Empathometer - An AI Technical Documentation Analyzer

A multi-persona AI-powered documentation analyzer built with FastAPI and OpenAI.

This tool reads your technical documentation and provides feedback from multiple perspectives: Junior Developers, Senior Developers, Business Users, and an AI agent. It helps you identify gaps, confusing sections, and actionable suggestions, so your documentation is clearer and more effective.

Table of Contents

• What It Does
• Key Features
• Tech Stack
• Getting Started
  • Clone the Repository
  • Set Up the Environment
  • Install Dependencies
  • Add API Keys
  • Run the App
• How to Use
• Personas Explained
• Sample Persona Comments
• Workflow Diagram
• Folder Structure
• Contributing
• License

What It Does

AI Docs Analyzer reads your documentation and generates persona-driven comments:

• Junior Developer: Asks clarifying questions, identifies missing context, and points out areas that might confuse a beginner.
• Senior Developer: Focuses on brevity, accuracy, and technical correctness.
• Business User: Highlights the business relevance, metrics, and clarity for non-technical audiences.
• AI Agent: Suggests tasks, queries, or improvements that can be performed based on the content.

With this, you can quickly see where your docs are strong and where they need improvement.

Key Features

• Multi-persona feedback on documentation
• Real-time inline comments
• Actionable insights from AI
• Supports both short and long documentation
• Easy to run locally with minimal setup

Tech Stack

• Backend: Python, FastAPI
• Frontend: HTML, CSS, JavaScript
• AI: OpenAI API
• Other: Git for version control, .gitignore for secret management

Getting Started

Follow these steps to set up and run the project on your local machine.

Clone the Repository

git clone https://github.com/Kemi-Elizabeth/AI-DocReviewer.git
cd AI-DocReviewer

Set Up the Environment

Create a virtual environment (to keep dependencies isolated):

python3 -m venv venv
source venv/bin/activate   # Mac/Linux
venv\Scripts\activate      # Windows

Install Dependencies

pip install -r backend/requirements.txt

This installs FastAPI, OpenAI, and all other required libraries.

Add API Keys

Create a .env file in the backend/ folder with your OpenAI API key:

OPENAI_API_KEY=your_openai_api_key_here

Note: .env is included in .gitignore for security.

Run the App

Start the backend server:

cd backend
uvicorn main:app --reload

Open the frontend in your browser:

open ../frontend/index.html   # Mac
# or just double-click the HTML file on any OS

You’re now ready to interact with your AI Docs Analyzer.

How To Use

1. Paste or load your documentation into the editor on the frontend.
2. Click “Analyze” to generate comments.
3. Review feedback from all four personas
4. Each persona’s comments appear in separate sections.
5. Iterate on your documentation based on the feedback.

Personas Explained

Persona	Focus	Example Feedback
Junior Developer	Clarity & basics	“Wait… what does PHP-FPM stand for?”
Senior Developer	Brevity & correctness	“This section is too long; summarize in 3 lines.”
Business User	Metrics & impact	“How does this affect our conversion rate or KPIs?”
AI Agent	Actions & tasks	“Based on this content, I could answer these queries: [X, Y, Z] or suggest improvements in structure.”

Sample Persona Comments

Documentation excerpt: “To deploy the application, first ensure Docker is installed and then configure the environment variables before starting the containers.”

Junior Dev: “What does Docker mean here? Is it needed on all machines?” “Which environment variables exactly? Can you give examples?” “What does ‘starting the containers’ involve? I’m confused.”

Senior Dev: “Too verbose. Condense to: Install Docker, set environment vars, run containers.” “Check command syntax; consider adding default values.”

Business User: “Does this deployment process affect uptime or SLA?” “Are there costs associated with Docker for this setup?”

AI Agent: “Could provide step-by-step instructions for setup.” “Could generate a checklist for deployment. “Could validate environment variables automatically.”

Workflow Diagram

flowchart LR
    A[User uploads or pastes docs] --> B[Frontend Editor]
    B --> C[Backend FastAPI receives docs]
    C --> D[OpenAI API analyzes docs]
    D --> E[Generate persona comments]
    E --> F[Frontend displays comments]
    F --> G[User reviews and iterates]

Loading

The diagram shows how documentation flows from input to AI analysis, persona comment generation, and back to the user.

Folder Structure

AI-DocReviewer/
│
├─ backend/
│   ├─ main.py          # FastAPI backend
│   ├─ requirements.txt # Python dependencies
│   ├─ __pycache__/     # Python cache files
│   └─ .env             # API keys (ignored)
│
├─ frontend/
│   ├─ index.html       # User interface
│   ├─ styles.css       # Styling
│   └─ script.js        # JS logic
│
├─ .gitignore
└─ README.md

Contributing

1. Fork the repository
2. Create a feature branch:

git checkout -b feature/new-persona

3. Commit your changes:

git commit -m "Add new persona"

4. Push to branch:

git push origin feature/new-persona

5. Open a Pull Request

License

MIT License © Kemi Elizabeth Ojogbede