Skip to main content

​
Overview

DSPy optimizers compile better policies from real outcomes. In OpenAgents, dsrs optimizers operate on collected examples and produce versioned manifests you can roll forward or back.

​
Optimizers

  • MIPROv2: prompt and instruction search
  • COPRO: compositional prompt optimization
  • GEPA: evolutionary policy search
  • Pareto: multi-objective tradeoff selection

​
Training Data

Autopilot captures examples and labels during runs. Plan Mode writes examples to:
  • ~/.openagents/autopilot-desktop/training/plan_mode.json

​
Manifests and Scorecards

Optimizers emit compiled manifests and scorecards under:
  • ~/.openagents/autopilot-desktop/manifests/plan_mode/
  • ~/.openagents/autopilot-desktop/optimization/
These artifacts enable:
  • Versioning and rollback
  • A/B or shadow testing
  • Promotion gates based on metrics

​
Why It Matters

This makes agent behavior evolvable without rewriting product logic. Policies improve through data, and every improvement is auditable and reversible.