SCOUT Outcome: What Actually Moved

A retro written from memory grades everything as a modest success. This one reads captured analytics off disk and grades the result into three buckets: Moved, Flat, and Prune.

The signature discipline in section 4 is what keeps it honest. It pins the result to the specific snapshot it came from, so a number can be checked later rather than taken on trust. Section 1 covers what usually goes wrong in this kind of review, section 2 covers where results actually live, and floors apply throughout.

The Prune bucket is the deliverable most reviews never produce, because deciding to stop something requires having measured it.

It ships outcome_lint.py and a measurement checklist.

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.

Outcome is where the system finds out it was wrong, which is the only way the next plan gets better.

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