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

# Agent Feedback: Outcome Feedback from Customer Agents

> Agent Feedback collects compact outcome reviews from the AI agents using your product. Add one middleware and get signal from every autonomous interaction.

Agent Feedback tells you whether your product actually worked for the autonomous agents calling it. Instrument your API, website, or MCP server once with any of the first-class SDKs, and every eligible response will carry a lightweight feedback contract that a feedback-aware agent runtime can use to report its outcome — no changes to your handlers, no blocking network calls, no agent accounts required.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Instrument your first endpoint in under five minutes
  </Card>

  <Card title="How It Works" icon="lightbulb" href="/how-it-works">
    Understand the protocol flow from response to outcome review
  </Card>

  <Card title="SDK Guides" icon="code" href="/sdks/node">
    Node, Python, Go, Rust, and MCP integration guides
  </Card>

  <Card title="API Reference" icon="rectangle-terminal" href="/api/overview">
    Explore the public endpoints for outcomes and telemetry
  </Card>
</CardGroup>

## Why Agent Feedback?

AI agents calling your product make decisions independently. Traditional analytics tell you what was called — Agent Feedback tells you whether it actually worked. When an agent completes a task, it reports a concise outcome (`success`, `partial`, or `failure`) along with a single explanatory sentence. That signal flows directly into your dashboard, scoped to your workspace and product.

<CardGroup cols={3}>
  <Card title="Zero Latency" icon="bolt">
    Capability tokens are signed locally — your product response never waits for a network call
  </Card>

  <Card title="Privacy First" icon="shield-halved">
    Only outcome and a short note are collected — no prompts, transcripts, or personal data
  </Card>

  <Card title="Protocol First" icon="file-code">
    One canonical signing algorithm works across every language and framework
  </Card>
</CardGroup>

## Supported Integrations

<CardGroup cols={2}>
  <Card title="Node — Express, Fastify, MCP" icon="node-js" href="/sdks/node">
    One global middleware for Express or Fastify; `instrumentMcp` for MCP servers
  </Card>

  <Card title="Python — ASGI & WSGI" icon="python" href="/sdks/python">
    Dependency-free middleware for FastAPI, Starlette, Flask, and Django
  </Card>

  <Card title="Go — net/http" icon="golang" href="/sdks/go">
    Standard-library middleware using only built-in packages
  </Card>

  <Card title="Rust — Axum & Tower" icon="gear" href="/sdks/rust">
    Tower layer for Axum with a bounded Tokio background queue
  </Card>
</CardGroup>

## Get Started in Three Steps

<Steps>
  <Step title="Create a product in the dashboard">
    Sign in, create a workspace, and add your first product to get an API key in the format `af_live_...`.
  </Step>

  <Step title="Add the middleware">
    Install the SDK for your framework and add one line of middleware — no handler changes required.
  </Step>

  <Step title="Watch outcomes arrive">
    Deploy and let agents call your product. Outcome reviews appear in your dashboard as agents report results.
  </Step>
</Steps>