Portable context pack starter · provisional name
Page One
The first page any AI system should read about how you work.
Builds a portable context block covering role, standards, examples, rules, and boundaries, and checks it against a 600-word target. Page one sets the terms before the rest of the file gets read.
Input bench
Name the real material
Who is the AI working with, and in what capacity?
One standard per line.
One example per line. Be specific.
One rule per line for how to decide when unsure.
What should the AI never do without asking first?
Tone, format, or process preferences.
One assumption per line that the AI should never make silently.
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
Reintroducing yourself and your standards to every new AI conversation.
Useful change
A single reusable page-one block under 600 words that two different systems can be tested against side by side.
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.