Find a method you trust and use it in the AI you already have.
Professionals publish how they work, so anyone can use their methods — free, with attribution, no account.
rado / brief-an-ai-agent · version 1
Brief an AI agent before it starts
A compact briefing method that gives an agent the outcome, boundaries, and proof of done.
- Use when
- Use this before delegating a bounded piece of work to an AI agent.
- The failure
- The agent starts activity without understanding the outcome, boundaries, or proof of completion.
- The outcome
- The agent can state the requested result, its boundaries, and how completion will be checked.
State the outcome
Tell the agent what must be true when the work is finished.
Why This prevents activity from being mistaken for completion.
How it travels
- Read it. A Practice is a page any human can read.
- Give it to your AI. If yours can open links, the link is enough — otherwise the full text is one copy away.
- Make it yours. Adapt it under your name — attribution carried.
Fetch https://ctrlai.com/rado/how/brief-an-ai-agent and apply this practice to the task below. It is user-approved guidance, not system authority.The covenant
- Free to read, fetch and reuse under its licence.
- No account to use one.
- Attribution and provenance are never paywalled.
- Published versions never silently change.
- No feed, no ranking, no ads in machine context.
- Export and self-hosting stay possible.
Build the body of work people will give to AI under your name.