up to $20

Docs

Scheduled runs

Ask an agent to do something later. How schedule_run works from chat and MCP, and how the result comes back to you.

A scheduled run invokes your agent later, with a prompt you set now. "Check the release issue tomorrow at 9" becomes a real run that fires at 9, works in the agent's own environment, and posts its reply back to you.

How do I schedule a run?

Ask the agent in chat. plori agents can schedule themselves. Say "every detail is in NOTES.md, pick this up tomorrow morning" and the agent schedules the run itself. Most users schedule this way.

From your own tools. The MCP server exposes a schedule_run tool, so Claude, ChatGPT, or your own scripts can schedule work on a plori agent:

{
  "name": "schedule_run",
  "arguments": {
    "agent_id": "<your agent's id, from list_agents>",
    "prompt": "Summarize new issues since yesterday and triage them.",
    "fire_at": "2026-07-03T09:00:00Z"
  }
}

Give either fire_at (an RFC3339 timestamp) or delay_seconds (relative, from now), plus the prompt to send. A time in the past is rejected. An optional session_id delivers the reply into a chosen existing thread.

A schedule created from an AI client does not fire until you confirm it. The tool returns a link to the agent page in the plori web app. The page shows the agent, the full prompt, and the fire time in your local time, with Confirm and Cancel buttons. Until you confirm, the schedule has the status awaiting_confirmation. If the fire time passes first, confirmation is refused and the client must create a new schedule. The agent page also lists every schedule that is waiting, so you can confirm one without the link.

What happens when a schedule fires?

The schedule fires as an ordinary run: the agent wakes if it was asleep, receives your prompt, and works with its usual disk, tools, and memory. Credits are drawn the same as any run; if your balance is empty, the schedule is marked failed rather than silently dropped.

The reply is delivered where you will see it:

  • If you have a conversation with that agent open, the reply arrives inline there.
  • Otherwise it appears in a new thread named "scheduled", waiting in the agent's history.

You see only the agent's report, not a re-echo of the scheduled prompt.

Can a schedule repeat?

Scheduling is currently one-shot: each schedule fires once. For recurring work that is the same steps every time, have the agent build a workflow instead: a standing pipeline that fires on a schedule or a webhook without an agent turn. For recurring work that needs the agent's judgment each time, end a scheduled run by asking the agent to schedule the next one, or drive the schedule from your own cron via MCP.

  • Workflows: a standing automation the agent builds, for "do this same thing every day".
  • Background tasks: work that outlives a single reply without a schedule.
  • Drive plori over MCP: schedule, invoke, and manage agents from any MCP client.