Back to Prompt Library
planning

DSPy Pipeline Design for Code Review

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

Linked challenge: Agentic Code Optimization & Review

Format
Text-first
Lines
1
Sections
1
Linked challenge
Agentic Code Optimization & Review

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Design a DSPy pipeline for your code optimization agent. Define the signature(s) (input/output schemas) for tasks like 'IdentifyIssues', 'SuggestOptimization', and 'ExplainChanges'. Outline how you'll use DSPy's modules (e.g., `ChainOfThought`, `Program` or `Retrieve`) to compose a robust workflow for analyzing code snippets and generating improvements using DeepSeek-R1. Consider how to incorporate RAG over a codebase for context.

Adaptation plan

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

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.