Add project documentation: AGENTS.md and README.md

AGENTS.md

@@ -0,0 +1,37 @@
+# AGENTS.md
+
+## Project Context
+
+**Goal**: Automate the e-filing process for legal documents.
+
+**Approach**: Research-driven development. We first study how filing works today — both the manual process and competitor solutions — before building an automated solution.
+
+## Directory Structure
+
+| Path | Purpose |
+|------|---------|
+| `videos/` | Reference videos: manual filing walkthroughs + competitor demos |
+| `docs/research/` | Research notes, video transcripts, skill-based analyses |
+| `app/` | Production codebase (Python, managed with uv) |
+
+## Key Guidelines for AI Agents
+
+### Phase 1 — Research
+- Analyze videos in `videos/` to understand the manual e-filing flow
+- Compare with competitor automated solutions
+- Document findings as structured notes in `docs/research/`
+- Skills may be used to extract insights, frame captures, or transcripts from the video content
+- Each research artifact should be self-contained and reference its source video
+
+### Phase 2 — Build
+- All implementation lives in `app/`
+- Use **Python** as the language
+- Use **uv** for dependency management (`pyproject.toml`, not `requirements.txt`)
+- Virtual environments are managed by uv (no manual `venv`)
+- Keep research docs separate from code — `docs/research/` is for knowledge, `app/` is for implementation
+
+### Coding Standards
+- Prefer clarity and readability over cleverness
+- Reference the research when designing features
+- Document assumptions and decisions in the code or as docstrings
+- Use structured output formats (JSON, markdown) where applicable

README.md

@@ -0,0 +1,35 @@
+# eFiling Automation
+
+Automating the process of e-filing legal documents.
+
+## Project Structure
+
+```
+├── AGENTS.md          # AI agent instructions & project context
+├── README.md          # This file
+├── videos/            # Research videos: manual workflows + competitor demos
+├── docs/              # Documentation
+│   └── research/      # Research notes & analysis (driven by video-based skills)
+└── app/               # Python codebase (managed with uv)
+```
+
+## Overview
+
+This project aims to automate the e-filing workflow. We take a methodical approach:
+
+1. **Research** — Watch and analyze videos showing both the manual filing process and competitor solutions. Skills are built to extract and organize insights from these videos. Research findings are documented in `docs/research/`.
+2. **Build** — Implement the automation as a Python application in `app/`, using [uv](https://github.com/astral-sh/uv) for dependency and virtual environment management.
+
+## Tech Stack
+
+- **Language**: Python
+- **Dependency Manager**: uv (`pyproject.toml` + `uv.lock`)
+- **Video Analysis**: Custom skills for research pipeline
+
+## Quick Start (after research phase)
+
+```bash
+cd app
+uv sync          # Install dependencies
+uv run python -m app   # Run the application
+```