Automations

An automation is a defined agent job that runs manually, once at a chosen time, or on a recurring schedule. Use one when the instructions and trigger are stable enough that each occurrence can be reviewed as the same kind of work.

Creating an automation without selecting a project gives it an unlisted project. Selecting a listed project lets the run use that project's instructions, memory, files, skills, and connector activations. You can change the project for future runs; historical run sessions remain in the project where they executed.

An automation defines

• the job instructions;
• an optional description that explains the operational purpose;
• the project context and capabilities used by future runs;
• model and reasoning settings;
• a manual-only, one-time, daily, weekly, or other supported recurring schedule;
• enabled or paused state;
• optional execution guardrails such as maximum steps and runs per day;
• run history, last result, and next due time.

Every fire creates a new automation session titled as its own run. Runs do not share conversation history with each other; the durable state that carries forward is project context, especially project memory. This makes it possible to inspect one failure without reading a long, continuously growing automation transcript.

Create and test an automation

Write instructions that make one occurrence self-contained: identify the inputs to inspect, the decision or artifact to produce, the destination, and what should happen when there is nothing to report. Choose the narrowest connector access the project needs.

Start with Manual and use Run now while refining the definition. After the output is reliable, add a one-time or recurring schedule. The manual run uses the same definition and execution path as a scheduled run, so it is a meaningful test.

Current automations are agentic: each accepted run invokes the configured model. Script-only execution and conditional preflight fields exist only as future scaffolding and are not exposed as a supported automation mode.

Prefer an agent when responsibility is ongoing

Automations optimize for a repeatable job with independent run records. Agents optimize for a persistent role and conversation. If the work should notice context, decide what responsibility is due, and continue a relationship across check-ins, staff an agent instead. If the only useful result is a maintained view, consider a dashboard.