Back to Prompt Library
implementation

Automate Code Review with Llama 3 via HF Endpoint

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

Linked challenge: Accelerated Code Dev & Review Agent

Format
Text-first
Lines
1
Sections
1
Linked challenge
Accelerated Code Dev & Review Agent

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Develop the 'CodeReviewer' agent in Mastra AI to automatically review the code generated by the 'CodeGenerator'. The 'CodeReviewer' should use a custom tool that calls a Llama 3 8B Instruct model deployed on a Hugging Face Inference Endpoint. The tool should take the generated code as input and return comments on code quality, potential bugs, and suggestions for improvement. The agent should then provide a structured review summary. Demonstrate this by feeding the output from the 'FeatureImplementation' task into the reviewer.

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.