Babysitter User Guide
Welcome to the Babysitter documentation. Babysitter is an AI-powered development workflow orchestrator that enables iterative quality convergence with human-in-the-loop approval through breakpoints.
Quick Start
Get up and running with Babysitter in minutes.
| Step | Description | Time |
|---|---|---|
| Installation | Install the CLI and Claude Code plugin | 5 min |
| Quickstart | Configure your environment | 5 min |
| First Run | Execute your first babysitter workflow | 10 min |
What is Babysitter? (Start Here if You're New)
Babysitter automates the "try, check, fix, repeat" cycle of development so you don't have to do it manually.
The Problem Babysitter Solves
When you ask an AI to write code, you typically:
- Get code from the AI
- Run tests → tests fail
- Send errors back to AI
- Get fixed code
- Run tests again → still failing
- Repeat 5-10 times...
Babysitter automates this entire loop, running it until your quality targets are met.
How It Works (In Plain English)
┌─────────────────────────────────────────────────────────────────┐
│ YOU: "Build a login page with tests" │
│ ↓ │
│ BABYSITTER: Runs this loop automatically: │
│ 1. AI writes code │
│ 2. Tests run → 60% pass │
│ 3. AI fixes failures │
│ 4. Tests run → 85% pass │
│ 5. AI fixes remaining issues │
│ 6. Tests run → 95% pass ✓ Target met! │
│ ↓ │
│ YOU: Review and approve the final result │
└─────────────────────────────────────────────────────────────────┘
Key Terms You'll See
| Term | What It Means | Example |
|---|---|---|
| Process | A workflow definition | "Build feature with TDD" |
| Run | One execution of a process | Running the TDD workflow for your login page |
| Task | A single step in the process | "Write tests", "Run linter", "Check coverage" |
| Quality Gate | A check that must pass | Tests must be 90% passing |
| Breakpoint | A pause for human approval | "Review this code before I deploy it" (handled in chat or via web UI) |
| Iteration | One try-check-fix cycle | Attempt #3 to pass the tests |
| Convergence | Improving until target met | Going from 60% → 85% → 95% |
Your First 5 Minutes
What you'll do:
- Install Babysitter (1 command)
- Run a simple workflow (1 command)
- See it iterate until tests pass
- Approve the result
What you'll learn:
- How the iteration loop works
- What a quality gate looks like
- How to approve at breakpoints
What you'll see:
/babysitter:call build a calculator with add, subtract, multiply, divide using TDD
Creating run: calculator-20260125-143012
Process: TDD Quality Convergence
Target: 90% quality
Iteration 1: Quality 65/100 - Tests: 6/10 passing
→ AI fixing test failures...
Iteration 2: Quality 82/100 - Tests: 9/10 passing
→ AI improving code coverage...
Iteration 3: Quality 95/100 - Target met! ✅
Claude: The implementation is complete. Quality score: 95/100.
Do you approve the final result?
[Approve] [Request Changes]
You: [Approve]
Done! Your calculator module is ready.
Note: Breakpoints (approval prompts) are handled directly in the chat when using Claude Code. No external service needed!
The main command: /babysitter:call <your request> handles everything automatically.
→ Start the Quick Start Tutorial
Documentation Sections
Tutorials
Step-by-step learning guides that take you from beginner to expert.
| Tutorial | Level | Time | Description |
|---|---|---|---|
| Getting Started | Beginner | 20 min | Installation, setup, and your first run |
| Build a REST API | Beginner | 45 min | Create a complete REST API with TDD |
| Custom Process | Intermediate | 60 min | Build your own process definition |
| Multi-Phase Workflows | Advanced | 90 min | Orchestrate complex multi-phase development |
Features
Deep dives into Babysitter's core capabilities.
| Feature | Description |
|---|---|
| Process Library | 2,239 JavaScript process files in the live generated snapshot, plus methodology, shared-process, skill, and agent layers discovered under library/ |
| Two-Loops Architecture | Hybrid agentic systems - symbolic orchestration + agentic harness, guardrails, and evidence-driven completion |
| Quality Convergence | Five quality gate types (tests, code quality, static analysis, security, performance) with 90-score patterns |
| Best Practices | Four guardrail layers, multi-gate validation, workflow design, and team collaboration patterns |
| Breakpoints | Human-in-the-loop approval system for critical decisions |
| Process Definitions | Customizable workflow templates and task orchestration |
| Journal System | Event-sourced audit trail and state reconstruction |
| Run Resumption | Continue interrupted workflows from any point |
| Parallel Execution | Concurrent task execution for faster results |
Highlight: The Process Library snapshot currently tracks 2,239 process files across 38 methodology families and the full specialization tree. Explore the library →
Essential Reading: Understanding the Two-Loops Architecture is key to designing reliable, bounded agentic workflows with proper guardrails and evidence-driven completion.
Reference
Technical specifications and lookup resources.
| Reference | Description |
|---|---|
| Slash Commands | Core modes (call, yolo, forever, plan) and utility commands for Claude Code |
| CLI Reference | Complete command-line interface documentation |
| Package & Plugin Map | Canonical public/internal docs map for active packages, apps, and harness plugins |
| Configuration | Environment variables and config file options |
| Error Catalog | All error codes with solutions |
| Glossary | Terminology and definitions |
| FAQ | Frequently asked questions |
| Troubleshooting | Common issues and resolutions |
Learning Paths
Choose a path based on your role and goals.
For Developers New to Babysitter
Start here if this is your first time using Babysitter:
- First: Read the "What is Babysitter?" section above - it takes 2 minutes and explains the core concepts
- Then: Complete the Getting Started tutorial (20 min) - you'll install and run your first workflow
- Practice: Build your first project with REST API Tutorial (45 min)
- Reference: Use the Glossary when you encounter unfamiliar terms (it has a quick-reference table at the top)
For Experienced Developers
- Quick setup via Installation
- Learn the Five Quality Gate Types for robust validation
- Study Best Practices for workflow design
- Reference the CLI for automation
For Technical Leads and Architects
- Start here: Understand the Two-Loops Architecture philosophy
- Study Quality Convergence for the 90-score convergence pattern
- Review the Four Guardrail Layers for safety and control
- Learn Journal System for audit compliance
- Explore Custom Process for team workflows
For Quality Engineers
- Essential: Study the Five Quality Gate Types
- Review The 90-Score Convergence Pattern
- Understand Evidence-Driven Completion
- Apply Domain-Specific Targets from Best Practices
For DevOps and Automation Engineers
- Install using Quickstart
- Master the CLI Reference
- Configure via Configuration Reference
- Automate with Run Resumption
What's New
Version 5.0.0
- Unified the public npm surface around
@a5c-ai/babysitterfor the main CLI - Split optional runtime orchestration into
@a5c-ai/babysitter-agent - Refreshed user-facing docs to match the current package and command boundaries
Recent Updates
| Version | Date | Highlights |
|---|---|---|
| 5.0.0 | 2026-04-25 | CLI/runtime package split clarified across public docs |
For the complete changelog, see the GitHub Releases.
Search Tips
Finding what you need quickly:
- Commands: Search for the command name (e.g.,
run:create,effects:get) - Errors: Search for the error code or key words from the message
- Concepts: Use terms from the Glossary
- Tasks: Search for what you want to do (e.g., "resume", "breakpoint", "quality")
Getting Help
Documentation Resources
- FAQ - Common questions answered
- Troubleshooting - Problem resolution guides
- Error Catalog - Error codes and fixes
Community and Support
- GitHub Issues: Report bugs or request features
- Discussions: Community Q&A and discussions
Documentation Structure
This documentation follows the Diataxis framework:
| Category | Purpose | User Mode |
|---|---|---|
| Tutorials | Learning through guided projects | Study |
| Features | Understanding capabilities | Study |
| Reference | Technical lookup information | Work |
| How-to Guides | Task-focused problem solving | Work |
Contributing
Found an issue with the documentation? Contributions are welcome.
- Check existing issues first
- Submit corrections via pull request
- Follow the documentation style guide
Last updated: 2026-01-25