Skip to content

Introduction

The AI Doc Generator is a multi-agent documentation system that uses Claude Code to orchestrate the generation of professional LaTeX documents from source materials.

System Overview

Key Concepts

Multi-Agent Architecture

The system uses a hierarchical agent structure:

AgentModelRole
OrchestratorClaude OpusControls workflow, makes decisions, merges context
WorkersClaude SonnetExecute parallel tasks (reading, writing, reviewing)

Parallel Processing

Multiple agents work simultaneously:

  • Source documents read in parallel
  • Chapters written concurrently
  • Reviews run asynchronously

External Research Integration

The orchestrator generates prompts for external AI tools:

  • NotebookLM - Synthesize uploaded source documents
  • Perplexity - Gather current statistics and trends
  • Scopus AI - Find academic papers with BibTeX citations

Workflow Phases

  1. Source Collection - Gather PDFs and documents into sources/
  2. Parallel Analysis - Sonnet agents read sources simultaneously
  3. External Research - Run prompts on NotebookLM, Perplexity, Scopus
  4. Document Planning - Opus plans structure with chapter assignments
  5. Parallel Writing - Writer agents create chapters concurrently
  6. Review & Build - Review agents check quality, LaTeX compiles to PDF

Technology Stack

AI Tools

ToolPurpose
Claude CodePrimary orchestration
OpenCodeAlternative multi-provider CLI
NotebookLMSource document synthesis
PerplexityCurrent data research
Scopus AIAcademic paper search

Output Technology

ComponentTechnology
Document FormatLaTeX with BibLaTeX
Build Systempdflatex + biber
DiagramsTikZ
Code Highlightinglistings

Getting Started

Ready to start?

  1. Quick Start - Set up in 10 minutes
  2. Full Workflow - Detailed process guide
  3. Agent Prompts - Ready-to-use prompts

Multi-Agent Documentation Generation System