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

# Introduction

> Reliability infrastructure for AI agents

# Welcome to ACME Docs

ACME builds the reliability layer for AI agent systems. We help operators answer the question every team running agents eventually asks:

> "My agents are running. But are they *reliable*?"

## The Problem

Standard monitoring catches crashes. But agents fail in ways that don't crash:

* **Silent failures** — the agent looks healthy but stopped making progress
* **Stalls** — waiting on a response that will never come
* **Drift** — behavior changes session-to-session without obvious cause

These failures don't trigger alerts. They just... happen. And you find out when a user complains or a workflow silently stops.

## The ACME Stack

We provide tools across the reliability lifecycle:

| Phase       | Tool                                    | What It Does                                      |
| ----------- | --------------------------------------- | ------------------------------------------------- |
| **Detect**  | [RadCheck](/products/radcheck/overview) | Read-only scan, 0-100 reliability score           |
| **Triage**  | [OCTriage](/products/octriage/overview) | Entry-point terminal for incident assessment      |
| **Protect** | [Sentinel](/products/sentinel/overview) | Runtime guardrails for stalls and silent failures |
| **Control** | Agent911                                | Unified control plane with recovery guidance      |

## Getting Started

The fastest path to understanding your agent reliability:

<CardGroup cols={2}>
  <Card title="5-Minute Quickstart" icon="rocket" href="/quickstart">
    Install observational mode. Get your first RadCheck score.
  </Card>

  <Card title="RadCheck Overview" icon="magnifying-glass" href="/products/radcheck/overview">
    Understand what RadCheck scans and how scores work.
  </Card>
</CardGroup>

## Free vs Paid

ACME follows a trust-first model:

* **Free**: RadCheck (scan), OCTriage (triage), Lazarus Lite (backup check)
* **Paid**: Sentinel (runtime protection), Agent911 (control plane)

Free tools build trust. Paid tools solve the problem at scale.