← back to the directory
Library / SDK Agents & Orchestration

DSPy

1Program 2language 3models, 4don’t 5just 6prompt.

the six Ws · specification

W1 Who

Research project from Stanford NLP.

W2 What

Define pipelines and let it optimize the prompts.

W3 Where

A Python library run anywhere.

W4 When

When hand-tuned prompts stop scaling.

W5 Why

Treats prompting as compiled, optimizable programs.

W6 With

Any LLM and a metric to optimize against.

PythonOptimizationPrompts

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.