Skip to main content
Plans and goals are two ways to drive multi-step work. A plan breaks a prompt into ordered tasks and tracks each one to completion. A goal pins a durable objective the agent keeps working toward across multiple follow-up messages. This guide uses both on the same thread.

1. Create a plan

Send /plan with a prompt the agent can break into tasks:
The agent returns a human-readable plan in event.markdown and a structured proposal with ordered tasks.

2. Run the plan

Start execution and watch each task complete:
Each task’s result is persisted to the thread, so you can inspect or resume a plan later without losing progress.

3. Plan state

4. Pin a goal

A goal persists across messages. Pin one and the agent treats every follow-up as a step toward it:

5. Send follow-up messages

Continue chatting normally. The agent keeps the goal in mind on each turn:

6. Check goal status

7. Goal state

Only one goal is active per thread at a time. Pinning a new goal replaces the previous one.

Lifecycle subcommands

Plan vs goal

Use a plan when you know the steps. Use a goal when you want the agent to keep steering toward an outcome across many turns.

Next