Atomizer/docs/00_INDEX.md

Atomizer Documentation Index

Last Updated: February 9, 2026
Project Version: 0.5.0 (AtomizerSpec v2.0 + Atomizer-HQ Multi-Agent Team)

---

Quick Start

For AI Agents (Atomizer-HQ Team)

Start here if you're an AI agent working on client projects:

1. HQ Overview — What Atomizer-HQ is and how agents work together
2. Project Structure — Standard project organization
3. Agent Workflows — Who does what in the project lifecycle
4. Knowledge Base Conventions — How to accumulate and share knowledge

For Engineers (Core Optimization)

Start here if you're using Atomizer for FEA optimization:

1. README.md - Project overview and philosophy
2. Getting Started - Installation, first study, dashboard
3. Protocol System - How Atomizer is organized
4. Example Studies - Working examples

---

Atomizer-HQ Agent Documentation

The multi-agent optimization team that runs client FEA projects.

Essential HQ Docs

Document	Purpose	Target Agents
HQ Overview	What Atomizer-HQ is, how to use these docs	All agents
Project Structure	Standard KB-integrated project layout	Manager, Technical Lead
KB Conventions	Knowledge Base accumulation principles	All agents
Agent Workflows	Project lifecycle and agent handoffs	All agents
Study Conventions	Technical study execution standards	Technical Lead, Optimizer

Agent Roles Quick Reference

Agent	Role	Primary Phase	Key Responsibilities
📋 Secretary	CEO interface	Intake	Client requirements, project initiation
🏗️ Manager	Coordination	Breakdown	Project structure, team coordination
🔧 Technical Lead	FEA expert	Introspection	Model setup, optimization planning
⚡ Optimizer	Study execution	Study	FEA optimization execution
📊 Post-Processor	Results analysis	Results	Performance analysis, insights
📝 Reporter	Documentation	Deliverables	Client reports, final packages

Living Examples

• Reference Project: projects/hydrotech-beam/ — Complete project structure
• Project Structure: Demonstrates KB-integrated organization and study flow
• Knowledge Accumulation: Shows generation-tracked knowledge evolution

---

Core Documentation

Essential reference for understanding Atomizer's optimization framework.

Foundation Documents

Document	Purpose
GETTING_STARTED.md	Setup, first study, dashboard basics
ARCHITECTURE.md	System architecture, hooks, data flow
QUICK_REF.md	Active reference guide

Protocol System

The Protocol Operating System (POS) provides structured workflows for optimization:

protocols/
├── README.md              # Protocol system overview
├── operations/            # How-to guides (OP_01-08)
│   ├── OP_01_CREATE_STUDY.md
│   ├── OP_02_RUN_OPTIMIZATION.md
│   ├── OP_03_MONITOR_PROGRESS.md
│   ├── OP_04_ANALYZE_RESULTS.md
│   ├── OP_05_EXPORT_TRAINING_DATA.md
│   ├── OP_06_TROUBLESHOOT.md
│   ├── OP_07_DISK_OPTIMIZATION.md
│   ├── OP_08_GENERATE_REPORT.md
│   └── OP_09_AGENT_COMMUNICATION.md
├── system/               # Technical specifications (SYS_10-18)
│   ├── SYS_10_IMSO.md           # Intelligent optimization
│   ├── SYS_11_MULTI_OBJECTIVE.md
│   ├── SYS_12_EXTRACTOR_LIBRARY.md
│   ├── SYS_13_DASHBOARD_TRACKING.md
│   ├── SYS_14_NEURAL_ACCELERATION.md
│   ├── SYS_15_METHOD_SELECTOR.md
│   ├── SYS_16_SELF_AWARE_TURBO.md
│   ├── SYS_17_STUDY_INSIGHTS.md
│   └── SYS_18_CONTEXT_ENGINEERING.md
└── extensions/           # Extensibility (EXT_01-04)
    ├── EXT_01_CREATE_EXTRACTOR.md
    ├── EXT_02_CREATE_HOOK.md
    ├── EXT_03_CREATE_PROTOCOL.md
    └── EXT_04_CREATE_SKILL.md

---

User Guides

Practical guides for using Atomizer features (engineers + Claude Code era).

Current User Guides

Guide	Purpose	Status
CANVAS.md	Visual study builder (AtomizerSpec v2.0)	Active
DASHBOARD.md	Dashboard overview and features	Active
NEURAL_FEATURES_COMPLETE.md	Neural acceleration guide	Active
NEURAL_WORKFLOW_TUTORIAL.md	Data → Training → Optimization	Active
hybrid_mode.md	Hybrid FEA/NN optimization	Active
TRAINING_DATA_EXPORT_GUIDE.md	Exporting data for neural training	Active

---

API Reference

Technical integration documentation for developers and advanced users.

Document	Purpose
system_configuration.md	Configuration format reference
nx_integration.md	NX Open API integration
GNN_ARCHITECTURE.md	Graph Neural Network details
NXOPEN_RESOURCES.md	NX Open documentation resources

---

Domain Knowledge

Physics and engineering domain documentation.

Physics Documentation

Document	Purpose
ZERNIKE_FUNDAMENTALS.md	Zernike polynomial basics
ZERNIKE_OPD_METHOD.md	OPD method for mirror optimization

---

Workflows and Operations

Operational workflows for common tasks.

Standard Workflows

Document	Purpose
CREATE.md	Study creation workflow
RUN.md	Optimization execution workflow
ANALYZE.md	Results analysis workflow
DELIVER.md	Deliverable creation workflow
VALIDATE.md	Validation and verification workflow
REPORT.md	Report generation workflow

---

Development and Architecture

Technical development documentation.

Development Guides

Document	Purpose
DEVELOPMENT_GUIDANCE.md	Development guidelines
DEVELOPMENT_ROADMAP.md	Future plans
Philosophy.md	Design philosophy

Architecture Documentation

Document	Purpose
architecture_overview.md	System architecture diagrams
protocol_workflows.md	Protocol execution flows

---

Archive

Historical and review documents preserved for context and CEO review.

Archive Structure

• archive/review/ — Documents flagged for CEO review
  • RALPH_LOOP implementation plans
  • Dashboard implementation iterations
  • Superseded development plans
  • Session summaries and old development notes
• archive/historical/ — Historical but valuable documents
  • Original protocol v1 monolithic document
  • Foundational design documents
  • Completed restructuring plans

Key Historical Documents

• PROTOCOL_V1_MONOLITHIC.md — Original monolithic protocol (Nov 2025)
• Various implementation plans and session summaries in review directories

---

Documentation by Task

For Agents: Project Execution

1. Agent Workflows — Project lifecycle and handoffs
2. Project Structure — How to organize projects
3. Study Conventions — Technical execution standards
4. KB Conventions — Knowledge accumulation

For Engineers: Creating Studies

1. GETTING_STARTED.md — First study tutorial
2. OP_01_CREATE_STUDY.md — Detailed creation protocol
3. guides/CANVAS.md — Visual study builder

For Engineers: Running Optimizations

1. OP_02_RUN_OPTIMIZATION.md — Run protocol
2. SYS_10_IMSO.md — Intelligent optimization
3. SYS_15_METHOD_SELECTOR.md — Method selection

For Engineers: Neural Acceleration

1. guides/NEURAL_FEATURES_COMPLETE.md — Overview
2. SYS_14_NEURAL_ACCELERATION.md — Technical spec
3. guides/NEURAL_WORKFLOW_TUTORIAL.md — Step-by-step

For Engineers: Analyzing Results

1. OP_04_ANALYZE_RESULTS.md — Analysis protocol
2. SYS_17_STUDY_INSIGHTS.md — Physics visualizations

For Everyone: Troubleshooting

1. OP_06_TROUBLESHOOT.md — Troubleshooting guide
2. GETTING_STARTED.md#troubleshooting — Common issues

---

Quick Reference

Protocol Summary

Protocol	Name	Purpose
OP_01	Create Study	Study creation workflow
OP_02	Run Optimization	Execution workflow
OP_03	Monitor Progress	Real-time monitoring
OP_04	Analyze Results	Results analysis
OP_06	Troubleshoot	Debugging issues
OP_09	Agent Communication	HQ communication standards
SYS_10	IMSO	Intelligent optimization
SYS_12	Extractors	Physics extraction library
SYS_14	Neural	Neural network acceleration

Essential Commands

# Activate environment
conda activate atomizer

# Run optimization (engineers)
python run_optimization.py --start --trials 50

# Resume interrupted run  
python run_optimization.py --start --resume

# Start dashboard
python launch_dashboard.py

# Neural turbo mode
python run_nn_optimization.py --turbo --nn-trials 5000

# KB status check (agents)
cad_kb.py status projects/[project]/kb

Key Extractors

ID	Physics	Function
E1	Displacement	extract_displacement()
E2	Frequency	extract_frequency()
E3	Stress	extract_solid_stress()
E4	Mass (BDF)	extract_mass_from_bdf()
E5	Mass (CAD)	extract_mass_from_expression()
E22	Zernike OPD	extract_zernike_opd()

Full catalog: SYS_12_EXTRACTOR_LIBRARY.md

---

LLM Resources

For Claude/AI integration:

Resource	Purpose
../CLAUDE.md	System instructions
../.claude/ATOMIZER_CONTEXT.md	Session context
../.claude/skills/	Skill modules

---

Last Updated: February 9, 2026
Maintained By: Atomizer-HQ Team (Manager, Technical Lead, Secretary) + Antoine