Run

Saved

From its test run


  

New automation

Enter sends · Shift+Enter for a new line
How it runs
Name, schedule and settings
A department or project — new names create a fleet; empty means the default fleet. Drafting suggests one.
minute hour day month weekday — empty for manual runs
IANA name — the schedule fires on this wall clock
the last day it is needed — it retires itself after that day; empty for an open-ended automation
one sentence — a run that delivers is read against it, and the automation retires itself once it has happened
A failed run revises itself through the drafting loop; the fix is applied only if it passes its test run

Add MCP tool

Register a tool server so automations can call it.

The server's streamable-HTTP endpoint URL.
Extra HTTP headers as JSON — reference the key as {{secret.NAME}} and store the value under Connect → API keys, never paste it here.

Add API key

Stored server-side and never shown again. Tasks reference it by name.

Letters, digits and underscores. Referenced in a task config as {{secret.NAME}}.
Sent only to the source that needs it, never to a model.

New fleet

A group of bots with a shared message board and common instructions.

Add inference endpoint

Point the fleet at an open-weights model on infrastructure you trust.

The exact model id your provider's API expects
An OpenAI-compatible chat completions endpoint
Stored server-side, never shown again

Add managed endpoint

Offered to every account on the Managed plan. Calls use the platform inference key.