> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openagents.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Optimizers and Manifests

> How dsrs improves policies over time.

## 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.