# agentful > Autonomous product development kit for Claude Code. Transform any project into a 24/7 self-building system with specialized agents. ## Docs - [Deployment Guide](/deployment): This guide covers deploying the agentful documentation site and publishing the npm package. - [Philosophy](/philosophy): agentful is built on Anthropic's research-validated multi-agent patterns. Here's the philosophy that drives every design decision. - [Bug Fixing Workflow](/workflows/bug-fixing): Complete guide to identifying, isolating, fixing, and validating bug fixes using agentful's systematic workflow. - [Feature Development Workflow](/workflows/feature-development): Complete guide to building features from requirements to production-ready code using agentful's autonomous development workflow. - [Workflows](/workflows): Complete end-to-end workflows for autonomous product development with agentful. - [Refactoring Workflow](/workflows/refactoring): Complete guide to improving code structure, maintainability, and performance using agentful's systematic refactoring workflow. - [Testing Workflow](/workflows/testing): Complete guide to achieving comprehensive test coverage (80%+) using agentful's systematic testing workflow. - [CLI Reference](/reference/cli-reference): Complete reference for all agentful CLI commands, options, and outputs. - [Settings Reference](/reference/settings-reference): Complete reference for `.claude/settings.json` configuration including hooks, permissions, and all available options. - [State Files Reference](/reference/state-files): Complete reference for all agentful state file formats, schemas, and validation rules. - [Best Practices](/guides/best-practices): Learn from real agentful development experience. These patterns, anti-patterns, and optimizations will help you get the most out of autonomous development. - [Guides Overview](/guides): Practical guides to help you succeed with agentful in real-world development scenarios. - [Team Adoption Guide](/guides/team-adoption): Using agentful in a team environment requires coordination, shared standards, and clear workflows. This guide shows you how to adopt agentful across your team effectively. - [Troubleshooting Guide](/guides/troubleshooting): agentful usually runs smoothly, but when issues arise, this guide helps you diagnose and resolve them quickly. - [Writing Product Specifications](/guides/writing-product-md): The quality of your product specification directly determines how well agentful can build your product. A well-written spec leads to autonomous development success. A vague spec leads to confusion, decisions, and delays. - [Configuration](/getting-started/configuration): Customize agentful to match your workflow, tech stack, and preferences. - [Your First Project](/getting-started/first-project): Build your first complete autonomous project with agentful. We'll create a **Task Management App** together. - [Installation](/getting-started/installation): Get agentful up and running in your project in under a minute. - [Quick Start](/getting-started/quick-start): Get agentful building your project autonomously in 5 minutes. - [REST API Service](/examples/api-development): A production-ready REST API for an e-commerce platform with user management, product catalog, order processing, and comprehensive testing. - [Modern Web Application](/examples/frontend-project): A stunning frontend-only project built with Next.js 14, featuring a reusable component library, sophisticated state management, and seamless API integration. - [Full-Stack SaaS Application](/examples/full-stack-app): A complete task management system for remote teams with authentication, real-time updates, and role-based access control. - [Examples](/examples): Learn from complete, real-world examples of projects built with agentful. Each example shows you: - [Agents](/core-concepts/agents): Agents are the **building blocks of agentful** - specialized AI workers, each with a specific domain of expertise, well-defined responsibilities, and clear boundaries. They don't just "write code" - they follow patterns, enforce standards, and collaborate through the orchestrator. - [Core Concepts Overview](/core-concepts): agentful represents a paradigm shift in software development - **autonomous product development powered by specialized AI agents**. Instead of writing code yourself, you coordinate a team of AI agents that build your product for you. - [Orchestrator](/core-concepts/orchestrator): The orchestrator is the **brain of agentful** - the conductor that leads a symphony of specialized agents without ever playing an instrument itself. It doesn't write code. It thinks, plans, delegates, validates, and tracks progress. - [Skills](/core-concepts/skills): Skills are **domain-specific capabilities** that can be added to agents to extend their functionality with specialized knowledge. Think of skills as "plugins" that give agents superpowers in specific domains. - [Slash Commands](/core-concepts/slash-commands): Slash commands are your **control interface for agentful** - simple, human-readable commands that trigger complex autonomous workflows. Think of them as the steering wheel, accelerator, and dashboard for autonomous development. - [State Management](/core-concepts/state-management): State management is **agentful's memory and truth source** - the system of record that tracks what's done, what's blocked, what's pending, and what decisions have been made. All coordination happens through simple JSON files that serve as the single source of truth. - [Agent Configuration](/configuration/agent-configuration): agentful's agents are highly configurable. You can customize existing agents, create new specialized agents, or modify agent behavior for your specific tech stack. - [Configuration Overview](/configuration): agentful provides a flexible configuration system that lets you customize every aspect of autonomous product development. Configuration is split between project-level settings and agentful's internal configuration. - [Project Structure](/configuration/project-structure): agentful requires a specific project structure to function correctly. Understanding the required and optional files helps you organize your project effectively. - [Workflow Configuration](/configuration/workflow-configuration): agentful workflows are defined as slash commands. You can customize existing commands, create new workflows, and integrate with your development processes. - [/agentful-decide](/commands/agentful-decide): Answer pending decisions that are blocking development progress. - [/agentful-start](/commands/agentful-start): Start or resume autonomous product development loop by delegating to the orchestrator agent. - [/agentful-status](/commands/agentful-status): Show current progress, completion percentage, phase, and what's being worked on. - [/agentful-validate](/commands/agentful-validate): Run all quality checks and validation gates by delegating to the reviewer agent. - [/agentful](/commands/agentful): The **main conversational interface** for agentful. Just talk naturally - no need to remember specific commands or syntax. - [agentful Commands Reference](/commands): Complete reference guide for all agentful slash commands used in autonomous product development. - [24/7 Development with Ralph Wiggum](/autonomous-development/24-7-development): Ralph Wiggum is a Claude Code plugin that enables continuous looping - perfect for autonomous development that runs while you sleep. This guide explains how to use Ralph Wiggum with agentful for true 24/7 productivity. - [Autonomous Development](/autonomous-development): agentful's autonomous development mode enables Claude Code to work independently, building your product 24/7 with minimal human intervention. This comprehensive guide explains how autonomous development works and how to use it safely. - [Monitoring](/autonomous-development/monitoring): Effective monitoring is crucial for autonomous development. This guide explains how to track progress, understand what agentful is building, and ensure quality throughout the development process. - [Quality Gates](/autonomous-development/quality-gates): agentful's quality gates ensure that all code entering your codebase meets production-ready standards. This comprehensive guide explains each gate, passing criteria, and how to troubleshoot failures. - [Recovery Strategies](/autonomous-development/recovery-strategies): agentful's self-healing capabilities automatically resolve most validation failures through the fixer agent. This guide explains how recovery works, what can be auto-fixed, and how to handle issues requiring manual intervention. - [Architect Agent](/agents/architect): The Architect analyzes the tech stack and dynamically generates specialized agents for frameworks, databases, and tools used in the project. - [Backend Agent](/agents/backend): The Backend Agent implements server-side code following clean architecture patterns with proper separation of concerns. - [Creating Custom Agents](/agents/custom-agents): Extend agentful by creating custom agents for specialized tasks, technologies, or workflows. - [Fixer Agent](/agents/fixer): The Fixer Agent automatically resolves validation failures identified by the Reviewer, ensuring code meets quality standards. - [Frontend Agent](/agents/frontend): The Frontend Agent implements user interfaces, client-side logic, and ensures excellent user experience. - [agentful Agents](/agents): agentful uses a multi-agent system where each agent has specialized responsibilities. The agents work together autonomously to build, test, and validate production-ready applications. - [Orchestrator Agent](/agents/orchestrator): The Orchestrator is the central coordinator of the agentful system. It manages the entire development lifecycle by reading state, delegating work to specialists, and tracking progress. - [Reviewer Agent](/agents/reviewer): The Reviewer Agent ensures code quality and production readiness through comprehensive validation of all changes. - [Tester Agent](/agents/tester): The Tester Agent ensures code quality through comprehensive testing, achieving 80% code coverage across all features.