Test Ideation agent

  • Updated

The Test Ideation agent in Optimizely Opal generates a prioritized package of experiment ideas for any page, grounded in what the page looks like today, what has already been tested, and what is most likely to move your goal.

  • Challenge – Identifying high-impact experiments is time-consuming. Without historical context, you risk repeating dead ends or missing obvious wins.
  • Agent outcome – A prioritized list of experiment ideas tailored to your page, goal, and past results.
  • Value – Accelerates your experimentation pipeline with ideas that build on what you know, not what you guess.

The Test Ideation agent powers the Get Test Ideas button available directly within Optimizely Web Experimentation, Personalization, and Feature Experimentation.

Required Optimizely products

None

Install the Test Ideation 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, complete the following steps:

  1. Go to Agents > Agent Directory.
  2. Select Test Ideation.

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

    Screenshot of the Agent Directory page in Optimizely Opal where the Test Ideation agent is shown with the Install Agent button.

Use the Test Ideation agent

In Opal Chat

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

  • URL – The page URL to analyze and generate ideas for. This is the primary input. The Test Ideation agent visits the page, takes a screenshot, and uses the screenshot as the foundation for all recommendations.
  • (Optional) Goal – Describe the business goal or problem you want to solve. For example, increase lead submissions, reduce drop-off on mobile, or get more users to create an account. If omitted, the Test Ideation agent infers the goal from the page.
  • (Optional) Metric – The specific metric you want to move. For example, conversion rate, revenue per visitor, or click-through rate on call to action (CTA). If omitted, the Test Ideation agent identifies the most important metric based on the page type and goal.
  • (Optional) Past Experiments – Specific experiment names or IDs you want the Test Ideation agent to reference and build on. The agent pulls the full results for each and uses them to inform recommendations. It iterates on winners, reframes losers, and avoids dead ends.
  • (Optional) Search Experiments – Keywords or themes to search your experiment history for relevant past tests. For example, checkout, CTA copy, or mobile homepage. The Test Ideation agent finds and pulls results for the most relevant experiments.
  • (Optional) Context – Any additional context that should shape the recommendations. Examples include audience information, known pain points, upcoming initiatives, areas to avoid, and heatmap findings.

Add to a workflow

The Test Ideation agent is an Optimizely-managed agent (an agent that Optimizely controls and locks from direct edits). Duplicate it before adding it to a workflow. If you add it without duplicating first, Optimizely displays a prompt to copy the agent.

Screenshot of the workflow builder in Optimizely Opal where a prompt to copy the Test Ideation agent is displayed.

Default agent configuration

The following default details apply to the Test Ideation agent. Because it is an Optimizely-managed agent, Optimizely locks some fields to ensure consistent performance. To make updates, duplicate the agent instead.

Input variables

The Test Ideation agent accepts the following inputs:

  • URL
  • (Optional) Goal
  • (Optional) Metric
  • (Optional) Past Experiments
  • (Optional) Search Experiments
  • (Optional) Context

Tools

The Test Ideation agent uses the following tools internally to process your request:

  • browse_web
  • browse_web_html
  • take_webpage_screenshot
  • analyze_image_content
  • exp_get_schemas
  • exp_execute_query
  • exp_summarize_test_result
  • exp_program_reporting_top_experiments
  • exp_program_reporting_underperforming_experiments
  • create_canvas
  • edit_canvas

Additional configuration

The following settings control how the agent processes requests:

  • Inference level – Pro. Determines the processing capacity the agent uses. Pro inference provides higher accuracy for complex requests.
  • Files – None. This agent does not use file attachments.

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.