Skip to content

JahnelGroup/authorless-docs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Authorless Docs: Multi-Agent Document Builder

A demo showing how Claude Code subagents collaborate to build a comprehensive document from raw data — without a human writing a single sentence.

What This Is

This repo contains everything needed to demonstrate a multi-agent document authoring workflow using Claude Code's subagents. Five specialized agents coordinate via the Task tool to transform raw research data into a polished industry report:

 You (Human)
  │
  ▼
┌─────────────┐
│  Architect   │ ◄── You talk to this agent. It runs the show.
└──────┬──────┘
       │  Uses the Task tool to spawn subagents, collects results between phases
       │
       ├── Phase 1: Research
       │   ┌──────────────┐  ┌──────────────┐  ┌──────────────┐
       ├──►│ Researcher 1 │  │ Researcher 2 │  │ Researcher 3 │  (parallel subagents)
       │   └──────┬───────┘  └──────┬───────┘  └──────┬───────┘
       │          └──── results return to Architect ───┘
       │                            ▼
       ├── Phase 2: Design    ┌──────────────┐
       ├────────────────────►│   Designer    │
       │                      └──────┬───────┘
       │                      returns outline
       │                             ▼
       ├── Phase 3: Writing
       │   ┌────────────┐ ┌────────────┐ ┌────────────┐ ┌────────────┐
       ├──►│ Writer §1  │ │ Writer §2  │ │ Writer §3  │ │ Writer §N  │  (parallel subagents)
       │   └─────┬──────┘ └─────┬──────┘ └─────┬──────┘ └─────┬──────┘
       │         └──── results return to Architect ────────────┘
       │                         ▼
       ├── Phase 4: Editing   ┌──────────────┐
       ├────────────────────►│    Editor     │ ── consistency, dedup, polish
       │                      └──────┬───────┘
       │                      returns revised doc
       │                             ▼
       └── Phase 5: Delivery ──► output/report.md ──► You

The Demo Scenario

Document: "The State of AI in Healthcare 2026" — a comprehensive industry report

Raw data (all fabricated for this demo):

File Description
data/survey_results.csv Survey of 50 healthcare organizations on AI adoption
data/market_analysis.json Market sizing, growth rates, investment data, competitive landscape
data/case_studies.md 5 detailed case studies of AI deployments in healthcare
data/regulatory_filings.md FDA authorizations, state legislation, international regulatory comparison
data/expert_interviews.md Interview transcripts with 5 industry experts
data/clinical_trials.csv 15 AI-related clinical trials with status and interim results
data/technology_trends.md Technical landscape: LLMs, multimodal AI, federated learning, edge AI

The Agents

All agent definitions live in .claude/agents/:

architect.md — The Orchestrator

  • Entry point for the human user
  • Coordinates the full 5-phase workflow
  • Delegates to all other agents via Task tool subagent calls
  • Never writes document content itself

researcher.md — The Data Analyst

  • Reads and analyzes raw data files
  • Extracts statistics, trends, quotes, and examples
  • Produces structured research summaries to output/research/
  • Multiple instances run in parallel on different data sources

designer.md — The Information Architect

  • Takes research summaries and designs the document outline
  • Defines sections, assigns content to each, and prevents duplication
  • Specifies tone, audience, word counts, and transitions
  • Produces the blueprint that writers follow

section-writer.md — The Content Creator

  • Writes one section of the document at a time
  • Receives the full outline (for context) plus section-specific research
  • Multiple instances run in parallel on different sections
  • Stays strictly within content boundaries to avoid duplication

editor.md — The Quality Controller

  • Reviews the complete assembled document
  • Scans for duplication, inconsistency, and flow problems
  • Fixes issues directly and reports what changed
  • Makes the patchwork read like a single-author document

How to Run the Demo

Prerequisites

Running It

  1. Clone this repo
  2. Open it in Claude Code:
    claude
    
  3. Start the Architect agent:
    /agents architect
    
  4. Give it a prompt like:
    Build me a comprehensive report on "The State of AI in Healthcare" using the
    data in the data/ directory. The audience is healthcare executives. Tone should
    be professional but accessible.
    
  5. Watch the agents work through the 5 phases
  6. Find the finished report in output/report.md

What You'll See

The Architect will:

  1. Research phase — Launch 3-4 Researcher subagents in parallel, each analyzing different data files and writing summaries to output/research/
  2. Design phase — Launch a Designer subagent that reads all research and produces an outline at output/outline.md
  3. Writing phase — Launch one Section Writer subagent per section in parallel, each writing to output/sections/
  4. Editing phase — Assemble the draft at output/draft.md, then launch an Editor subagent for consistency review and polish
  5. Delivery phase — Copy the final document to output/report.md and present a summary

Why This Architecture?

Parallelism

Researchers work simultaneously on different data sources. Writers work simultaneously on different sections. The work that can be parallelized is parallelized — by launching multiple Task tool calls in a single response.

Separation of Concerns

Each agent has a clear, bounded responsibility:

  • Researchers don't write prose
  • The Designer doesn't analyze data
  • Writers don't decide what to cover
  • The Editor doesn't add new content

Duplication Prevention

The biggest risk in multi-agent document creation is content duplication. This is addressed at two levels:

  1. The Designer explicitly assigns every piece of content to exactly one section
  2. The Editor scans the assembled document and removes any duplication that slipped through

Iterative Quality

The Editor can flag sections needing revision. The Architect can re-launch Section Writer subagents for specific sections, then re-edit. Quality emerges from the loop, not from any single agent being perfect.

Repo Structure

authorless-docs/
├── .claude/
│   ├── settings.json           # Permissions config for subagents
│   └── agents/
│       ├── architect.md        # Orchestrator agent
│       ├── researcher.md       # Data analysis subagent
│       ├── designer.md         # Document structure subagent
│       ├── section-writer.md   # Content writing subagent
│       └── editor.md           # Review & consistency subagent
├── data/
│   ├── survey_results.csv      # Healthcare AI adoption survey
│   ├── market_analysis.json    # Market sizing & investment data
│   ├── case_studies.md         # Real-world deployment case studies
│   ├── regulatory_filings.md   # Regulatory landscape data
│   ├── expert_interviews.md    # Expert interview transcripts
│   ├── clinical_trials.csv     # AI clinical trial tracker
│   └── technology_trends.md    # Technical landscape overview
├── output/                     # All generated files go here
│   ├── research/               # Research summaries (Phase 1)
│   ├── sections/               # Individual sections (Phase 3)
│   ├── outline.md              # Document outline (Phase 2)
│   ├── draft.md                # Assembled draft (Phase 4)
│   ├── edited.md               # Editor's revised draft (Phase 4)
│   ├── editorial-report.md     # Editor's change log (Phase 4)
│   ├── report.md               # Final deliverable (Phase 5)
│   └── .gitkeep
└── README.md                   # You are here

How It Works

Claude Code's subagents let you spawn focused worker agents within your session using the Task tool. Each subagent:

  • Has its own context window — it runs independently with the prompt you give it
  • Returns results directly to the calling agent when finished
  • Can read and write files — subagents write their outputs to disk so other phases can use them
  • Runs with the agent persona defined in .claude/agents/ Markdown files

Agents are defined as Markdown files in .claude/agents/. Each agent:

  • Has a system prompt (the Markdown content) that defines its role, capabilities, and instructions
  • Can be invoked directly by the user with /agents <name>
  • Can be spawned as a subagent by another agent using the Task tool

Key Patterns Demonstrated

  1. Orchestrator pattern — The Architect coordinates all others, acting as the single point of control
  2. Fan-out/fan-in — Multiple Researcher or Writer subagents run in parallel, then their outputs are collected
  3. Pipeline pattern — Data flows through stages: Research → Design → Writing → Editing → Delivery
  4. Quality gate — The Editor acts as a gate before delivery, sending work back if quality is insufficient
  5. File-based handoff — Subagents share work products through files in output/, keeping context windows lean

Customizing the Demo

Change the Topic

Replace the files in data/ with data about any topic. The agents are designed to work with whatever data they're given. The Architect will adapt its approach based on what's available.

Change the Output Format

Modify section-writer.md and editor.md to output a different format (e.g., HTML, LaTeX, presentation outline).

Add More Agents

Some ideas:

  • Fact-checker agent — Verifies claims against source data
  • Visualization agent — Suggests or generates charts and diagrams
  • Summarizer agent — Creates an executive brief from the full report
  • Translator agent — Produces the report in multiple languages

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors