Back to Prompt Library
testing
Test Code Generation with Performance Constraints
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
Text-first
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
Describe a test case where your agent is tasked with generating a custom PyTorch layer (e.g., a specific type of activation function) given high-level requirements and explicit performance constraints (e.g., 'must be low memory footprint'). Detail how the agent will use its RAG capabilities to find relevant examples and then leverage DeepSeek-R1 to generate the code, followed by validation using your Marvin-MCP integrated tools (e.g., a mock memory usage checker).
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 rubric, target behavior, and pass-fail criteria as the baseline for evaluation.
Tune next
Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.
Verify after
Make sure the prompt catches regressions instead of just mirroring the happy-path examples.