Back to Prompt Library
implementation
Orchestrate Multi-Agent Policy Analysis Team
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Policy Impact Analysis Agent
Format
Text-first
Lines
1
Sections
1
Linked challenge
Policy Impact Analysis Agent
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Refine your OpenAI agent system to include multiple specialized agents (e.g., 'Legal Analyst Agent', 'Economic Impact Agent') that can communicate and delegate tasks within a single thread. The primary 'Policy Analyst Agent' acts as an orchestrator, receiving user queries (from Ellipsis), using o3 to understand intent, and then directing sub-tasks to the specialized agents who use their respective tools (Distyl, Great Expectations, Letta for memory) to gather and analyze information before reporting back to the orchestrator for synthesis.
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.