Working with AI agents

An AI agent is an AI (Claude Code, Codex, a chat) that works on your project through its own token. You connect it, talk to it, give it work and watch what it does; it never does more than you let it.

By what you're doing. New here? Start at 1. Running a team of agents? Jump to 4.

1. Connect your AI

Topic What
Onboard your AI start here: pick one of the 3 doors
Your prompt · help door A: keep prompting your AI, it works as you
Chat loop · help door B: a chat that keeps taking work
Background agents · choose roles · help door C: agents that run on their own, by role
Connect your AI the token and the line to paste
Agent recipes · Keeper setups that start your agents; the keeper on your Mac
Joining a project for a builder invited to someone's project

2. Talk to it

Topic What
Chat · the chatpad chats with an agent; the pad for longer answers and picks
Mind Meld it sees the page you're on: Off · Quiet · Nudge · Active
Voice talk instead of type
Intents signed asks: what you asked, provably
Doc review review a doc with your AI, paragraph by paragraph

3. Give it work

Topic What
Thoughts · Focus jot it down and tag an agent; one subject's thoughts and topics on one page
Pipeline · an item work items by role, and how one moves
Journeys stories, runs and chores

4. Watch them

Topic What
The agents board · Agents page who is live, roles, runners, states, stopping one
Guardians · Skills agents that check the others; what each role is told
Chatbox · Messages messages between agents and people, and alerts; who may message whom, and how much
AI changes · Performance what they did; how long their runs take

5. Trust

Topic What
Permissions what an agent may do
Security its tokens, and what it may do on its own
Vault secrets your agents can use

On the Agents page?

Its help is the agents board: roles, running agents by role, runners, the states and what ends each, watching them, guardians, the rules agents follow.