Engineer. Automaniac. All things distributed. CTO at @Sixt. These are my views...
Munich, Bavaria
Joined June 2009
- Tweets459
- Following795
- Followers822
- Likes626
Over 1000 apps have been built and deployed on our SIXT Vibe platform by our business teams in the last 3 months!
In my Platformcon talk I share how we built the platform underneath. youtu.be/zDW7MY57z2w?si=CvXN…
2
379
Opus 4.8 is disappointing… massive regression from 4.7 on basics. Does not follow up on memory , ignores basic Claude.md instructions constantly and keeps admitting of doing so.
1
2
188
Codegen is not the interesting part for large orgs.
It's whether agents can help move a change through the many generations of services and APIs that exist. And how to organize your context so that they can verify a solution end to end autonomously - it's where the time goes.
130
A decade after the West gave up on building the super app, it’s coming back- and this time it might actually work.
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude.
Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
1
111
With the latest Claude Code session limit changes I started hitting the wall way more often - especially during peak hours I didn't even know existed.
So I built a small status line tool that keeps your budget visible at all times. Pacing, per-prompt cost, peak detection, and a warning before you burn through it.
github.com/boyand/cc-budget
Lately I get the best results by chaining Claude and Codex together.
Claude plans. Codex reviews. Claude implements. Codex reviews again.
Tried different solutions but never got to a reliable unattended mode so ended up building a plugin that makes the loop repeatable.
github.com/boyand/codex-revi…
How it works
/codex-review:plan — Codex reviews your Claude plan
/codex-review:impl — Codex reviews implementation against the approved plan
/codex-review:summary — severity counts + per-finding decisions
Each Claude session gets its own workflow. Prior rounds are preserved.
1
143
Funny first days of 2026 with Claude Code. At first, one started maxing out the MAX 20x within 1-2 days for what took a whole week before. Now the Usage tracking is completely gone. Vibe++
1
284
For the first time publicly, we unveiled the core foundations that enable us at SIXT to generate ready-to-ship, full-fidelity, enterprise-quality screens directly from Figma designs.
The magic happens when years of platform investments compound: Our AI-powered pipeline now transforms designs from intent into production-ready code, supporting 800+ engineers, product owners, designers and data scientists across SIXT's ecosystem.
We are just getting started. If you want to join a wild journey, DM me.
More on our AI Design to Code pipeline and our platform engineering approach:
slideshare.net/slideshow/how…
youtube.com/watch?v=OtxWxkeh…
195
Albeit being bullish on AI, I can’t stop thinking about the mountains of e-garbage being produced.
All those “AI companions” creating your motivation letter and applying in your name to hundreds of jobs. And then we have “AI screening tooling” and “AI recruiters” filtering out the thrash. So much capital wasted to get back to square 1.
2
372
Boyan Dimitrov retweeted
A fantastic retrospective from #AWS Sr. Principal Engineer @molson, who's been at the heart of scaling #EBS for over a decade. Marc shares hard-won lessons on driving continuous performance improvements - a must-read for cloud infrastructure nerds.
allthingsdistributed.com/202…
#Crowdstrike , you may actually be remembered for the most expensive line of code in history. Wonder about the amount of digits in that number @GWR
2
199
BSOD affected machines are starting to come back after continuous reboots. Probably #Crowdstrike is getting this fiasco slowly under control . Thousands of our Windows workstations are returning online.
2
645