Experiment Backlog Generation and Output Formatting

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.