Back to Prompt Library
implementation
Integrate Marvin and MCP for a Mock Profiler Tool
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: PyTorch Optimization Agent
Format
Code-aware
Lines
1
Sections
1
Linked challenge
PyTorch Optimization Agent
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Using Marvin, define a declarative AI function that acts as an interface to a mock PyTorch profiler. This function should take PyTorch code as input and return mock performance metrics (e.g., execution time, memory usage for specific operations). Explain how this profiler tool is exposed via MCP and how your agent will invoke it to validate proposed optimizations.
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.