CEO @ ZenML Labs | Ship AI you can trust
Munich
Joined July 2016
- Tweets336
- Following522
- Followers199
- Likes680
Adam retweeted
Five years ago @adamvpro and I started @zenml_io because getting AI from a notebook into production was painful.
It still is.
Only now it's agents, not just ML models, that make it hard.
Building an agent takes an afternoon. Keeping it working is the hard part. A prompt tweak breaks something that worked yesterday. A cheaper model quietly stops answering. You only hear about it when customers complain.
Every team we talked to said the same thing: we don't need another dashboard, we need someone to do the work.
So we built that.
ZenML Pro now comes with an always-on AI engineering team. It reads your traces, finds what your evals miss, and proves the fix works before you ship it. This tech is backed by ZenML and Kitaru, our two OSS products, that stay open source and freely available.
To kick off this new chapter, we have decided to rebrand. ZenML is now ZenML Labs, and our ambition is greater than ever.
Connect your agent traces today, free at zenml.io.
We are very proud of the onboarding ;-)
We wrote about it here: zenml.io/blog/introducing-ze…
It’s not Ferrari vs Toyota. It’s: on my traffic, per task, what holds and what does it really cost? Most teams can’t answer that, so they switch and watch the complaints.
That’s why we replay your real prod sessions against the new model.
Who’s measured the full cost of a swap?
2
44
Kicking off the @aiDotEngineer summit in NYC! Let’s go!!
@swyx thank you for bringing together so many real builders!
4
92
Adam retweeted
Let's go #SFTechWeek
If you're not attending this event, partiful.com/e/e1ylZcEsWzY0b…, what are you even doing?
@zenml_io woot woot
Adam retweeted
Let’s go @aiDotEngineer !!
Drop by if you want to see our agent that improves your agents
Adam retweeted
We will be at @aiDotEngineer at STATION F this Wednesday and Thursday, where we’re proud to be sponsoring with @zenml_io .
Thank you, @MistralAI for organizing!
Come find us if you’re building AI agents and thinking about how to make them reliable in production. We’ll be showing how Kitaru helps teams capture production traces, turn real-world behavior into evaluations, and replay agent workflows to understand whether changes actually improve the system.
Also something special: Peek into something we will announce soon! (It's not "just" Jev ;-) )
Come by our booth. Stay for a drink!
We're sponsoring an official side event: luma.com/v3bao3nd
Adam retweeted
Roadshow alert! Meet the @zenml_io team in person, as we gear up for event season.
Meet us this week in Amsterdam at MCP Con, or next week in Paris for @aiDotEngineer (where we're proudly sponsoring this year).
Come chat to us about GPU management, self-improving agents, and everything in between!
You swap the model in a production agent. How do you know nothing broke?
Kitaru replays your real sessions against the new model, with the writes blocked, and shows what got better, what got worse and what it costs.
A raw 5-minute walkthrough this morning, no polish
1
7
165
Adam retweeted
I love catching up with all the new videos that come out of the AI Engineer @aiDotEngineer conferences on Youtube. It's one of the main venues where people building agents really show their work.
The problem is that it publishes more talks than I can honestly keep up with. So I made AIE Talks: a written archive of the channel. 🧵 (h/t to @swyx for his amazing leadership in growing these conferences!)
Tinder for Traces 🫶
Well this went viral. Seems like we need a better way to visualize agentic traces, especially for people who are not crazy technical enough to diagnose a JSON trace.
Here's one UX we're exploring in Kitaru (kitaru.ai/) - a Tinder-style approach to evaluating your agent traces.
You can swipe left and right (and up), and leave notes on what went wrong with a mic.
There are so many UX innovations that have not happened yet. Leave more ideas in the comments if you have any 👇
nitter.gq/htahir111/status/20948…
3
115
Five years of ZenML, pointed at the newest problem. The most important thing we've shipped since the first release. Proud of the team 👇
I messed up.
I accidentally deleted our launch X post for Kitaru that went viral last week.
Hope this answers the question for some of you wondering. It was just a silly mistake, nothing deeper :D.
20K views, 100s of bookmarks, 400 likes, all gone in a moment of madness tbh. Oh well it lives on on LinkedIn!
But you know what I learned? Sometimes, your biggest mistakes can be opportunities hidden in disguise.
So I'll take this opportunity to reintroduce Kitaru again 😀
If anything, hopefully it gets people to check out our latest releases: We're even better today then we were last week on our mission from creating a self improving loop from your existing agent traces.
Ingest traces from langfuse, braintrust, arize etc, get interviewed by Kitaru with targetted annotations, and get evaluator functions individualized for you. Replay against baselines of what happened in prod. Export to harbor datasets when you're ready to go beyond the harness layer and finetune/RL your OSS models for your agent.
Try it now, free and OSS: kitaru.ai/
1
129
Adam retweeted
Well this went viral. Seems like we need a better way to visualize agentic traces, especially for people who are not crazy technical enough to diagnose a JSON trace.
Here's one UX we're exploring in Kitaru (kitaru.ai/) - a Tinder-style approach to evaluating your agent traces.
You can swipe left and right (and up), and leave notes on what went wrong with a mic.
There are so many UX innovations that have not happened yet. Leave more ideas in the comments if you have any 👇
nitter.gq/htahir111/status/20948…
Nobody cares about your trace.
If you think your domain expert, who could be a lawyer, doctor, or a mechanic working in a workshop is going to login to your observability tool and "annotate" what went wrong with your agent, you're living in dream land.
Self improving agents need a better UX then this JSON dump
Five years of ZenML, pointed at the newest problem. In my eyes the most important thing we've shipped since the first release. Proud of the team 👇
This quoted post is unavailable.
Adam retweeted
Today, we've also signed the Open Weights letter.
Open source strategic flexibility is what we’ve been betting on for years at @zenml_io
Long live open weights and open source for AI!
Adam retweeted
Just released my open-source course "Building a Coding Agent From Scratch" with a focus on hardcore harness engineering.
In LangChain’s Terminal-Bench experiment, changing only the harness (with the same model) moved a coding agent from ~30th place into the top 5: the harness, not the model, is what makes a coding agent good.
In this course, you’ll build that harness from scratch in Python: Decode, a complete coding agent that grows lesson by lesson from a bare agent loop into a swarm of remote agents running in parallel in the cloud.
Adam retweeted
Had fun talking to @bigdata about AI agents and Kitaru by @zenml_io.
A small reminder we are "old-school" OSS: github.com/zenml-io/kitaru. Giving us a star means a lot.
So much to launch this week - make sure to follow along. Hinted some of this in the podcast
thedataexchange.media/hamza-…
Adam retweeted
Stoked to be featured in the @pydantic AI blog yesterday.
In a world where all AI frameworks are pulled to every corner of the stack, it's great to see @samuelcolvin's team have the discipline to separate the stack's layers in a smart way. In this case, we both believe the runtime layer is distinct from the AI framework layer.
That's why we've shipped our first deep integration with Pydantic AI. It works seamlessly, you just wrap your Pydantic AI agent and get checkpoints, replay, resume, wait states, artifacts, logs, execution history, and operational control. That gives the agent somewhere to land when production does ordinary production things: a URL times out, a process dies, a human approval arrives later than expected, or someone needs to understand a failed run without reconstructing it from pasted tracebacks.
Read more here: pydantic.dev/articles/runtim…
Thank you @lais_bsc for the support in this collab!
Adam retweeted
Late night podcasting with the production AI 🐐, coming to you soon from a random hotel in 🇩🇪👀 @Dpbrinkm
