Skip to main content
app.pome.sh is the web view for everything you run with Pome: the agents you register, the twin sessions they run against, the runs themselves, and the judge handoff for each one. pome run records to the dashboard by default. Local copies of the artifacts (events.jsonl, score.json, state snapshots) also land on disk under runs/<scenario>/<run-id>/.

​
What you find

The dashboard top nav today is Dashboard | Runs | Twins | Docs. There is no dedicated Agents page; registered agents surface inside the Runs list (filter by agent) and on individual run pages.

​
Runs

A run is a single scenario execution. The run page shows:
  • The full trace. Every tool call the agent made, in order.
  • The score against the scenario’s acceptance criteria.
  • The judge handoff. A concise summary plus an actionable suggestion to fix or improve the agent. Use it as the next prompt back to your coding agent.

​
Twins

The Twins page lists the active twin sessions across your team. From a session you can see which agents have run against it and inspect state diffs run-to-run. Session lifecycle is also driven from the CLI via pome session create / list / stop.

​
How runs end up here

Anything that talks to the backend lands on the dashboard:
  • pome run <scenario> from the CLI.
  • /pome-test invocations.
  • Any agent you have registered with pome register agent, once it makes scored runs.
The CLI uses the API key from the macOS Keychain (preferred on macOS), ~/.pome/credentials.json (other OSes or when Keychain is unavailable), or POME_API_KEY (CI). See Quickstart for the login flow.

​
Open it

open https://app.pome.sh
Or grab a direct link from the URL /pome-setup prints after registering your agent.

​
Next

/setup

/pome-setup registers the agent and prints the dashboard URL. /pome-test populates the runs.

CLI reference

pome run, pome register agent, pome session, and the auth env vars.