Claim-mapping instrument · provisional name
Claim Trail
See where every important claim came from and where it can break.
Creates a compact claim ledger and flags unsupported or ambiguous statements before a larger graph is warranted. A trail makes each step from thesis to evidence retraceable.
Input bench
Name the real material
The decision or belief the map is meant to support.
One per line as: claim | sourced/derived/inferred/guessed/judgment/unsupported but verifiable | evidence.
Which claim numbers must be true for the conclusion to hold?
What evidence still needs to be found or checked?
Where does the conclusion apply, and where does it not?
What would the strongest smart skeptic say?
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
Three claims: sourced, inferred, and guessed.
Useful change
A map that marks the guessed causal claim as the weak link and preserves the counterclaim as a test condition.
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.