Back to Workshops
Workshop Basic or above

End-to-End Agent Deployment

April 21, 2026 Alexey Grigorev

Starting from a Jupyter notebook that runs an agentic-RAG bot, we turn it into a FastAPI service with a vanilla-JS frontend, containerize it, deploy it to Railway, and add a GitHub Actions CI/CD pipeline. Most of the code-writing work is delegated to a coding agent (Claude Code), and the exact prompts I used are quoted verbatim.

Links

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 is a minimal teaching-assistant chatbot for the DataTalks.Club Data Engineering Zoomcamp FAQ. One tool is exposed to the model: search(query). Everything else is the web layer, the container, and the deploy pipeline.

Appendix

A file inventory of the final repo is in Appendix: file inventory.

Basic or above required

Upgrade to Basic to access this workshop

  • Full workshop overview
  • Complete page list
  • Step-by-step tutorial
  • Cancel anytime
Upgrade

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

More from AI Shipping Labs

Workshop Basic or above

Deploying an Agent to AWS Lambda

We start from the FastAPI service we deployed to Railway in the previous workshop, strip out FastAPI, and swap it for a custom AWS Lambda runtime. The runtime handles both the sta…

May 5, 2026

Article

CRISP-DM for AI Engineering: Why a 1996 Framework Still Describes Modern AI Development

See how CRISP-DM still guides AI engineers in 2026, translating each phase into practical workflows for LLM apps, RAG pipelines, and production AI systems.

March 11, 2026

Article

How Claude Code Accidentally Wiped Our AWS RDS Database (24-Hour Recovery)

An incident story: how I accidentally wiped our AWS RDS production database and deleted snapshots by letting Claude Code touch production infrastructure.

March 6, 2026