Experiment Program Health Review agent
Experiment Program Health Review is an agent in Mark (Optimizely Agent Platform). It analyzes Optimizely Web Experimentation or Optimizely Feature Experimentation projects. It routes you to the correct interactive dashboard for each program type.
- Challenge – Experimentation programs generate large volumes of data. Translating that data into a clear, program-level story takes time and effort. Teams lack a single view that shows what is working, what is not, and where to focus next. This applies across Web Experimentation and Feature Experimentation.
- Agent outcome – The agent analyzes your Experimentation project data and routes you to the dashboard that matches your program type. Both dashboards are ready to share.
- Value – The agent removes the manual effort of piecing together program performance across experiments. Teams and stakeholders get a clear, structured view of experimentation health. This view supports faster, more confident decisions about where to invest next.
Required Optimizely products
The Experiment Program Health Review 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 Experiment Program Health Review or use the drop-down list filters to narrow the list.
- Click Install on Experiment Program Health Review 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 @experiment_program_health_review and provide the following details:
- Project ID or Project Name – The project to analyze. Enter a project ID or a project name. You can enter several projects.
- Timeframe – The period to analyze. Enter a relative period or a date range, such as last 6 months, Q1 2026, or 2026-01-01 to 2026-06-30. The agent asks for a timeframe if you leave it blank.
The Experiment Program Health Review agent returns a canvas. Web Experimentation projects receive an Experiment Signal Intelligence Dashboard with a journey heatmap. Feature Experimentation projects receive a Program Health Dashboard with lifecycle and performance intelligence. If you enter both project types, the agent asks which dashboard to generate first. It builds one dashboard per run.
To use the Experiment Program Health Review agent in a workflow agent, add it to your workflow. See Create a workflow agent.
Default agent details
These are the default details for the Experiment Program Health Review agent. After you install the agent in your Mark instance, customize these details for your organization's needs. See Manage agents for instructions.
Input variables
The Experiment Program Health Review agent takes the following input:
- Project ID or Project Name
- Timeframe
Tools
The Experiment Program Health Review agent uses the following tools internally to process your request:
- exp_program_reporting_execute_query
- exp_program_reporting_win_rate
- exp_program_reporting_top_experiments
- exp_execute_query
- exp_get_schemas
- create_canvas
Default configuration
The agent uses the following default configuration:
- Inference level – Pro, which provides maximum reasoning depth.
- 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.