Action-oriented builders. Now open.
A community for action-oriented builders interested in AI engineering and AI tools. Get the structure, focus, and accountability you need to ship practical AI products.
Build
Practical AI projects
Ship
With structure & accountability
Grow
Through peer collaboration
Philosophy
Designed for motivated learners who prefer learning by doing. Get clear frameworks, direction, and community support to make consistent progress on your projects.
No passive consumption. Every activity is designed around building, shipping, and getting feedback on real work.
Focus on what actually works in production. Move from prototypes to reliable systems with battle-tested patterns.
Work alongside other practitioners. Hackathons, projects, and group problem-solving instead of isolated learning.
Develop better instincts through peer feedback, expert guidance, and exposure to real-world decision-making patterns.
Membership
Each tier is designed for a different type of builder. More investment means more structure, accountability, and support to help you ship your AI projects consistently.
Content only
Educational content without community access.
Access curated educational content, tutorials, and research. Perfect for self-directed builders who learn at their own pace.
Best for independent builders who prefer self-paced learning. Upgrade to Main for structure, accountability, and community support.
Choose BasicLive learning + community
Build with the community and get the accountability and direction you need to make progress.
Everything in Basic, plus the structure, accountability, and peer support to ship your AI projects consistently.
Best for builders who need structure and accountability to turn project ideas into reality alongside motivated peers.
Get StartedCourses + personalized feedback
Accelerate your growth with structured courses and personalized feedback.
Everything in Main, plus structured learning paths through mini-courses and personalized career guidance to accelerate your growth.
Best for builders seeking structured learning paths to complement hands-on projects, plus personalized career guidance.
Choose PremiumWhat learners say
AI Shipping Labs community is new, but here's what practitioners say about the courses that inspired it.
"This course helped me understand how to implement a RAG system in Python. From basic system-design of a RAG, to evaluating responses and implementing guardrails, the course gave me a great overview of the necessary skills for implementing and managing my own agent."
Rolando
AI Data Scientist · AeroMexico
"I highly recommend the AI Engineering Buildcamp. I learned a tremendous amount. The material is abundant, very well organized, and progresses in a logical and progressive manner. This made complex topics much easier to follow and digest. The instructor Alexey Grigorev is clearly very knowledgeable in the field, and also super helpful and responsive to questions."
John
AI Tutor · Meta
"Excellent, comprehensive, and modern course that elevated my knowledge of generative AI from RAG applications to well-evaluated, fully functioning agentic systems. Alexey Grigorev incorporated essential software engineering practices, especially unit testing and evaluation, teaching us how to systematically improve our agents."
Yan
Senior Data Scientist · Virtualitics
"I really enjoyed this course! It made the process of building AI agents both accessible and exciting. The progression from RAG to agents, multi-agent systems, monitoring, and guardrails was clear and practical. I'm walking away inspired and full of new ideas to build on."
Scott
Principal Data Scientist, Applied AI · interos.ai
"The course provides an excellent introduction to the core tooling needed to develop an agentic tool. Worth the effort especially given the comprehensiveness of the options and solutions available in the course."
Naveen
Software Engineer
"Excellent course, it gets you practicing the concepts you need to know to work on agentic AI. The instructor is accessible, clear, and flexible."
Nelson
Practitioner
Event Recordings
Workshop recordings with embedded content, timestamps, descriptions, and materials. Learn from hands-on sessions on building AI agents and practical systems.
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 - [Workshop recording](https://www.youtube.com/watch?v=h84rcRezNM4) - [Starting notebook (gist)](https://gist.github.com/alexeygrigorev/8c92913c23ec23e77ce8b355053ac531) - [Final code](https://github.com/AI-Shipping-Labs/workshops/tree/main/2026/2026-04-21-end-to-end-agent-deployment) ## The app you will build The final app looks like this: ```mermaid flowchart LR UI["Frontend UI<br/>vanilla JS, SSE"] API["FastAPI app"] AGENT["Agent loop"] SEARCH["FAQ search tool<br/>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](https://datatalks.club/faq). One tool is exposed to the model: `search(query)`. Everything else is the web layer, the container, and the deploy pipeline. ## Walkthrough Follow the numbered files in order. Each file is one self-contained step. 1. [Overview and setup](/workshops/end-to-end-agent-deployment/tutorial/overview) - what you will build, prerequisites, and project setup with `uv` and `.env`. 2. [Part 1: The starting notebook](/workshops/end-to-end-agent-deployment/tutorial/starting-notebook) - the agentic RAG notebook. FAQ loading, `minsearch` index, `AsyncOpenAI`, one-by-hand tool-call round, then the full `run_agent` loop with a renderer. 3. [Part 2: Notebook to FastAPI backend](/workshops/end-to-end-agent-deployment/tutorial/fastapi-backend) - split the notebook into `app.py`, `agent.py`, `search.py`, `renderer.py`, `schemas.py`. Two endpoints (`/ask`, `/ask/stream`) plus `/health`. 4. [Part 3: Vanilla-JS frontend with Vite](/workshops/end-to-end-agent-deployment/tutorial/vanilla-js-frontend) - scaffold a tiny `frontend/` with Vite and plain JavaScript, proxied to the backend in dev. 5. [Part 4: Streaming with Server-Sent Events](/workshops/end-to-end-agent-deployment/tutorial/streaming-sse) - replace the wait-for-the-whole-answer UI with one that streams tokens live and shows tool calls as collapsible blocks. 6. [Part 5: Dockerize as one container](/workshops/end-to-end-agent-deployment/tutorial/dockerize) - one-container, two-stage Dockerfile that builds the frontend with Node and serves it from the FastAPI Python image. Includes the `.env` quoting gotcha. 7. [Part 6: Deploy to Railway via CLI](/workshops/end-to-end-agent-deployment/tutorial/deploy-railway) - deploy the Docker image to Railway using the Railway CLI. 8. [Part 7: GitHub Actions CI/CD](/workshops/end-to-end-agent-deployment/tutorial/cicd-github-actions) - a GitHub Actions workflow that calls `railway up` on every push, plus a note on never pasting tokens into the agent chat. 9. [Deferred items](/workshops/end-to-end-agent-deployment/tutorial/deferred-items) - what was intentionally skipped and earmarked for a follow-up: vector DB, multi-turn chat, structured output, tests, dev/prod separation. 10. [Q&A: side discussions](/workshops/end-to-end-agent-deployment/tutorial/qa) - side discussions from the live session: Hetzner vs cloud, tmux, SSH port forwarding, coding-agent pricing, framework choice, free models, FastAPI folder conventions. ## Appendix A file inventory of the final repo is in [Appendix: file inventory](/workshops/end-to-end-agent-deployment/tutorial/appendix).
Join us for the official launch of AI Shipping Labs! Valeriia and I are launching a new community for AI builders. In this session we'll walk through: - What AI Shipping Labs is and who it's for - The community structure: building sessions, group learning, accountability circles - How the platform was built (almost entirely by AI agents working autonomously) - The tiers and what you get at each level - Live Q&A Whether you're a software engineer moving into AI, an ML engineer who wants to go deeper, or anyone who wants to build and ship AI products — this is for you. Early members get a personal onboarding call to understand your goals and how the community can help.
We start from the coding agent from the prerequisite workshop and turn it into a general-purpose coding agent with two reusable behavior layers: skills and slash commands. Skills are loaded by the agent when the user's request matches a skill description. Commands are invoked by the user with a leading slash and rendered into prompts before the agent acts. ## Links External resources for this workshop: - [Workshop recording](https://www.youtube.com/watch?v=OhgDEZfHsvg) - [Workshop code](https://github.com/alexeygrigorev/workshops/tree/main/agent-skills) - [Starting notebook](https://github.com/alexeygrigorev/workshops/blob/main/agent-skills/notebook.ipynb) - [GitHub fetch skill](https://github.com/alexeygrigorev/workshops/blob/main/agent-skills/gh-fetch-skill.md) - [Prototype implementation](https://github.com/alexeygrigorev/workshops/tree/main/agent-skills/prototype) - [Prerequisite coding-agent workshop](https://github.com/alexeygrigorev/workshops/tree/main/coding-agent) - [ToyAIKit](https://github.com/alexeygrigorev/toyaikit) - [OpenCode](https://github.com/anomalyco/opencode) - [OpenCode skills documentation](https://opencode.ai/docs/skills/) - [AgentSkills spec](https://agentskills.io) ## The agent you will build The final workshop system looks like this: ```mermaid flowchart LR USER["User"] RUNNER["ToyAIKit runner<br/>OpenAI Responses"] LLM["OpenAI model"] CODETOOLS["Coding tools<br/>read, write, tree, bash, search"] SKILLTOOL["skill(name) tool"] LOADER["SkillLoader"] SKILLS["skills/*/SKILL.md<br/>scripts and templates"] COMMANDS["commands/*.md"] COMMANDTOOL["execute_command(name, args)"] USER -->|plain request| RUNNER USER -->|/command| RUNNER RUNNER --> LLM RUNNER --> CODETOOLS RUNNER --> SKILLTOOL SKILLTOOL --> LOADER LOADER --> SKILLS RUNNER --> COMMANDTOOL COMMANDTOOL --> COMMANDS ``` The project stays small enough to understand in a notebook, but it mirrors the pieces used by real coding agents. The coding tools let the model read, write, search, and run commands. The skill loader turns `SKILL.md` files with YAML frontmatter into tool-loadable instructions. The command loader turns markdown files like `review.md` or `test.md` into reusable prompt templates. ## Walkthrough Follow the numbered files in order. Each file is one self-contained step. 1. [Overview and setup](/workshops/coding-agent-skills-commands/tutorial/overview) - prerequisites, environment setup, workshop code, and the project folder. 2. [Part 1: Demoing skills and commands](/workshops/coding-agent-skills-commands/tutorial/github-fetch-demo) - demo a Claude Code skill that fetches `/kid` and `/parent` commands from GitHub. 3. [Part 2: Recapping the coding agent](/workshops/coding-agent-skills-commands/tutorial/agent-tools-recap) - recap the agent loop and the coding-agent tools from the prerequisite workshop. 4. [Part 3: Building the base runner](/workshops/coding-agent-skills-commands/tutorial/general-purpose-runner) - build a general-purpose coding-agent runner in Jupyter with ToyAIKit. 5. [Part 4: Defining the skill format](/workshops/coding-agent-skills-commands/tutorial/skill-markdown-and-examples) - define the `SKILL.md` format and look at the example skills. 6. [Part 5: Loading `SKILL.md`](/workshops/coding-agent-skills-commands/tutorial/parse-and-load-skills) - parse skill markdown, read frontmatter, list skills, and resolve extra files. 7. [Part 6: The skill tool and prompt injection](/workshops/coding-agent-skills-commands/tutorial/expose-skills-to-agent) - expose skills as a tool and inject the available skill list into the prompt. 8. [Part 7: Implementing commands](/workshops/coding-agent-skills-commands/tutorial/slash-commands) - load slash-command markdown files and run them as prompt templates. 9. [Part 8: The fuller prototype](/workshops/coding-agent-skills-commands/tutorial/prototype-and-tests) - connect the notebook version to the fuller `prototype/` implementation and its tests. 10. [Q&A: skills and commands](/workshops/coding-agent-skills-commands/tutorial/qa) - side questions about skill design, execution, model support, and command discovery. 11. [Deferred items](/workshops/coding-agent-skills-commands/tutorial/deferred-items) - items intentionally left as follow-ups or reference-only behavior. ## Appendix A file list for the workshop materials is in [Appendix: workshop files](/workshops/coding-agent-skills-commands/tutorial/appendix).
From the blog
Long-form notes, walkthroughs, and experiments. Stay close to how we build and reason.
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.
An incident story: how I accidentally wiped our AWS RDS production database and deleted snapshots by letting Claude Code touch production infrastructure.
Learn what an AI engineer is in 2026: responsibilities, skills, tools, and real-world use cases based on analysis of 1,000+ AI engineer job descriptions.
Project Ideas
Project ideas and real projects from people who've taken courses. End-to-end AI applications and agentic workflows you can learn from and build on.
Build a research assistant that uses multiple specialized agents — a searcher, a summarizer, and a fact-checker — coordinated by an orchestrator agent. Learn agent communication patterns, tool use, and how to build reliable multi-step workflows.
A small, self-contained project idea: take a photo of an everyday object and turn it into a short story with AI. Expand gradually with illustration, audio, a small website, and a podcast feed. Great for experimenting with multimodal pipelines (vision, text, speech) and sharing with kids, family, or friends.
Carlos Pumar-Frohberg's agent analyzes client satisfaction using Stack Exchange data, focusing on UI discussions to find frustration patterns. An orchestrator agent routes questions to a MongoDB agent for 'what'/'how' queries or a Cipher agent that translates natural language into Neo4j graph queries, often calling both for safety.
Curated Links
Curated GitHub repos, model hubs, and learning resources. Dev tools, local LLMs, and courses to level up.
Curated list of ML resources. Frameworks, papers, and tools.
Large language model course. From basics to RAG, agents, and fine-tuning.
Open-weight reasoning
AI copilot for data science. One prompt runs the full
Open standard for AI coding
Course from dlthub on building robust ELT pipelines. Includes a holiday lesson (Dec 22) on integrating LLMs into your workflow, with 50 swag packs to compete for.
FAQ
Action-oriented builders interested in AI engineering and AI tools who want to turn ideas into real projects. Whether you're learning Python or working as an ML engineer, if you have project ideas but need structure, focus, and accountability, this community is for you. We attract motivated learners who prefer learning by doing and builders who contribute back to the ecosystem.
We focus on helping you ship practical AI products, not just consume content. You get clear frameworks, direction, and gentle external pressure to make consistent progress on your projects. The community concentrates highly engaged builders in a focused environment centered on productivity, structured execution, and hands-on project work.
Yes. The community is designed to help you make consistent progress on side projects even with limited time. You get the structure and accountability to stay focused and ship incrementally through projects, hackathons, and collaborative activities.
The Basic tier is designed exactly for this. You get access to exclusive content, tutorials, research, and curated materials without any expectation of community participation. Perfect for self-directed builders who learn at their own pace.
Main tier gives you the structure, accountability, and peer support to ship your AI projects consistently. Includes everything in Basic, plus closed community access, collaborative problem-solving, interactive group coding sessions, guided projects, hackathons, career discussions, and the ability to propose and vote on topics.
Premium tier accelerates your growth with structured learning paths through mini-courses and personalized career guidance. Includes everything in Main, plus access to all mini-courses on specialized topics, the ability to vote on course topics, and professional profile teardowns (resume, LinkedIn, GitHub).
Pick the tier that fits your needs, click the button to check out securely via Stripe, and you'll receive access details by email within 24 hours. You can start with any tier and upgrade or downgrade at any time.
All payments are processed securely through Stripe. You can choose monthly or annual billing (annual saves ~17%). Stripe handles tax calculation automatically based on your location. You'll receive invoices and receipts by email after each payment.
Yes, you're in full control. You can cancel, upgrade, downgrade, or update your payment method at any time through the Stripe Customer Portal. If you cancel, you'll retain access until the end of your current billing period.