Documentation

Documentation

Welcome to the Conduct documentation. Learn how to manage AI agents at 100x speed with specification-driven development.

Quick Navigation

Getting Started
Install and initialize Conduct in minutes
CLI Reference
Complete command reference
AI Agents
Integration with AI coding tools
Architecture
How Conduct works under the hood

What is Conduct?

Conduct is a control plane for delegating and managing AI agents. It’s also a spec generation CLI that works with all major AI coding tools:

  • Cursor - Command palette integration
  • Claude Code - Automatic context loading
  • Warp - Agent Mode commands
  • Factory - Workflow integration
  • OpenCode - Slash commands
  • GitHub Copilot - Prompt files

Key Features

Specification-First Development

Document features before implementation:

conduct init
# Use /feature command in your AI agent

Automatic Versioning

Conduct automatically versions your specifications:

  • spec.v0.md → spec.v1.md → spec.v2.md
  • Old versions preserved for audit trail
  • No manual version management needed

Nested Hierarchies

Organize features naturally:

conduct/features/
├── authentication/
│   ├── spec.v2.md
│   └── features/
│       ├── oauth/
│       └── two-factor/
└── dashboard/
    └── spec.v1.md

Issue Tracker Integration

Connect with your existing tools:

  • GitHub Issues
  • Jira
  • Linear
  • GitLab
  • Azure DevOps

Next Steps

New to Conduct? Start here:

  1. Install and initialize Conduct in your project
  2. Learn about AI agent integration
  3. Explore the CLI commands
  4. Understand the architecture
  5. Read the comparison with other tools
Getting Started