AI product Open source
The Fable Method is an agent-workflow repository that distills the Fable Workflow into skills that models can run. Its process classifies the request, defines completion with named verification, gathers evidence from primary sources in parallel, commits to one recommendation, changes the smallest correct thing, verifies the result by observation, and reports the outcome with caveats. The repository provides four related skills—fable-method for thinking, fable-loop for acting, fable-judge for evaluating results, and fable-domain for generating domain adapters—along with evaluation cases, transcripts, judge outputs, and logs. The project reports testing the method across fifteen evaluation rounds and more than 260 agent runs, with judges checking diffs and execution rather than relying on agent reports.
1 use taken from transcripts — each links to the moment in the video.
A method for structured agent work that classifies requests, defines proof, gathers evidence, makes a decision, changes the smallest correct thing, and verifies the result. The repository includes installable skills, adapters, and evaluation logs.
1 in the library.