Back to Prompt Library
implementation
Orchestrate Agents with Shakudo and Add Observability
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Agentic SaaS Competitive Intelligence
Format
Text-first
Lines
1
Sections
1
Linked challenge
Agentic SaaS Competitive Intelligence
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Now, integrate your Pydantic AI agents into a multi-agent workflow orchestrated by Shakudo (you can simulate Shakudo's orchestration by defining sequential agent calls or a simple graph). Focus on how the output of the 'Market Researcher' agent becomes the input for the 'Competitor Analyst' agent. Implement basic logging for agent actions and outputs. Finally, describe how you would integrate Arize AI to monitor the structured outputs and execution flow, specifically capturing the Pydantic models generated by each agent.
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.