diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..0cde0ac
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,19 @@
+.git
+.github
+.venv
+__pycache__
+.pytest_cache
+.ruff_cache
+.mypy_cache
+.langgraph_api
+tests
+docs
+*.pyc
+*.pyo
+*.pyd
+*.log
+.env
+.env.*
+README.md
+TEMPLATE_README.md
+drawkit.xml
diff --git a/.github/workflows/publish-ghcr.yml b/.github/workflows/publish-ghcr.yml
new file mode 100644
index 0000000..9751d7a
--- /dev/null
+++ b/.github/workflows/publish-ghcr.yml
@@ -0,0 +1,55 @@
+name: Build and Publish Container
+
+on:
+  push:
+    branches: [main]
+    tags: ["v*"]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  packages: write
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+
+      - name: Set image name
+        id: image
+        run: echo "name=ghcr.io/${GITHUB_REPOSITORY,,}" >> "$GITHUB_OUTPUT"
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract image metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ steps.image.outputs.name }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha
+            type=raw,value=latest,enable={{is_default_branch}}
+
+      - name: Build and push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..4c306e6
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,19 @@
+FROM python:3.12-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    UV_LINK_MODE=copy
+
+WORKDIR /app
+
+RUN pip install --no-cache-dir uv
+
+COPY pyproject.toml uv.lock ./
+COPY casts ./casts
+COPY app ./app
+
+RUN uv sync --frozen --no-dev --all-packages
+
+EXPOSE 8000
+
+CMD ["uv", "run", "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
diff --git a/README.md b/README.md
index 3a9c6d1..41e6e27 100644
--- a/README.md
+++ b/README.md
@@ -1,23 +1,107 @@
-# Act: Interview Graph
+# 🙋‍♂️ InterviewGraph
 
-A LangGraph-based Act project scaffolded with Act Operator.
+InterviewGraph is a LangGraph-based service that generates structured interview questions from resume content.
 
-## Quick Start
+It accepts either resume text or a PDF file, extracts relevant signals, and returns 15 questions with difficulty ratings.
+
+The response includes both structured JSON and Markdown for interviewer-friendly review.
+
+> This project was developed through Act-Operator.
+>
+> [😺 Act-Operator Github](https://github.com/Proact0/act-operator)
+
+## What It Does
+
+- Accepts resume text or PDF input
+- Parses resume sections (summary, skills, experience, projects, education)
+- Extracts signals (skills, projects, keywords)
+- Generates 15 interview questions
+- Rates question difficulty (1-5)
+- Formats output as JSON and Markdown
+
+## Architecture (MVP)
+
+Pipeline:
+
+`extract_text -> parse_sections -> extract_signals -> generate_questions -> rate_difficulty -> format_output`
+
+## Quick Start (Local)
 
 1. Install dependencies:
-   ```bash
-   uv sync --all-packages
-   ```
 
-2. Run the development server:
-   ```bash
-   uv run langgraph dev
-   ```
+```bash
+uv sync --all-packages
+```
+
+1. Run API server:
+
+```bash
+uv run uvicorn app.main:app --reload
+```
+
+1. Open API docs:
+
+- `http://127.0.0.1:8000/docs`
+
+## API Usage
+
+- `POST /api/v1/interview-questions` for text input
+- `POST /api/v1/interview-questions/upload` for PDF upload (multipart/form-data)
+
+Example JSON payload:
+
+```json
+{
+  "resume_text": "Summary ... Skills ... Projects ..."
+}
+```
+
+## Container Usage
+
+Build image:
+
+```bash
+docker build -t interviewgraph:local .
+```
+
+Run container:
+
+```bash
+docker run --rm -p 8000:8000 interviewgraph:local
+```
+
+Open docs:
+
+- `http://127.0.0.1:8000/docs`
+
+## GHCR Publishing
+
+This repository includes `.github/workflows/publish-ghcr.yml`.
+
+- On push to `main`, the workflow builds and publishes to `ghcr.io/<owner>/<repo>`.
+- On push tag `v*`, it also publishes versioned tags.
+- You can manually trigger publishing with `workflow_dispatch`.
+
+Pull from GHCR:
+
+```bash
+docker pull ghcr.io/<owner>/<repo>:latest
+docker run --rm -p 8000:8000 ghcr.io/<owner>/<repo>:latest
+```
+
+## Current Scope (MVP)
+
+- Text-extractable PDF support
+- Resume-grounded question generation pipeline
+- Structured error payloads
+
+## Out of Scope (MVP)
 
-3. Access Studio UI:
-   - Studio UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
-   - API: http://127.0.0.1:2024
-   - API Docs: http://127.0.0.1:2024/docs
+- OCR for scanned PDFs
+- Vector DB / RAG
+- Multi-agent orchestration
+- Mock interview answer scoring
 
-For detailed documentation, see [TEMPLATE_README.md](TEMPLATE_README.md).
+## License
 
+Apache License 2.0 - see [LICENSE](https://www.apache.org/licenses/LICENSE-2.0) for details.