AI Dev Tools Zoomcamp

Now it's time to learn from your peers! We closed the form for submitting Project 1. If you submitted it, you will find your peer review assignments here: https://courses.datatalks.club/ai-dev-tools-2026/project/project1/eval Review deadline: end of Monday, November 2 (Tuesday, November 3, 00:00 CET) Remember that reviewing 3 peers is a mandatory step. If you don't complete it, you will not pass the project. Have fun and happy learning!

Project 1 is due next week: October 27, 2026 at 00:00 CET (October 26 at 23:00 UTC). The final project criteria are ready: 12 criteria worth 24 points, and you need 10 points to pass. Check what to build and how it's scored before you submit. After the deadline, you review three projects from other participants. Reviews are part of the project: without them, your project doesn't pass. They're due November 3, 2026 at 00:00 CET (November 2 at 23:00 UTC).

The final project criteria are ready! 12 criteria, 24 points - you need 10 points to pass. See what to build and how it will be scored: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/tree/main/project

Project 1 is due in two weeks: October 27, 2026 at 00:00 CET (October 26 at 23:00 UTC). Your project needs to cover everything we talked about in the course: • Specification-driven development • Creating the front end and the back end • Containerizing the application • Deploying the application • Following the best DevOps practices Project requirements: https://datatalks.club/docs/courses/ai-dev-tools-zoomcamp/project/ Submit: https://courses.datatalks.club/ai-dev-tools-2026/project/project1 After the deadline, you review your peers' projects. Questions and project-scope discussions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C09HWT76L95

Today, it's time to start working on your projects. Your project needs to cover everything we talked about in the course: • Specification-driven development • Creating the front end and the back end • Containerizing the application • Deploying the application • Following the best DevOps practices We will update the current project criteria. Right now, it's outdated and contains the criteria from last year, but it's going to be updated and we will have announcements about it soon. You are free to choose any coding agent and technology you want, as long as you follow the ideas we described in the course. Have fun learning and have fun building!

We start Module 5, the final module, on Coding Agent Capabilities. Across the course, you have used coding agents for planning, implementation, testing, deployment, and operations. This module shows how to make useful agent behavior reusable without giving every task the same context and permissions. We cover: - Reusable skills and specialized subagents - Which instructions and tools each task needs - Where to set boundaries for an agent - How to make the result verifiable by another person Materials: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/tree/main/05-agent-capabilities Recording: https://www.youtube.com/watch?v=t8OrAjNO2Zs Companion article: https://aishippingblog.com/p/coding-agent-building-blocks-reusable There is no graded Homework 5 in the 2026 cohort. Use this week to create or improve one reusable capability and apply it to a real task in your project. After Module 5, the course moves to the final project. Review the requirements early so you have time to choose a clear problem and build something another person can run, test, and review. Project requirements: https://datatalks.club/docs/courses/ai-dev-tools-zoomcamp/project/ Project 1 deadline: October 27, 2026 at 00:00 CEST (October 26 at 22:00 UTC). Project 2 deadline: November 17, 2026 at 00:00 CET (November 16 at 22:00 UTC). Questions and project-scope discussions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C09HWT76L95 You can submit Homework 4 until October 5, 2026 at 01:00 CEST (September 28 at 23:00 UTC).

Homework 4 is finally live. Sorry for the delay, and thank you for your patience. Homework instructions: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/blob/main/cohorts/2026/homework/04-devops/homework.md Submit here: https://courses.datatalks.club/ai-dev-tools-2026/homework/hw4 We’ve moved all remaining deadlines by one week, including project submissions and peer reviews: • Homework 4: 5 October • Project 1 submission: 26 October; peer review: 2 November • Project 2 submission: 16 November; peer review: 23 November All dates are in 2026, and all deadlines are at 23:00 UTC.

Louis Amaudruz built a team of AI agents in Slack, live, during our latest workshop. They worked together on GitHub issues for the Switch repository. The recording is now up. Louis started with an empty Slack workspace and walked through each agent: - A Claude Code coder agent that fixes an issue and opens a pull request - A Codex reviewer agent that reviews the fix in the same channel - A lead agent that runs the code-review loop, with a maximum of two cycles - An issue manager that creates one channel per issue and starts the work in each of them Louis also showed how the Switch team uses the same pattern for its own work, with rooms for bug reports, feature work, local deployments, releases, and staging deployments. Watch the recording to follow the full build: https://www.youtube.com/watch?v=vl00W8eEtZg

We start Module 4 on DevOps and Observability for AI-Built Apps. Once your application is deployed, you need to know what it is doing. With observability, you can see where the app failed, investigate with the right context, and decide how to respond. We cover: - What to observe in a running application - Which failures should trigger alerts - What context an investigation needs - Where coding agents can help with operations safely - Which production permissions stay with humans Materials: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/tree/main/04-devops Recording: https://www.youtube.com/watch?v=YkxLo_FRoQw Companion article: https://aishippingblog.com/p/devops-and-observability-for-an-ai Homework 4 is currently a draft and the questions will likely change. We will announce once it’s ready. Homework: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/blob/main/cohorts/2026/04-devops/homework.md Submit: https://courses.datatalks.club/ai-dev-tools-2026/homework/hw4 Deadline: September 29, 2026 at 01:00 CET (September 28 at 23:00 UTC). Next week, the final module covers reusable coding-agent capabilities: skills and specialized subagents. Questions go in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C09HWT76L95

New free model: https://x.com/OpenRouter/status/2100235351575191751

We're starting a stream about organizing a team of agents and creating a startup https://www.youtube.com/watch?v=vl00W8eEtZg Join us here or watch later in recording

We start Module 3 Getting an application to work once is different from making it reproducible and ready for other people to run. This week, you will strengthen the checks around your application, package it consistently, document how to run it, and deploy it somewhere others can inspect. Materials: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/blob/main/03-deployment/lesson.md Recording: https://www.youtube.com/watch?v=gxt5ZDVnBMM Companion article: https://aishippingblog.com/p/deploy-a-full-stack-app-with-ai-coding Homework page: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/blob/main/cohorts/2026/homework/03-deployment/homework.md Submission page: https://courses.datatalks.club/ai-dev-tools-2026/homework/hw3 Deadline: September 22, 2026 at 01:00 CET (September 21 at 23:00 UTC). Next week, Module 4 will cover DevOps and observability for applications built with AI assistance. Questions belong in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C09HWT76L95

If you're looking for a way to get free or cheap AI coding assistant, I just wrote an article about it https://aishippingblog.com/p/free-and-affordable-ai-native-development Maybe it'll help some of you!

The homework is updated: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/blob/main/cohorts/2026/homework/02-development/homework.md Have fun!

We start Module 2 This week, we move from designing an AI-native workflow to using it across a full-stack application. Module 2 is Build and Ship an AI-Assisted Full-Stack App. The focus is the complete development loop: planning the application, coordinating frontend and backend work, testing the integration, documenting the result, and getting it deployed. Materials: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/tree/main/02-development Recording: https://www.youtube.com/watch?v=x9dq5nBpDg8 Companion article: https://aishippingblog.com/p/build-and-ship-a-full-stack-app-with The current Homework 2 is DRAFT. Once it’s updated, we’ll notify you. Submission page: https://courses.datatalks.club/ai-dev-tools-2026/homework/hw2 Deadline: September 15, 2026 at 01:00 CET. Next week, Module 3 will focus on testing, containerizing, and deploying the application. Questions belong in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C09HWT76L95

Muse Spark 1.3 is completely free in opencode How to use it - download and install OpenCode - select Muse Spark 1.3 Free - use for free while they run this campaign

Module 1 has started This week, we begin with AI-Native Developer Workflow. The goal is to turn a vague product idea into specified, implemented, and independently verified software with coding agents, while keeping requirements, key decisions, and final review in human hands. You will work on: - Turning an idea into a product specification and focused backlog. - Giving agents durable context with AGENTS.md and project documents. - Separating product manager, software engineer, and QA roles. - Using loop engineering around checkable completion conditions. - Coordinating specialized agents across a backlog with graph engineering. Materials: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/tree/main/01-ai-native-workflow Recording: https://www.youtube.com/watch?v=VUJxJGpaDEs Companion article: https://aishippingblog.com/p/ai-native-development-specifications Homework 1 asks you to apply this workflow to a spec-driven Django application based on a deliberately vague shared-household-chores idea. Instructions: https://github.com/DataTalksClub/ai-dev-tools-zoomcamp/blob/main/cohorts/2026/01-overview/homework.md Submit here: https://courses.datatalks.club/ai-dev-tools-2026/homework/hw1 Deadline: September 8, 2026 at 01:00 CET (September 7 at 23:00 UTC). The homework is useful practice, but it is not required for the certificate. Questions belong in the course Slack channel: https://app.slack.com/client/T01ATQK62F8/C09HWT76L95

We're officially starting our AI Dev Tools Zoomcamp! Join us to learn how to go from raw idea to production with AI coding agents - Stream: https://www.youtube.com/watch?v=YEsrF3EX4Hw - Article: https://aishippingblog.com/p/ai-dev-tools-zoomcamp-2026-starts - Questions: https://qna.dtcdev.click/r/ai-dev-tools You can also watch the stream later in recording Have fun!

Coming back with "Use Claude Code as a Pro"! Stream: https://www.youtube.com/watch?v=H-Ot4_1PkoM Materials: https://github.com/thelearningdev/use-claude-code-like-pro Join now or watch later in recording