> ## Documentation Index
> Fetch the complete documentation index at: https://quintsecurity.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Introduction
> Visibility and control for every AI agent action in your organization
# The accountability engine for AI Agents
AI agents are shipping to production with zero security telemetry. They execute processes, read and write files, make network calls -- and nobody is watching. Quint changes that.
Quint is an endpoint agent that monitors AI coding assistants and autonomous agents on developer machines. It captures every process execution, file access, and tool invocation as structured events, tracks sessions across agent interactions, and surfaces risk through a centralized dashboard. Think of it as endpoint detection and response (EDR), purpose-built for AI agents instead of humans.
End-to-end flow in one page — follow a single tool call from agent → interception → cloud scoring → dashboard.
Three-tier design: endpoint agent (truth) + cloud API (aggregation) + dashboard (visibility).
## Explore the Platform
Kernel-level ground truth on macOS: process spawns, file I/O, code-signing verification.
Transparent interception of LLM API traffic on macOS — no env vars, no CA trust dance.
How the daemon delivers events to the cloud — batching, overflow, SNS/SQS fan-out.
Unifies proxy + ES into one session model, forwards to cloud, holds the signed audit log.
Cross-session divergence detection and the fleet learning loop. The cloud sees only intent frames, never conversation content.
Session-centric visibility across every agent, machine, and alert in your org.
## How It Works
Quint operates as a system daemon that monitors AI agent activity at the OS level:
```mermaid theme={null}
flowchart TB
subgraph DM["Developer Machine"]
AI["AI Agents\n(Claude Code, Cursor, Windsurf, Cline, Copilot)"]
QD["quint daemon"]
ES["Endpoint Security (macOS)"]
AI -->|"process exec, file I/O, network"| ES
ES -->|"structured events"| QD
end
subgraph AWS["AWS Cloud"]
INGEST["Ingest Service\n(api.quintai.dev/v1/ingest)"]
SNS["SNS FIFO + SQS"]
API["Cloud API"]
PG["PostgreSQL (RDS)"]
QD -->|"events + sessions"| INGEST
INGEST --> SNS
SNS --> API
API --> PG
end
subgraph DASH["Dashboard"]
UI["cloud.quintai.dev\n(Next.js / Vercel)"]
API --> UI
end
```
The daemon detects AI agents through **code signing identification** -- no proxy configuration, no code changes, no agent cooperation required. When an agent like Claude Code spawns a process or accesses a file, Quint captures it as a structured event with full context.
## Three-Tier Architecture
Quint's architecture separates concerns into three layers:
1. **Endpoint Agent (Truth)** -- The daemon running on each machine. Captures ground-truth system events via Endpoint Security on macOS (Linux via eBPF is on the roadmap — see [Platform Coverage](/concepts/platform-coverage)). This is the source of truth for what actually happened.
2. **Cloud API (Aggregation)** -- Go service at `api.quintai.dev`. Receives events and session lifecycle data, stores in PostgreSQL with row-level security, and serves the REST API for querying.
3. **Dashboard (Visibility)** -- Next.js app at `cloud.quintai.dev`. Session-centric UX with drill-down from fleet overview to individual events.
**Divergence between what an agent claims to do and what the OS observes is the key security signal.**
## Production Deployment Flow
```mermaid theme={null}
sequenceDiagram
participant MDM as MDM / IT Admin
participant Mac as Developer Machine
participant Daemon as quint daemon
participant Cloud as api.quintai.dev
participant Dash as Dashboard
MDM->>Mac: Deploy .pkg installer
Mac->>Daemon: Install + configure token
Daemon->>Cloud: Authenticate (qt_deploy_*)
Cloud-->>Daemon: 200 OK
Daemon->>Cloud: Stream events (HTTPS batch to /v1/ingest)
Daemon->>Cloud: Session lifecycle events
Cloud->>Dash: API serves session + event data
Dash-->>MDM: Fleet visibility + risk overview
```
## Event Model
Every captured action is stored as an event with structured fields:
| Field | Description |
| ------------- | ------------------------------------------------------------------------------------------------ |
| `action_type` | What happened: `PROCESS_EXEC`, `FILE_READ`, `FILE_WRITE`, `FILE_DELETE`, `NETWORK_CONNECT`, etc. |
| `tool_name` | The binary or tool that was invoked (e.g., `git`, `node`, `curl`) |
| `arguments` | Process arguments or file paths |
| `session_id` | UUID v5 linking the event to a session |
| `agent_id` | The detected AI agent that triggered the action |
| `risk_score` | Assessed risk level (0-100) |
## Tech Stack
| Component | Technology |
| -------------- | ------------------------------------------------------------------------------------------------------------- |
| Endpoint Agent | Go daemon + Swift Endpoint Security & Network Extension (macOS). Linux (eBPF) + Windows (WFP/ETW) on roadmap. |
| Ingest | HTTPS batch POST to `/v1/ingest` → SNS FIFO → SQS fan-out |
| Cloud API | Go (stdlib net/http, pgx/v5) |
| Database | PostgreSQL (RDS) with Row-Level Security |
| Auth | Supabase (JWT) + Deploy Tokens (SHA-256 hashed) |
| Dashboard | Next.js on Vercel (shadcn/ui) |
| Config | /etc/quint/config.yaml |
## Risk Score Bands
| Score | Risk Level | Color |
| ------ | ---------- | ------ |
| 0-10 | None | Green |
| 11-30 | Low | Blue |
| 31-55 | Medium | Yellow |
| 56-80 | High | Orange |
| 81-100 | Critical | Red |
The risk score is a **shadow-mode corroborating signal**, not the enforcement mechanism. Enforcement is deterministic scope evaluation — only an out-of-scope action against a sensitive resource is block-capable. See [Intent vs Truth](/concepts/intent-vs-truth).