Experiment Conflict Checker agent

  • Updated

The Experiment Conflict Checker in Optimizely Opal detects conflicts between the experiment you plan to launch and any live experiments.

  • Challenge – Running overlapping experiments on the same page can corrupt your data, skew results, and lead 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 an HTML report with an immediate conflict verdict and a full breakdown of every live experiment it analyzed.
  • Value – Eliminate the guesswork before you launch. Teams catch conflicts early, protect data integrity, and make faster, more confident decisions, without manually auditing their experiment configuration.

Required Optimizely products

The Experiment Conflict Checker requires one of the following Optimizely Experimentation products:

  • Optimizely Web Experimentation
  • Optimizely Performance Edge
  • Optimizely Personalization

Install the Experiment Conflict Checker agent

Opal 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 Opal instance. See Add users and set permissions.

Install the Experiment Conflict Checker to make it available in Opal Chat and in workflow agents across your Opal instance. Complete the following steps:

  1. Go to Agents > Agent Directory.

  2. Select Experiment Conflict Checker.

    Screenshot of the Agent Directory where the Experiment Conflict Checker is selected, showing the agent details pane before installation.

  3. Click Install Agent to add it to your instance.

    Screenshot of the Agent Directory where Install Agent is highlighted, showing the button that adds the Experiment Conflict Checker to an Opal instance.

Use the Experiment Conflict Checker agent

Run the Experiment Conflict Checker from Opal Chat to identify conflicts before you launch. Call it from inside an existing experiment to check that specific experiment. In Opal Chat, 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 any of the following and the agent determines the input type.
    • A URL, like https://www.example.com/checkout or www.example.com.
    • A page name from your Optimizely project, like Homepage or Checkout Page.
    • An experiment name or ID, like Hello World or 12345678901. Or call the agent from inside an existing experiment, and Opal checks for conflicts before you launch that experiment.

To use the Experiment Conflict Checker agent in a workflow agent, drag and drop it into your workflow. For instructions, see Configure workflow agent.

Default agent configuration

The Experiment Conflict Checker agent uses the following default configuration. After you Install the Experiment Conflict Checker agent, customize these details based on your organization's needs. See Manage agents for instructions.

Input variables

The Experiment Conflict Checker takes the following input:

  • Page or URL to check (can be a URL, page name, experiment name, or experiment ID).

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 configuration

The following settings control how the agent processes requests:

  • Inference level – Pro. Determines the processing capacity the agent uses. Pro inference provides higher accuracy for complex requests.
  • Files – None. This agent does not use file attachments.

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.