Back to Prompt Library
implementation

Workflow Orchestration with Metaflow & Kiln AI

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

Linked challenge: Multi-Agent Code Review & Refactoring

Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Agent Code Review & Refactoring

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Orchestrate the end-to-end code review and refactoring workflow. Describe how Metaflow steps will manage the sequential process (e.g., fetch code, trigger review, receive suggestions, simulate PR creation). Explain how Kiln AI will be used to manage the lifecycle, state, and observability of your OpenAI Agents SDK agents within this Metaflow workflow. Provide pseudo-code or a detailed design outline for this orchestration layer, demonstrating how agents are invoked and their outputs handled.

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.