Experiment Program Health Review agent

  • Updated

Optimizely Opal's Experiment Program Health Review agent turns winning test results into a stakeholder-ready business case. It projects annual impact, quantifies revenue lift, and applies an optional conservative discount. The output gives your experimentation program a defensible number to justify investment and ship winning variations with confidence.

  • Challenge – Communicating the business impact of a winning experiment is difficult. Teams struggle to translate test results into concrete, stakeholder-ready numbers. Lift percentages and statistical significance do not justify investment to a non-technical audience.
  • Agent outcome – The Experiment Value Estimator generates a report with the projected annualized impact of rolling out a winning experiment variation. Provide conversion rates, traffic, duration, and value per conversion. The agent returns a shareable projection of the revenue or business value the winning variation delivers.
  • Value – 
    • Quantifies the return on investment (ROI) of experimentation in dollar terms stakeholders understand.
    • Removes the guesswork from post-experiment reporting.
    • Supports confident decisions on whether to ship winning variations.
    • Applies an optional conservative discount factor so projections stay realistic and defensible.

Required Optimizely products

Web Experimentation or Feature Experimentation with Opal.

Install 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.

In Opal,

  1. Go to Agents > Agent Directory.
  2. Select Experiment Program Health Review.

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

    Screenshot of the Agent Directory with the Experiment Program Heath Review agent selected with Install Agent highlighted.

If Install Agent is disabled, ensure you have the Required Optimizely products connected to your Opal instance.

Use

In Opal Chat, enter @experiment_program_health_review and provide the following details:

  • date_range – The time period for the report. Accepts natural language (for example, Q4 2025, January 2026, Last 90 days) or date ranges (for example, 01/01/2025 - 12/31/2025). The agent converts the date_range to ISO-8601 timestamps.
  • (Optional) project_ids – Project IDs to filter the report. Provide a single ID or comma-separated list. If omitted, runs across all projects. Example: 19963491707 or 12345, 67890.
  • (Optional) email – Email address to send the report to.

To use the Experiment Program Health Review agent in a workflow agent, drag and drop it into your workflow. See the Configure workflow section in the Create a workflow agent documentation.

Details

The following are the default details of the Experiment Program Health Review agent. After you install the agent in your Opal instance, you can customize these details based on your organization's needs. See Manage agents for instructions.

Input variables

  • date_range
  • (Optional) project_ids
  • (Optional) email

Tools

  • create_canvas
  • exp_program_reporting_top_experiments
  • exp_program_reporting_win_rate
  • take_webpage_screenshot
  • exp_execute_query
  • send_email

Output

  • Inference level – Balanced
  • Files – None

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.