# How It Works

Guardrail's platform connects to EVM RPC nodes with archive and tracing support. We index every transaction in real-time and run your configured guards against relevant state changes.

<figure><img src="https://818258224-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FgMfPgPt8Iu1wrPze8HXT%2Fuploads%2Fgit-blob-fcc4a9b70811022573441d3a9e57db0b23467482%2Fslider%20v1.png?alt=media" alt=""><figcaption></figcaption></figure>

## Architecture Overview

{% @mermaid/diagram content="flowchart LR
A\[Blockchain<br/>RPC Node] --> B\[Guardrail<br/>Indexer]
B --> C\[Your Alert<br/>Channels]
B --> D\[Guard<br/>Processors]" %}

**Indexer** — Subscribes to new blocks and indexes transactions with full trace data. Supports archive queries for historical state.

**Guard Processors** — Stateless checks that evaluate transactions against your configured rules. Each guard has trigger conditions (when to run) and alert conditions (when to notify).

**Response System** — Delivers alerts to your channels and can trigger automated responses like contract pauses or webhook calls.

## Detection Speed

Guards trigger on transaction confirmation. Alert delivery is typically under 1 second from block finality. For chains with fast block times, this means near-instant detection.

## What Makes Us Different

**Custom over generic** — Other tools send generic alerts. We build monitoring that understands your protocol's unique risks, economic model, and business logic.

**Full trace access** — We analyze the complete execution path of transactions, including internal calls, not just top-level events.

**Simulation support** — Test guards against historical transactions before deploying. Replay any transaction to see what would have triggered.

***