AI Guard Documentation
Explore technical guides, workflow configurations, and architectural deep-dives for catching unreliable and insecure AI-generated code.
Getting Started
Quick installation, prerequisites, CLI scan, and choosing the right preset for your repository.
ESLint Plugin Configuration
Integrate with ESLint 9 Flat Config or ESLint 8 .eslintrc, customize rule severities, and inline disables.
CLI Tool Reference
Command reference for run, changed, baseline, init-context, doctor, and fail strategies in CI/CD.
GitHub Actions & CI/CD
Automate PR checks with SARIF 2.1.0 output, inline review annotations, and differential scanning.
AI Coding Context (CLAUDE.md & .cursorrules)
Shift safety left: translate AST rules into prompt directives for Cursor, Claude Code, and Copilot.
Browse All 18 AST Rules
Inspect every rule in detail: unhandled promises, hardcoded API secrets, SQL concatenation, and dead branch detection with before/after code fixes.
Core Architecture & Philosophy
AI coding tools like GitHub Copilot, Cursor, and Claude Code generate impressive code rapidly, but probabilistic models do not guarantee correctness. Subtle bugs—like unhandled promise rejections, swallowed exceptions, or missing authorization checks—frequently pass standard syntax checks.
AI Guard provides a deterministic safety layer. Unlike LLM-based PR reviewers that hallucinate and add latency, AI Guard evaluates AST nodes with 100% predictability in milliseconds. Every rule is calibrated against hundreds of real AI code samples to ensure low false-positive rates.
Zero Type-Info Lag
AST structural heuristics run in <400ms without requiring slow TypeScript project compiler instantiation.
GitHub-Native SARIF
Upload findings straight into GitHub Code Scanning and display inline review annotations on PR diffs.
Prompt Shift-Left
Generate CLAUDE.md and .cursorrules files to stop models from generating anti-patterns at the prompt stage.