions.

The output is two files, covering vocabulary, wants, objections, and what went unanswered. That last section is the one that matters most: it names what the dump didn't cover, which is invisible by construction unless something looks for it.

It ships lexicon_lint.py and a question sheet.

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.

Intake exists because most research now arrives pre-summarised, and a summary nobody graded is a premise nobody checked.

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