Back to Workshops
Workshop Basic or above

End-to-End Agent Deployment

April 21, 2026 Alexey Grigorev

We build a FAQ chatbot from notebook to production. You start with a Jupyter notebook that calls the OpenAI Responses API with a single search tool. Then you wrap it in FastAPI and add a vanilla-JS frontend with streaming (SSE). From there you containerize with Docker, deploy to Railway, and wire up a GitHub Actions CI/CD pipeline.

Each step is done alongside a coding agent. The prompts are included verbatim so you can reproduce the workflow with any agent you like.

Links

Useful resources for this workshop:

The app you will build

The final app looks like this:

flowchart LR UI["Frontend UI vanilla JS, SSE"] API["FastAPI app"] AGENT["Agent loop"] SEARCH["FAQ search tool minsearch"] OPENAI["OpenAI Responses API"] UI -->|POST /ask or /ask/stream| API API --> AGENT AGENT -->|tool call| SEARCH AGENT -->|model call| OPENAI API -->|JSON or SSE| UI

The final app answers questions from the DataTalks.Club Data Engineering Zoomcamp FAQ. The model gets one tool, search(query). Everything else is the web layer, the container, and the deploy pipeline.

Tutorial pages

  1. Overview and setup
  2. Part 1: The starting notebook
  3. Part 2: Notebook to FastAPI backend
  4. Part 3: Vanilla-JS frontend with Vite
  5. Part 4: Streaming with Server-Sent Events
  6. Part 5: Dockerize as one container
  7. Part 6: Deploy to Railway via CLI
  8. Part 7: GitHub Actions CI/CD
  9. Deferred items
  10. Q&A: side discussions
  11. Appendix: file inventory

Watch the recording

Recording available with Main or above.

Main or above View code on GitHub

Upgrade to Basic to access this workshop

The workshop overview and page list are visible now; membership unlocks the step-by-step tutorial.

Basic or above required

View Pricing