SitePilot

AI copilot for construction project managers.

Turn project chaos into clear action.

SitePilot reads RFIs, submittals, emails, and project logs to show construction teams what needs attention today.

---

What it does

Upload any construction project document (PDF, CSV, Excel, or TXT) and SitePilot will:

1. Extract all text and data from the file
2. Send it to Claude AI for analysis
3. Return a structured dashboard showing:
   • Urgent items — what needs action today
   • Overdue items — what's already past due
   • Waiting on someone — who's blocking progress
   • Project risks — what could derail the project
   • Weekly summary — executive overview for PMs
   • Suggested follow-up messages — ready to send

---

Tech Stack

Layer	Technology
Frontend	Next.js 14 (App Router, TypeScript, Tailwind CSS)
Backend	FastAPI (Python 3.11)
Database	PostgreSQL 16
AI	Anthropic Claude API
Infra	Docker + Docker Compose

---

Quick Start (Docker)

Prerequisites

• Docker Desktop installed and running
• An Anthropic API key

1. Clone and configure

git clone <this-repo>
cd sitepilot
cp .env.example .env

Edit .env and set your API key:

ANTHROPIC_API_KEY=sk-ant-your-key-here

2. Start everything

docker-compose up --build

This starts:

• PostgreSQL on port 5432
• FastAPI backend on http://localhost:8000
• Next.js frontend on http://localhost:3000

3. Open the app

Visit http://localhost:3000

Upload a file from the sample-data/ folder to try it out.

---

Local Development (without Docker)

Backend

cd backend

# Create virtual environment
python -m venv venv
source venv/bin/activate   # Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Set environment variables
export ANTHROPIC_API_KEY=sk-ant-your-key-here
export DATABASE_URL=postgresql://sitepilot:sitepilot_password@localhost:5432/sitepilot

# Start PostgreSQL (Docker is the easiest way)
docker run -d --name sitepilot-db \
  -e POSTGRES_DB=sitepilot \
  -e POSTGRES_USER=sitepilot \
  -e POSTGRES_PASSWORD=sitepilot_password \
  -p 5432:5432 \
  postgres:16-alpine

# Start the server
uvicorn main:app --reload --port 8000

API docs available at http://localhost:8000/docs

Frontend

cd frontend

# Install dependencies
npm install

# Create local env file
echo "BACKEND_URL=http://localhost:8000" > .env.local

# Start dev server
npm run dev

Frontend available at http://localhost:3000

---

Sample Data

The sample-data/ folder contains realistic construction project files for testing:

File	Type	Contents
sample_rfi_log.txt	TXT	6-entry RFI log with statuses, priorities, and due dates
sample_submittal_log.csv	CSV	12-item submittal register with review statuses
sample_project_notes.txt	TXT	Full weekly meeting minutes with action items, change orders, and risk issues

Upload all three to see the dashboard populate with real-looking construction data.

---

Project Structure

sitepilot/
├── backend/
│   ├── main.py                  # FastAPI entry point
│   ├── database.py              # SQLAlchemy engine + session
│   ├── models.py                # DB models (UploadedFile, Analysis)
│   ├── schemas.py               # Pydantic response schemas
│   ├── routers/
│   │   ├── files.py             # File upload, list, delete endpoints
│   │   └── analysis.py         # Dashboard + analysis detail endpoints
│   ├── services/
│   │   ├── extractor.py         # PDF/CSV/Excel/TXT text extraction
│   │   └── claude_service.py    # Claude API integration + prompt
│   ├── requirements.txt
│   └── Dockerfile
├── frontend/
│   ├── app/
│   │   ├── page.tsx             # Landing page
│   │   ├── upload/page.tsx      # File upload page
│   │   ├── dashboard/page.tsx   # Project dashboard
│   │   └── analysis/[id]/page.tsx  # Analysis detail
│   ├── components/
│   │   └── Navbar.tsx
│   ├── lib/
│   │   └── api.ts               # API client + TypeScript types
│   ├── next.config.js           # Rewrites proxy to backend
│   └── Dockerfile
├── sample-data/                 # Test files for trying the app
├── docker-compose.yml
├── .env.example
└── README.md

---

API Endpoints

Method	Path	Description
POST	/api/files/upload	Upload and analyze a file
GET	/api/files/	List all uploaded files
GET	/api/files/{id}	Get file metadata
DELETE	/api/files/{id}	Delete a file
GET	/api/analysis/dashboard	Aggregated dashboard data
GET	/api/analysis/file/{file_id}	Analysis for a specific file
GET	/api/analysis/{id}	Get analysis by analysis ID
GET	/api/health	Health check

---

Configuration

Variable	Default	Description
ANTHROPIC_API_KEY	—	Required. Your Anthropic API key
CLAUDE_MODEL	claude-sonnet-4-6	Claude model to use
DATABASE_URL	postgres://...	PostgreSQL connection string
UPLOAD_DIR	uploads	Directory to store uploaded files
MAX_FILE_SIZE_MB	50	Maximum upload size in MB
ALLOWED_ORIGINS	http://localhost:3000	CORS allowed origins

---

Supported File Types

• PDF — extracted with pdfplumber (fallback: PyPDF2)
• CSV — parsed with pandas, formatted as readable table
• Excel (.xlsx / .xls) — all sheets extracted with pandas
• TXT — read directly as UTF-8

---

Notes

• No authentication — all data is shared in the same instance (V1 design)
• File processing is asynchronous — the UI polls for status updates
• Large files (>50 MB) are rejected; >60,000 characters are truncated before sending to Claude
• All analyses are stored in PostgreSQL and persist across restarts