Skip to main content
Back to Prompt Library
implementation

Experiment Backlog Generation and Output Formatting

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Perplexity-Powered Growth Intelligence Agent with OpenAI Agents SDK

Format
Text-first
Lines
6
Sections
1
Linked challenge
Perplexity-Powered Growth Intelligence Agent with OpenAI Agents SDK

Prompt source

Original prompt text with formatting preserved for inspection.

6 lines
1 sections
No variables
5 checklist items
Extend your agent's capabilities to translate identified growth opportunities into a structured experiment backlog. For each highly-rated opportunity, the agent should:
1.  **Formulate a clear, testable hypothesis**.
2.  **Suggest a concise experiment title and description**.
3.  **Propose key metrics to track** for experiment success.
4.  **Generate appropriate UTM parameters** (`campaign`, `source`, `medium`, `content`) for tracking a hypothetical marketing campaign related to the experiment.
5.  **Compile all findings** into a final JSON output structure as specified in the evaluation module. Crucially, ensure every insight and experiment is backed by **full citations** (source URL and relevant snippet) from the `perplexity_search` results.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.