Experiment Planning agent

  • Updated

Experiment Planning is an Optimizely Opal agent that transforms raw ideas into a fully formed experiment plan, complete with hypotheses, key metrics, risks, and critical assumptions.

  • Challenge – A poorly planned test results in few learnings. Running quality tests means teams can get to deeper learning faster.
  • Agent outcome – A fully-formed test plan with hypotheses, metrics, risks, and assumptions.
  • Value – Create an experiment plan that enhances your team's overall testing framework.

Required Optimizely products

None.

Install agent

Opal Administrators, Agent Builders, and Opal 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 agent from the Opal Agent Directory.

  1. Go to Agents > Agent Directory.
  2. Select Experiment Planning.

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

    screenshot of the Experiment Planning entry in the Opal Agent Directory where Install Agent is highlighted

Use the agent

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

  • URL – Page where the test will run.
  • Test Idea – The idea or hypothesis you want to test.

The Experiment Planning agent returns a structured test plan in text, including a hypothesis, variant descriptions, targeting settings, a metrics table, statistical sizing guidance, risks, and assumptions.

To use the Experiment Planning agent in a workflow agent, drag and drop it into your workflow. See Create a workflow agent.

Details

These are the default details for the Experiment Planning agent. After you install the agent in your Opal instance, customize these details for your organization's needs. See Manage agents for instructions.

Input variables

The Experiment Planning agent takes the following input:

  • URL
  • Test Idea

Tools

The Experiment Planning agent uses the following tools internally to process your request:

  • browse_web_html
  • take_webpage_screenshot

Additional details

The agent uses the following default configuration:

  • Inference level – Complex. Provides advanced reasoning and detail.
  • Files – None.
  • Output – Text.

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.