München | Claude Workshop
Build a software factory with Claude Code. A hands-on evening, not a talk night: bring your laptop and leave with a crew of Claude Code sessions that plans with you, builds, reviews and merges.
- When: Thursday 29 October 2026, 18:00 to 20:45
- Where: JetBrains München, Christoph-Rapparini-Bogen 23, 80639 München
- Hosts: Claude Community x GlassFlow, supported by Anthropic. JetBrains hosts the evening at its venue.
- Event page: luma.com/claude-pm6s
- Language: English
Do the setup at home before you come. The venue Wi-Fi is shared by everyone in the room, so installs and downloads on the night are slow.
Tares is open source. Everything tonight runs on it. If you like what you build, star the repo on GitHub: it helps others find it.
★ Star Tares on GitHub
What you build
Part 1: Software factory
You set up a software factory on your laptop: a crew of Claude Code sessions that turns a plan into pull requests merged on main. Then you give it a small test job to watch the whole loop run once.
- You build the crew, running in the background on your own Claude Code plan: the orchestrator, which picks up planned projects and starts builders; a builder, which works the tickets in your repo, one pull request each; and the reviewer, which reviews every pull request before it is merged. Tares holds what they share: the spec, the tickets, the reviews and your answers.
- You test it on a toy job: a click counter for a tiny link shortener, your own copy of a template repo with tests and CI. You plan it in a short interview with Claude: two tickets.
- You watch the orchestrator hand the plan to the builder, which opens one pull request per ticket. The reviewer reviews each one, and once CI is green the builder merges it.
- You take home a factory that works on any repo: point it at a real project next.
About 30 minutes. Start Part 1.
Bonus: Build an AI SRE with a handover agent
Finished early? Build two agents that watch a small live service, break the service on purpose, and watch the agents find the root cause.
- You watch a demo service with steady traffic: its Prometheus metrics, its error logs and the alerts Prometheus fires. Tares puts all of it on one timeline for the service.
- You build a watcher on a small, cheap model that looks every 2 minutes, and a root-cause agent on a bigger model that only runs when the watcher says “investigate”.
- You see a finding appear 2 to 4 minutes after you break the service: what is failing, since when, the likely cause and a next step.
- You take home the watch-then-escalate pattern, and how to point it at your own services.
About 45 minutes. Start the bonus build.
Agenda
| Time | What |
|---|---|
| 18:00 | Doors open, pizza, drinks and networking. Connect to the Wi-Fi and run the setup check |
| 18:30 | Welcome (Florian Steiner, Claude Community Ambassador Munich) |
| 18:35 | The software factory setup (Armend Avdijaj and Kiran Nambiar, GlassFlow) |
| 18:45 | Hands-on: build a software factory with Claude Code and Tares |
| 19:30 | Bonus build for early finishers: an AI SRE with Claude Code and Tares |
| 20:15 | Show and tell: what did you build, and what did the reviewer catch? |
| 20:35 | Wrap-up and a short outlook from GlassFlow |
| 20:45 | End |
Workshop by
- Armend Avdijaj, Co-founder and CEO at GlassFlow. Armend leads GlassFlow, a Berlin-based startup building data infrastructure and observability tooling for AI agents in production.
- Kiran Nambiar, Senior Backend Engineer at GlassFlow. Kiran builds the data infrastructure behind observability and context engineering for AI agents in production.
Good to know
- You build on your own laptop, alone or at a table with others.
- Every approved participant receives Claude API credits after the workshop. Register with the email address of your Claude account.
- Space is limited. If you can’t make it, release your spot on Luma so someone from the waitlist can join.
Local or cloud
You can run each part against a Tares on your laptop (local) or against a Tares workspace we host for you (cloud).
- Local: everything runs on your laptop. The bonus build local needs Docker and your own Anthropic API key.
- Cloud: a free Tares workspace with $10 of model credit. You get the join link on the night. No API key needed.
Both are fine. If Docker or the Wi-Fi gives you trouble on the night, switch to cloud. The guides here are the local versions; the cloud versions follow before the workshop.
Downloads
Everything the two builds use, in one place.
| File | For | What it is |
|---|---|---|
| factory-workshop-starter | Part 1 | The link shortener you copy with Use this template. |
| click-counter-spec.txt | Part 1 | The ready-made spec, to skip the planning interview. |
| tares-demo.zip | Bonus | The demo stack: docker-compose.yml and inject.sh. Unzip it, then run docker compose pull inside: the images (about 600 MB) still come from the internet. |
Keep going
After the workshop, point what you built at your own systems.
Part 1: Software factory
- Get started with the software factory : run a crew on your own repos.
- A project end to end : one real project followed from the spec to eight merged pull requests and a deploy.
- Autonomous Claude Code sessions : how the crew’s sessions keep working in the background while you are away.
Bonus: AI SRE
- Build an AI SRE : the same demo, then how to swap in your own metrics, logs, alerts and deploys.
- Watch, then escalate : the watcher and root-cause pattern from the bonus build, for any sources.
- Connectors : Prometheus, Alertmanager, Docker logs, OpenTelemetry, GitHub, Postgres, webhooks and more.
- Tares cookbooks : a complete incident-response agent in code, if you would rather write the agent than configure it.
Tares and Claude Code
- Tares docs and the Tares repo on GitHub . A star helps others find it.
- Connect your agents to Tares over MCP.
- Claude Code docs .