---
title: Experiment Planning agent
slug: agent-platform/docs/experiment-planning-agent
docTags: 
createdAt: 2026-08-12T15:37:08.000Z
---

**Experiment Planning** is an Optimizely Agent Platform agent that transforms raw ideas into a fully formed experiment plan. The plan includes hypotheses, key metrics, risks, and critical assumptions.

- **Challenge** – A poorly planned test results in few learnings. Running quality tests means teams can get to deeper learning faster.
- **Agent outcome** – A fully formed test plan with hypotheses, metrics, risks, and assumptions.
- **Value** – Create an experiment plan that enhances your team's overall testing framework.

## 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 *Experiment Planning* or use the drop-down list filters to narrow the list.
3. Click **Install** on **Experiment Planning** to add it to your Agent Platform instance.

::Image[]{src="https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/C3RHeOM51WDzfwNnrb-Ep_install-exp-planning-agent.png" size="100" isUploading="false" width="1994" height="1074" darkWidth="1994" darkHeight="1074" showCaption="false" indent="1"}

## Use the agent

In [Mark chat](docId\:dtNBEttEGVvkhNkwNypLM), enter *@experiment\_planning* and provide one of the following details:

- `URL` – Page where the test will run.
- `Test Idea` – The idea or hypothesis you want to test.

The **Experiment Planning** agent returns a structured test plan in text. The plan includes a hypothesis, variant descriptions, targeting settings, a metrics table, statistical sizing guidance, risks, and assumptions.

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

## Details

The following are the default details of the **Experiment Planning** agent. After you [install the agent in your Agent Platform instance](docId\:ojN9RQfH-nZhQmRdYIYgO), customize these details based on your organization's needs. See [Manage agents](docId\:SSeNiblVMXwVvDR_lhtvI) for instructions.

### Input variables

The **Experiment Planning** agent takes the following input:

- `URL`
- `Test Idea`

### Tools

The **Experiment Planning** agent uses the following tools internally to process your request:

- `browse_web_html`
- `take_webpage_screenshot`

### Additional details

The agent uses the following default configuration:

- **Inference level** – Complex. Provides advanced reasoning and detail.
- **Files** – None.
- **Output** – Text.

:::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).
:::