DOCS

Documentation for secure AI workflows

Everything you need to install, integrate, and protect your code with Pretense for modern AI development workflows.

Quick Start

Up and running in 5 minutes.

Install Guide

curl, Homebrew, or npm.

CLI Reference

All commands grouped by category.

Configuration

.pretense.yaml, .pretenseignore, credentials.

CI/CD Integration

GitHub Actions, GitLab CI, SARIF.

Git Hooks

Pre-commit and pre-push scanning.

API Reference

Proxy endpoints and schemas.

Integrations

Claude Code, Cursor, VS Code, GitHub.

MCP Server

Pre-send scanning inside Claude Code.

Code Architecture

Knowledge graph, MCP, analysis

How It Works

Mutation algorithm, token scanning, proxy pipeline.

Team Deploy

Bash and PowerShell one-liners for team rollout.

How It Works

So we built a firewall for the thing they actually use

Pretense sits between your developer and the AI, like a proxy on the machine. When code goes out, it finds the sensitive parts and swaps them for stand-ins. The AI does its work on the safe version. When the answer comes back, Pretense puts the original values back in place.

The developer writes code the way they always have. The AI answers the way it always has. The passwords, the patient records, the source nobody is allowed to see, none of it ever leaves the laptop.

Your machine

Real code + secrets

Mutate

Pretense

Swaps secrets for stand-ins

Safe prompt

The AI

Sees only stand-ins

← real values restored in the response, back on your machine

Security stops being a thing you bolt on after the fact. It becomes part of the conversation with the AI itself.

security compared

Trusted protection for modern AI workflows

Feature

Pretense

Trasitional DLP

No Protection

Code Protection (preserves AI context)

Deploys in 30 seconds

-

Works offline (local-first)

Multi-provider (Claude + GPT + Gemini)

-

SOC2/HIPAA audit trail

Starting at $0/month