Rewire Agents

Use the BRIEF Framework to build your AI agents

Answer five questions to build your AI Agent. The same ones you'd have to answer to get that role approved and your new hire trained.

The five questions

Background
What is the background of the job? The context a new hire needs on day one: the team, the customers, the documents, how things are done here.
Role
What is the specific role, the task? One job, one agent. "You sort the shared inbox into three buckets." Not "you handle HR."
Instructions
What are the instructions to do the job well? The rules, the order of operations, and what needs a person before it goes anywhere. Say what it never does, when it stops and hands back to you, and which way it leans on a close call.
Expectations
What does good look like? Share up to three real examples of good and three of bad, from your own work. Make one of the bad ones something it should never do. This is the field that's easiest to skip, but it also is what teaches your agent the most.
Feedback
How do you make sure it gets better? The review loop: give the agent your final version, edits and all. Ask what it notices, what it assumed, and how it can improve next time. Either you or the agent can update the BRIEF so that it keeps getting better over time. A good rule of thumb is to hand it a group of final versions and have it do the review all at once itself. Put the review on the calendar, or set it up as a task that runs on its own and shows you what it would change.
If you were hiring someone tomorrow, you would tell them what the job is about, what they do, how they do it, what good looks like, and how you are going to help them get better. That is an agent script. That's it.

Now write one

Five boxes, for one task on your desk. Answer them the way you would tell a person and we'll make it your agent.

Not sure which task? Pick one you've done at least three times and have a few real examples of, good and bad.

What you type stays in this browser. There is no server, no account, and nothing is sent anywhere until you decide to send it.

The job title on the req. One line. It names the file you download and heads the BRIEF itself.

The context a new hire needs on day one: the team, the customers, the documents, how things are done here.

One job, one agent. "You sort the shared inbox into three buckets." Not "you handle HR."

The rules, the order of operations, and what needs a person before it goes anywhere. Say what it never does, when it stops and hands back to you, and which way it leans on a close call.

Share up to three real examples of good and three of bad, from your own work. Make one of the bad ones something it should never do. This is the field that's easiest to skip, but it also is what teaches your agent the most.

The review loop: give the agent your final version, edits and all. Ask what it notices, what it assumed, and how it can improve next time. Either you or the agent can update the BRIEF so that it keeps getting better over time. A good rule of thumb is to hand it a group of final versions and have it do the review all at once itself. Put the review on the calendar, or set it up as a task that runs on its own and shows you what it would change.

Expectations is still empty. This is the field that's easiest to skip, but it also is what teaches your agent the most. Up to three real examples of good and three of bad, from your own work.

When you are ready, confirm and you will see what you just wrote, in plain English and as a document.

Where each part lives

Background
Uploaded knowledge files, plus a short summary at the top of the instructions.
Role
The first sentence of the project instructions, the system prompt, or the skill file.
Instructions
The bulk of the same text block. A rule that only applies to one kind of task goes in a skill that loads for that task.
Expectations
Pasted examples, in the same block. Real ones, not descriptions of one.
Feedback
A review on your calendar, and the BRIEF itself, updated as you both learn. Not a setting. A process.

Before you trust it, test it

Three quick checks, the first time you run your agent.

Same job, twice
Give your regular AI chat a real piece of work. Then give your agent the same one. If you can't tell the difference, the BRIEF isn't adding anything yet.
Something new
Give it a real example that isn't in your BRIEF.
Something it should stop on
Give it one it should refuse or hand back to you.

If it misses, fix the BRIEF, not the output.

The tool question

Whatever AI you use, the BRIEF is designed to work as an agent or skill doc for any of them. Focus on the answers and then we'll give you a version to run wherever your AI is.

The Rewire Company is here to help make AI work for you. For more information visit our website or contact Sean Glennon at sean@rewirecompany.com.