Experimentation Program Overview agent
Experimentation Program Overview is an agent in Mark (Optimizely Agent Platform). It analyzes experimentation performance within a specified timeframe. It generates an overview of program velocity, win rate, and top-performing experiments.
- Challenge – Compiling an overview of your Experimentation program by hand is time-consuming and complex. The overview includes win rates, top performers, and key learnings. Assessing program health and identifying trends is difficult.
- Agent outcome – The agent generates a quarterly business review (QBR)-style Hypertext Markup Language (HTML) report for a specified date range. The report includes program key performance indicators (KPIs), identifies biggest winners, and summarizes key learnings. It also provides a comparative summary table against a prior period. The agent captures page screenshots and sends the report directly to an email address when you provide one.
- Value – Removes the manual effort of compiling program performance data. Stakeholders get a clear, structured view of experimentation health. They can identify successful strategies and communicate impact.
Required Optimizely products
The Experimentation Program Overview agent requires Optimizely Web Experimentation or Optimizely Feature Experimentation.
Install agent
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.
Install the agent from the Directory.
- Go to Directory > Agents.
- (Optional) Enter Experimentation Program Overview or use the drop-down list filters to narrow the list.
- Click Install on Experimentation Program Overview to add it to your Mark instance.
If Install is disabled, connect the Required Optimizely products to your Mark instance first.
Use the agent
In Mark 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) project_ids – Project IDs to filter the report. Provide a single ID or a comma-separated list. If you omit it, the agent runs across all projects. For example, 19963491707 or 12345, 67890.
- (Optional) email – Recipient email address to send the report to directly.
The Experimentation Program Overview agent generates an HTML canvas report. The report includes program KPIs, a top winner card, a runner-up card, and a summary table of top experiments. When you provide an email address, the agent sends the report to that address.
To use the Experimentation Program Overview agent in a workflow agent, add it to your workflow. See Create a workflow agent.
Default agent details
The following are the default details of the Experimentation Program Overview agent. After you install the agent in your Mark instance, 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
Default configuration
The agent uses the following default configuration:
- Inference level – Balanced, which provides reliable answers with additional reasoning.
- Files – None.
- Output – Text.
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.