> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.site/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect your harness

> Set up the credential that powers the agent runtime, the skills that give workers access to GitHub, Datadog, and the Arize API, and the permissions that govern both.

<Info>
  Managed agents are available on **Enterprise**. Free and Pro include [Signal](/docs/ax/observe/signal) only. Through **September 15, 2026**, Signal and managed agents are included at no additional charge for Enterprise. See [Pricing and usage](/docs/ax/security-and-settings/pricing-and-usage).
</Info>

This is the setup page for managed agents. Two things need connecting before a worker can do anything useful:

* **The harness** — the agent runtime inside the sandbox, and the model credential that powers it.
* **Skills** — the outside systems a worker is allowed to reach.

Both are configured once per account and reused across every agent.

## The harness

The **harness** is the agent runtime that runs inside the sandbox. **Claude Code** is available today; Codex, Cursor, and others are on the roadmap.

Claude Code needs an Anthropic credential, which Arize calls an **agent integration**. By default, runs use the **Arize-managed** credential and you configure nothing. On Enterprise you can bring your own key instead:

<Steps>
  <Step title="Add an Anthropic AI Provider">
    Under **Settings → AI Providers**, add an [Anthropic provider](/docs/ax/security-and-settings/integrations-playground/anthropic) with your key.
  </Step>

  <Step title="Allow it in agents">
    Enable **Allow use in agents** on the integration, or add it from **More → Agent Integrations** with **Add Agent Integration**.
  </Step>

  <Step title="Select it">
    Choose that integration on a preset, during agent setup, when enabling Signal, or as the space default under **Space Settings**.
  </Step>
</Steps>

Manage available integrations under **More → Agent Integrations**. Enterprises that must not use Arize-managed models can ask Arize to disable the Arize-managed integration for the account, so only customer-owned keys are ever used.

## Skills

**Skills** are account-level integrations that give sandbox workers access to external systems. You connect them inline while setting up an agent — the **Connect** step of the guided setup — and a skill you save is then available to every preset in the account.

<Note>
  These are not the same as [Arize Skills](/docs/ax/skills/overview), which run in your own coding agent on your own machine. Same idea, different runtime: these inject credentials into an Arize-managed sandbox.
</Note>

### GitHub

Lets a worker clone a repo, branch, and open PRs.

**Secret:** `GH_TOKEN` — a personal access token or GitHub App token with the scopes your workflow needs.

Once a GitHub skill is attached, set the repository the worker should use. For Signal, attach the skill and repo from **Configure Signal** on the project.

### Arize

**Optional.** Workers already have **read access to traces** in the project you selected, without this skill — Arize provisions a short-lived credential scoped to that project when a run starts, which covers investigations, Signal, and other trace-only work.

Add an Arize skill only to **expand** what a worker can do:

* Query or update **datasets** and **experiments**
* Create or run **evaluators**
* Apply **annotations** or manage other resources through the API

**Secret:** `ARIZE_API_KEY`. The worker can only call what that key allows, so use a dedicated least-privilege key rather than a personal admin key.

### Datadog

Lets a worker query Datadog alongside Arize traces.

**Secrets:** `DD_API_KEY`, `DD_APP_KEY`, and optionally `DD_SITE` (defaults to `datadoghq.com`).

### Custom skill

Installs a skill from a **GitHub repository** into the sandbox — an internal runbook, or a fork of an Arize skill.

| Field              | Requirement                                                                                      |
| ------------------ | ------------------------------------------------------------------------------------------------ |
| **Name**           | Letters, numbers, spaces, hyphens, underscores, periods. Max 253 characters.                     |
| **Install source** | GitHub repo only: `https://github.com/owner/repo`, `git@github.com:owner/repo`, or `owner/repo`. |
| **Description**    | How the harness should use the skill. Max 1000 characters.                                       |
| **Installer**      | `github` (git clone).                                                                            |

Custom skills may declare optional env vars. Every non-custom provider requires at least one secret.

### Add a skill

<Frame>
  <video
    src="https://storage.googleapis.com/arize-assets/doc-images/managed%20agents/managed-agents-add-agent-skill.mp4"
    alt="Adding an agent skill: choose a provider and configure the skill"
    width="100%"
    height="100%"
    style={{
  display: 'block',
  objectFit: 'fill',
  backgroundColor: 'transparent',
}}
    controls
    autoPlay
    muted
    loop
  />
</Frame>

<Steps>
  <Step title="Start agent setup">
    Launch an agent from **Signal & Agents → + New Agent**. The **Connect** step lists the skills that agent needs.
  </Step>

  <Step title="Choose a provider">
    **GitHub**, **Arize**, **Datadog**, or **Custom skill**.
  </Step>

  <Step title="Enter secrets">
    Paste them as `ENV=value` lines or a JSON object. The form shows which env vars it will store.
  </Step>

  <Step title="Save">
    The skill becomes available to every preset in the account. For GitHub, set the repo after saving.
  </Step>
</Steps>

## What a worker can reach

| Source                     | Scope                                                                                                    |
| -------------------------- | -------------------------------------------------------------------------------------------------------- |
| **Arize traces (default)** | Read spans in **the project you selected** for the run, provisioned at run start. No Arize skill needed. |
| **Arize skill (optional)** | Whatever the `ARIZE_API_KEY` you attach permits — datasets, experiments, evaluators, and so on.          |
| **GitHub**                 | The repos and tokens on the GitHub skill, plus the repo set on the preset.                               |
| **Datadog**                | The APIs the Datadog keys allow.                                                                         |
| **Custom skills**          | The GitHub repos you list as install sources, cloned into the sandbox.                                   |

That access is limited to the project you selected, and to what your own space and project permissions already allow. An attached Arize skill adds exactly what its key permits and nothing beyond it.

Each run gets a dedicated sandbox that is torn down when the run ends. Agent execution is traced, so you can audit tool use and outputs from the run's detail view.

## What a worker cannot do

* Serve as your **customer-facing production runtime**. Managed agents improve systems you observe in Arize; they do not replace your app.
* Change production without review. Code lands as a **PR** that you merge.
* Reach any project or space other than the one selected for the run — or anything your own permissions exclude, whichever is narrower.

## Permissions

Account Admins grant managed-agent permissions on [custom roles](/docs/ax/security-and-settings/sso-and-rbac/custom-roles) at the space level. Under legacy space roles, **Space Member+** maps to full managed-agent access, and **Read-only** can view Signal issues but not agent jobs or transcripts.

| Action                                                   | Requires                                       |
| -------------------------------------------------------- | ---------------------------------------------- |
| View agent jobs, automations, and transcripts            | `MANAGED_AGENT_READ` (legacy: Space Member+)   |
| Start a session or automation; manage skills and presets | `MANAGED_AGENT_CREATE` (legacy: Space Member+) |
| Send messages, reprovision, or update a running job      | `MANAGED_AGENT_UPDATE`                         |
| Delete or archive a sandbox job                          | `MANAGED_AGENT_DELETE`                         |
| Enable or configure Signal on a project                  | `PROJECT_UPDATE`                               |
| View Signal issues                                       | `PROJECT_READ`                                 |
| Create AI Provider integrations                          | Organization Admin or Account Admin            |

**Annotators** cannot manage skills, presets, or agents.

Inside a running sandbox, workers use a fixed Managed Agent role today. Per-agent roles you can attach to a preset are on the roadmap.

## Security practices

* **Least privilege** — read-only GitHub tokens until you actually need PRs; Datadog keys scoped to the APIs in use.
* **One skill per integration** — reuse a skill across presets rather than duplicating secrets.
* **No secrets in prompts** — credentials belong on the skill or the AI Provider integration. Skill secrets are encrypted at rest and injected into the sandbox only for the run.
* **Trust your install sources** — the sandbox clones and executes custom skill code during a run.
* **Review outputs** — treat PRs and investigation suggestions as untrusted automation output until a person has read them.

## Related docs

* [Build your own agent](/docs/ax/agents/build-your-own-agent) — The gallery, presets, and customization
* [Cost agent](/docs/ax/agents/cost-agent) — The ready-made agent for spend
* [Signal](/docs/ax/observe/signal) — Ranked issues per tracing project
* [Custom Roles](/docs/ax/security-and-settings/sso-and-rbac/custom-roles) — Grant `MANAGED_AGENT_*` permissions
* [Anthropic AI Provider](/docs/ax/security-and-settings/integrations-playground/anthropic) — Bring your own Anthropic key