---
title: Feature Experimentation Governance agent
slug: agent-platform/docs/feature-experimentation-governance-agent
docTags: 
createdAt: 2026-09-02T20:57:41.000Z
---

**Feature Experimentation Governance** is an Optimizely Agent Platform agent that analyzes an Optimizely Feature Experimentation project. It generates a read-only Hypertext Markup Language (HTML) governance report on a canvas.

- **Challenge** – Feature flags accumulate across environments, and teams lose visibility into which flags are live, stale, or abandoned.
- **Agent outcome** – The agent produces a client-ready HTML report. The report includes flag counts, a rule-type breakdown, health classification, hygiene indicators, priority review and cleanup lists, and tiered recommendations.
- **Value** – Teams identify cleanup and promotion opportunities in one pass, which reduces technical debt and keeps flag inventory under control.

## Required Optimizely products

The **Feature Experimentation Governance** agent requires Feature Experimentation.

## Install agent

:::hint{type="info"}
**Note**

**Mark Administrators**, **Agent Builders**, and users with the **Add, edit, and install specialized agents** attribute for a custom role can add agents to their organization's Optimizely Agent Platform instance. See [Add users and set permissions.](../../get-started/get-started-with-optimizely-opal-for-administrators.mdx)
:::

Install the agent from the **Directory**.

1. Go to **Directory > Agents**.
2. (Optional) Begin entering *Feature Experimentation Governance* or use the drop-down list filters to narrow the list.
3. Click **Install** on **Feature Experimentation Governance** to add it to your Agent Platform instance.

::Image[]{src="https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/L_7DGFxRqIrMVRJR8Oukt_feature-experimentation-governance.png" size="100" isUploading="false" position="center" width="2036" height="1096" darkWidth="2036" darkHeight="1096" showCaption="false" indent="1"}

If **Install** is disabled, connect the required Optimizely products to your Agent Platform instance first.

## Use the agent

In [Mark chat](docId\:dtNBEttEGVvkhNkwNypLM), enter *@feature\_experimentation\_governance* and provide the following details:

- `Project Name` – Full or partial name of the Feature Experimentation project to analyze. The agent supports partial matches. It searches for the project and confirms the match before it runs.

The agent returns a canvas with a self-contained, read-only HTML governance report. The report covers flag counts, a rule-type breakdown, and health classification. It also covers lifecycle hygiene indicators, a priority review list of stale active flags, cleanup opportunities, and tiered recommendations.

To use the **Feature Experimentation Governance** agent in a [workflow agent](docId:2HD0fUsIsfdek516VtN9l), drag and drop it into your workflow. See [Create a workflow agent](docId\:KWaI2TBwD38sN7p74exoy).

## Details

These are the default details for the **Feature Experimentation Governance** agent. After you [install the agent](docId\:e5srnf01HOPzI4azZZdap), customize these details for your organization's needs. See [Manage agents](docId\:SSeNiblVMXwVvDR_lhtvI) for instructions.

### Input variables

The **Feature Experimentation Governance** agent takes the following input:

- `Project Name`

### Tools

The **Feature Experimentation Governance** agent uses the following tools to process your request:

- `exp_get_schemas`
- `exp_execute_query`
- `exp_summarize_test_result`
- `code_execute`
- `create_canvas`

### Additional details

The agent uses the following default configuration:

- **Inference level** – Standard. Provides fast, efficient responses.
- **Files** – None.
- **Output** – Text. A client-ready, self-contained, read-only HTML Feature Governance & Health report. The report includes flag counts, a rule-type (Kind) breakdown, deterministic health classification, hygiene indicators, Priority Review and Cleanup lists, tiered recommendations, and advisory recommended-action badges (no interactive controls).

:::hint{type="info"}
**Note**

If you use Opti ID, administrators can turn off generative AI in the Opti ID Admin Center. See [Turn generative AI off across Optimizely applications](docId\:X5U0kKD2azV5cIdNqwGNj).
:::