Experiment Backlog Prioritization agent

  • Updated

The Experiment Backlog Prioritization agent in Optimizely Opal transforms your list of testing ideas into a ranked, actionable plan. It scores each idea against the PIE (Potential, Importance, Ease) framework. The results aligns with your strategic key performance indicators (KPIs). The agent then generates a report with recommended experiments and the reasoning behind every score. This accelerates backlog grooming so your team focuses on the tests that matter most. The ranked plan maximizes the impact of every experimentation sprint.

  • Challenge – Experimentation backlogs grow fast, but bandwidth is limited. Teams struggle to decide which ideas to test next. Many default to gut instinct or stakeholder pressure rather than a structured, objective framework.
  • Agent outcome – The Experiment Backlog Prioritization agent scores each idea in your backlog against the PIE framework. It generates a prioritized report with recommended experiments and the reasoning behind every score, so your team knows what to test next.
  • Value –
    • Removes subjectivity from backlog decisions with a consistent, repeatable scoring methodology.
    • Aligns experiment priorities directly to your strategic KPIs.
    • Surfaces the highest-impact ideas first, maximizing the return on your experimentation investment.
    • Provides transparent reasoning for every score, making it easy to align stakeholders and justify prioritization decisions.

Required Optimizely products

The Experiment Backlog Prioritization agent does not require any other Optimizely products.

Install the Experiment Backlog Prioritization 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.

Install the Experiment Backlog Prioritization agent to make it available in Opal Chat and in workflow agents across your Opal instance. Complete the following steps:

  1. Go to Agents > Agent Directory.

  2. Select Experiment Backlog Prioritization.

    Screenshot of the Agent Directory with the Experiment Backlog Prioritization agent highlighted.

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

    Screenshot of the Agent Directory with the Experiment Backlog Prioritization agent selected with the install agent button highlighted.

Use the Experiment Backlog Prioritization agent

Run the Experiment Backlog Prioritization agent from Opal Chat to transform your list of testing ideas into a ranked, actionable plan. The agent produces a Canvas dashboard with three artifacts: a leaderboard, a quadrant chart, and individual idea scorecards.

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

  • backlog_ideas – Conversion rate optimization (CRO) backlog ideas to evaluate. The input accepts plain text, spreadsheet-derived content, or a structured list of testing ideas.
  • strategic_kpis – Strategic KPIs used to score how well each idea aligns with your priorities.

To add the Experiment Backlog Prioritization agent to a workflow agent, drag and drop it into your workflow. For instructions, see Configure workflow agent.

Default agent configuration

The Experiment Backlog Prioritization agent uses the following default configuration. After you install the agent, optionally customize the following details to match your organization's needs. See Manage agents for instructions.

Input variables

The Experiment Backlog Prioritization takes the following inputs:

  • backlog_ideas
  • strategic_kpis

Tools

The Experiment Backlog Prioritization agent uses the following tools internally to process your request.

  • create_canvas

Additional configuration

The following settings control how the agent processes requests:

  • Inference level – Complex. The inference level determines the processing capacity the agent uses.
  • 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.