Skip to main content
This walks through the first-run loop over the Pome MCP. It applies whether you’re a human following along or an agent executing the calls directly.

​
The loop

​
1. Read the playbook

Returns the coach playbook — read it before doing anything else.

​
2. Confirm identity and quota

Confirms identity, team, plan tier, and quota headroom.

​
3. Register the agent under test

Use intake_clone_scope for the rich path — it captures the agent’s clone scope so run_scenario can assemble the examinee launch spec:
Or register_agent for a lightweight registration:
Keep agent.id from either response — you’ll pass it as agent_id to run_scenario.

​
4. Choose or author a scenario

Pick an existing scenario:
Or author one:
Then sanity-check the seed before you spend a run on it:

​
5. Run the scenario

Or run_trials for N trials of the same scenario sharing a group:
This provisions one twin sandbox per twin and returns examinee_launch — the clone spec. Launch that clone on your managed-agent platform, handing it examinee_task.prompt.
Set mcp_permission_policy { type: "always_allow" } on every examinee MCP toolset from examinee_launch.mcp_servers[], or the headless clone deadlocks on its first MCP call.

​
6. Finalize

Grades synchronously — pulls the recorded twin tape, scores it, tears down the sandbox. The score is returned directly in run, no polling. Call this before the session expires.

​
7. Get the report

Returns the scored markdown report plus a human weblink to app.pome.sh.
Coach vs examinee: the agent making these tool calls is the coach — it sees criteria and picks scenarios. The examinee is the separately launched clone that actually attempts the task; it holds no Pome tools and never sees the criteria.

Tools reference

Full input/output reference for every tool.

Digital Twins reference

What run_scenario provisions against.

Command Line Interface

The CLI equivalent of this loop.