Introduction

Conduct is a backend-powered platform that enables AI agents to build software systematically with long-term memory, team collaboration, and verified progress tracking.

What is Conduct?

Conduct transforms AI agent workflows from ad-hoc prompting into systematic, memory-driven development with:

• Persistent Memory: Centralized backend stores all specs, runs, and checks
• Team Collaboration: Self-hostable backend enables multi-developer workflows
• Verified Progress: Three-phase workflow (spec → run → check)
• Feature Memory: Automatic discovery and tracking of codebase features
• Profile Management: Multi-environment support (local, staging, production)

Version 0.2.0

This documentation covers Conduct v0.2.0, which introduces a fundamental architectural shift from local-first to backend-powered operation. Key changes:

• Self-hostable backend service with REST API
• Lightweight CLI that communicates with backend
• Multi-database support (PostgreSQL, MySQL, SQLite)
• Profile-based credential management
• True team collaboration capabilities

Architecture

┌─────────────┐
│  AI Agent   │
└──────┬──────┘
       │
       ▼
┌──────────────────┐
│  Conduct CLI     │ 
│  + HTTP Client   │
│  + Cache         │
└──────┬───────────┘
       │ REST API
       ▼
┌──────────────────────┐
│  Conduct Backend     │
│  + API Endpoints     │
│  + Auth              │
│  + File Storage      │
└──────┬───────────────┘
       │
       ▼
┌──────────────────────┐
│  Database            │
│  (Postgres/MySQL/    │
│   SQLite)            │
└──────────────────────┘

Getting Started

1. Quick Start - Get up and running in 5 minutes
2. Installation - Detailed setup instructions
3. Configuration - Configure CLI profiles
4. Workflow - Learn the spec → run → check workflow

Use Cases

For AI Agents

• Maintain long-term memory across sessions
• Track specifications and implementation progress
• Verify work with automated checks
• Discover and reuse existing features

For Development Teams

• Centralized AI agent memory management
• Collaborative spec and run tracking
• Self-hosted deployment options
• Multi-environment support

For Organizations

• Audit trail of AI-driven changes
• Compliance and security controls
• Scalable backend infrastructure
• Integration with existing tools

Next Steps

• Quick Start - Get Conduct running in 5 minutes
• Architecture - Understand the system design
• Backend Setup - Deploy your own backend
• CLI Reference - Complete command documentation