Invisible expertise extractor · provisional name
Rule Ledger
Write down the judgment call before it walks out the door.
Turns a recurring decision and its cues into a testable when, because, unless rule with a small plan to check it. A ledger keeps the rule on record long after the person who made the call has moved on.
Input bench
Name the real material
Name the decision this expert makes over and over.
What do they notice before deciding? One cue per line.
What do they actually decide when those cues appear?
What do they give up by deciding this way, and why is it worth it?
How do they know the decision was made well?
When does this rule not apply? One per line.
PRIVACY: INPUTS STAY IN THIS BROWSER. SAVE USES LOCAL STORAGE ON THIS DEVICE. NOTHING IS SENT BY THIS INSTRUMENT.
Output desk
Your result appears here
Load the sample or bring real material.
THE TOOL TRANSFORMS WHAT YOU ENTER. IT DOES NOT CALL A MODEL OR INVENT MISSING FACTS.
Worked example
Starting material
A senior reviewer who just says 'I know it when I see it.'
Useful change
A written when, because, unless rule with three test cases, so someone else can apply the same judgment and check where it might be wrong.
Put the result to work
A method to follow. A prompt to take with you.
Prompts
Agent Assignment Contract
Turn an ambitious request into a precise agent assignment with outcome, evidence, authority, and an honest stop condition.
Skills & workflows
Agentcraft
Design, compose, harden, diagnose, and attest agents and multi-agent systems so repeated delegation becomes an inspectable operating system.
Tutorials
How to Know Whether Your AI Workflow Actually Works
Build a small honest evaluation that compares artifacts, exposes failures, and limits adoption to what the evidence demonstrates.
StrAItegy writing ↗
The Rules Nobody Wrote Down
The unwritten operating rules of working with AI agents, written down.