Skip to content

Start building

Integration · Automation

AI agents for Trigger.dev

Trigger Trigger.dev background tasks with a payload, find runs and read their status, output and errors, and cancel or replay runs, in one environment of a Trigger.dev project.

Actions
7
Read
4
Write
3

Actions

What your agents can do in Trigger.dev

Trigger Trigger.dev background tasks with a payload, find runs and read their status, output and errors, and cancel or replay runs, in one environment of a Trigger.dev project (Trigger.dev Cloud or your own instance), with that environment's secret key.

Read 4

Look things up. Nothing changes.

  • List runs

    Lists runs in the environment, newest first, filtered by status, task, tag, version, schedule and creation time; without a time filter only the last 7 days.

  • Get a run

    Reads one run by its ID: status, taskIdentifier, payload, output (when finished), error, attempts.

  • Get a run's result

    Reads the result of a finished run: ok (true when it completed), output (the task's return value, serialized as text; outputType says how, usually application/json) or error.

  • List schedules

    Lists the environment's cron schedules.

Write 3

Create, change or send.

  • Trigger a task

    Starts a run of a task by its ID (the id in the task's code, like send-welcome-email) with a JSON payload.

  • Cancel a runDeletes data

    Cancels a run that has not finished: it stops at once and runs no more attempts.

  • Replay a run

    Starts a new run of the same task with the original run's payload and options, for example after fixing the code it failed on.

A person can approve first

Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything. Actions that delete data ask first by default.

Connection

How it connects

Connect it once in the console, then give it to the agents and workflows that need it.

API key

Paste an API key from your Trigger.dev account.

What you enter

  • Secret API key

Settings

  • API address

Kept safe

  • Credentials are stored encrypted with your organization's own keys.
  • They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
  • Calls go only to the tool's own servers.

How we protect your data

Ideas

Ideas to start with

Starting points made only from the actions above. Mix them with any other tool your agents can use.

  • 01

    Ask about your Trigger.dev data

    Ask a question in plain words. The agent can list runs, get a run or get a run's result in Trigger.dev, then answers with what it found.

  • 02

    Let an agent update Trigger.dev

    Have the agent trigger a task or cancel a run in Trigger.dev as part of a larger task. Turn on approval and a person signs off on each change first.

  • 03

    Share what it finds in Slack

    Give one agent Trigger.dev and Slack: it can list runs in Trigger.dev and post a summary to a Slack channel in the same run.

FAQ

Trigger.dev and MyDeepAgents

Can MyDeepAgents connect to Trigger.dev?

Yes. The Trigger.dev connector has 7 actions: 4 read and 3 make changes. Your agents can call them as tools, and your workflows can run them as steps.

How do I connect Trigger.dev?

Paste an API key from your Trigger.dev account. You'll need: Secret API key. The connection also asks for: API address. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.

Can an agent change data in Trigger.dev without asking?

Only if you let it. Each of the 3 actions that change data can be set to wait for a person's approval before it runs, and the one that deletes data asks first by default.

Can I use Trigger.dev in workflows as well as agents?

Yes. Every Trigger.dev action also works as a step in a workflow, and the same connection serves your agents and your workflows.

Early access

Put Trigger.dev to work

Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.