Experimentation Program Overview agent

  • Updated

Optimizely Opal's Experimentation Program Overview agent creates a report on how your Optimizely Experimentation program is performing using top experiment and win rate data. Get a polished overview with KPIs, your biggest wins, key learnings, and a summary table.

  • Challenge – Manually compiling a comprehensive overview of your Experimentation program, including win rates, top performers, and key learnings, can be time-consuming and complex. It is difficult to quickly assess program health and identify trends.
  • Agent outcome – The agent generates a Quarterly Business Review (QBR)-style HTML report for a specified date range. This report includes program KPIs, identifies biggest winners, summarizes key learnings, and provides a comparative summary table against a prior period. It also captures page screenshots and can be sent directly through email.
  • Value – You can get a clear, actionable summary of your Experimentation program's performance, letting you quickly identify successful strategies, understand areas for improvement, and communicate the impact of your experiments to stakeholders. It automates the reporting process, saving time and ensuring consistent, data-driven insights.

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 Experimentation Program Overview.

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

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

Use

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

  • Date range – The time period for the report, For example, "Q4 2025", "January 2026", or "Last 90 days".
  • (Optional) Email – Recipient email address if you want the report sent directly.
  • (Optional) Project IDs – Project IDs to filter the report. Provide a single ID or comma-separated list. If omitted, the agent runs across all projects. For example, "19963491707" or "12345, 67890".

To use the Experimentation Program Overview 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 Experimentation Program Overview 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) email
  • (Optional) project_ids

Tools

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

Output

  • Inference level – Balanced
  • Creativity – 0.5

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.