---
title: Experiment Conflict Checker agent
slug: agent-platform/docs/experiment-conflict-checker-agent
docTags: 
createdAt: 2026-08-12T15:37:09.000Z
---

**Experiment Conflict Checker** is an agent in Agent Platform. It detects conflicts between a proposed experiment and any live experiments in the same project.

- **Challenge** – Running overlapping experiments on the same page corrupts your data, skews results, and leads to flawed conclusions. Flawed conclusions leave teams unable to trust their findings or ship with confidence.
- **Agent outcome** – Analyzes any URL, page, or experiment and cross-references it against every live experiment in your project. It produces a Hypertext Markup Language (HTML) report with an immediate conflict verdict and a full breakdown of every live experiment it analyzed.
- **Value** – Eliminate the guesswork before you launch. Catch conflicts early, protect data integrity, and make faster, more confident decisions. You do not need to audit your experiment configuration manually.

## Required Optimizely products

Optimizely Web Experimentation, Optimizely Performance Edge, or Optimizely Personalization.

## 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 Mark 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 Conflict Checker* or use the drop-down list filters to narrow the list.
3. Click **Install** on **Experiment Conflict Checker** to add it to your Mark instance.

::Image[]{src="https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/Et2Rj2PEto_duSaCLvFjf_install-exp-conflict-checkeragent.png" size="100" isUploading="false" width="2436" height="1102" darkWidth="2436" darkHeight="1102" showCaption="false" indent="1"}

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

If **Install** is disabled, connect the [Required Optimizely products](docId\:w_lOurxOg8fEDKaEK2JXC) to your Mark instance first.
:::

## Use the agent

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

- `Page or URL to check` – The page or URL you want to check for conflicts. Paste a URL, page name, or experiment name or ID, and the agent determines the input type.

The agent produces an HTML conflict report in a [canvas](docId:1_VDSKJ_RG0FEQe0MCTv1). The report shows any live experiments that overlap with the page or URL you specified. It also lists their status and estimated time remaining.

To use the **Experiment Conflict Checker** 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 **Experiment Conflict Checker** agent. After you [install the agent in your Mark instance](docId\:w_lOurxOg8fEDKaEK2JXC), customize these details for your organization's needs. See [Manage agents](docId\:SSeNiblVMXwVvDR_lhtvI) for instructions.

### Input variables

The **Experiment Conflict Checker** agent takes the following input:

- `Page or URL to check`

### Tools

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

- `exp_get_schemas`
- `exp_execute_query`
- `exp_summarize_test_result`
- `reasoning_step`
- `create_canvas`

### Additional details

The agent uses the following default configuration:

- **Inference level** – Pro. Provides maximum reasoning depth.
- **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).
:::