Connect Humanloop to your AI agent

AI Tools 4 actions available

Humanloop helps developers build and refine AI applications, offering user feedback loops, model training, and data annotation to iterate on language model performance

We set up the connection using your own Humanloop account, with keys you control, and keep it running. Your agent picks it up and starts doing the work.

What your agent can do in Humanloop

Each one is a real action the agent can take on its own, the same things a person clicking around Humanloop could do. Read-only by default; write actions are confirmed against your policy.

  • Create Project This tool creates a new project in Humanloop. It is an independent action that generates a project by accepting a project's name (required), an optional description, and an optional organization_id. Upon execution, it r…
  • Delete Project This tool allows you to delete a specific project from your Humanloop organization. The deletion is permanent and cannot be undone. All associated data, including sessions, datapoints, and evaluations linked to the proj…
  • List Experiments This tool retrieves an array of experiments associated with a specific project in Humanloop. It requires a project_id (starting with 'pr_') and returns details including experiment_id, name, description, creation timest…
  • List Sessions This tool retrieves a paginated list of sessions for a specific project in Humanloop. It requires a project_id (and optionally, page and size for pagination) and returns session details such as id, reference_id, project…

How we connect it

  1. 1

    Connect your account

    You create a key in Humanloop, a key you create and control, and paste it in once. It lives in a secrets store on your server, not with us.

  2. 2

    Set the guardrails

    Read-only by default. You choose which write actions the agent may take, and anything outside that policy gets confirmed with you first.

  3. 3

    We keep it running

    Health checks on every connection, updates handled for you, and we watch the first week of activity to make sure the work lands.

Humanloop questions, answered.

With a key you create and control. You paste it in once, it is stored in a secrets store on your server, permissions are scoped to the minimum the agent needs, and you can revoke it at any time.
The actions Humanloop's API allows, the same things a person clicking around the app could do. Connections start read-only by default; write actions are confirmed against the policy you set before the agent takes them.
Connections are priced per tool on top of the base plan. Some are included, some are premium. See pricing for how connection charges work.
Standard tools are ready inside 7 business days of the setup call. We test the connection end to end, walk you through how the agent uses it, and watch the first week of activity.

Ready to put Humanloop to work?

Tell us what your team runs on. We set up the connection, secure it, and your agent takes it from there.

All product names, logos, and brands are property of their respective owners; used for identification only. ZeroToClaw is not affiliated with or endorsed by Humanloop.