Berlin
Joined February 2013
- Tweets1.1K
- Following1.3K
- Followers1.1K
- Likes8.4K
Clemens Rawert retweeted
Invited 700 @ClickHouseDB staff to our office to start the week with some sausage, really excited for the week
Clemens Rawert retweeted
Really excited about WalShadow. @saisrirampur and the Postgres team at Clickhouse are the best in the business
So exciting to see the power of WalShadow in action! Literally fusing Postgres and ClickHouse together.
The past month has been intense, rigorous POCs, lots of testing, and a few early production customers! The results have been incredibly promising. 🚀
We’re seeing WalShadow replicate hundreds of MB/s from Postgres to ClickHouse with sub-second latency. Something that was previously impossible to achieve!
Here’s one from Anirudh at @physical_int, 350ms vs. 35 seconds! 🤯
A little bittersweet seeing the comparison with PeerDB, but always wanted to do, take Postgres to ClickHouse replication to the next level.
Huge thank you to Anirudh, @mairbek and the Physical Intelligence team for their support since the beginnning. It means a lot to us! ❤️
Stay tuned for more stories. We’re just getting started! 🔥
Clemens Rawert retweeted
Wrote about optimizing the cost of your AI agent. This is such an important aspect of building agents successfully, and people often do this "vibes-based". This should offer some structure for anyone going through the process.
Clemens Rawert retweeted
Pick 🪢 @langfuse, add your keys 🤝
xitter.cf/langfuse/status/211042…
Claude agent traces, now in Langfuse.
The Claude Platform exports OpenTelemetry traces natively from Claude Managed Agents, the Messages API and the Claude SDKs, now in public beta.
Inspect turns, tools, latency and cost in Langfuse. Turn real runs into evals to improve agents.
Get started: langfuse.com/integrations/mo…
@ClaudeDevs
Clemens Rawert retweeted
"The whole pipeline to improve our chat agent happens entirely in Langfuse. Engineers and domain experts work hand-in-hand.."
@DKB_de self-hosts Langfuse to trace and screen its in-app assistant across 10,000 to 20,000 conversations a day. langfuse.com/users/dkb
Clemens Rawert retweeted
The wonderful humans behind @langfuse
Come join our team (remote, offices in SF, NYC, Amsterdam, Berlin), help users at the frontier of AI, while most work is in public/OSS
langfuse.com/join-us
(part of @ClickHouseDB, very ai-pilled, growing fast, stellar leadership)
Best offsite yet. Team is growing quickly and meeting in-person, exploring what’s next, and spending time with each other is really nice
Thanks @nimarblu for leaning into the analogue film here to capture the moments
Clemens Rawert retweeted
Hi I am in your city I'm on the other side of town and I have 45 minutes of free time and we're not very close friends and I'm generally kind of unpleasant to be around we have GOT to hang out are you free right now
Clemens Rawert retweeted
Jesus christ
Some data we recently assembled on entrepreneurship/compute in Europe: eudata.vercel.app.
We hope that one of the useful roles that Stripe can play is in collecting and publishing empirical data pertaining to entrepreneurship and industry in Europe. There's growing appetite to get Europe on a better footing, and cross-sectional comparisons can often shine light on where opportunities lie. If you're interested in this kind of thing, we publish more at stripeeconomics.substack.com.
Clemens Rawert retweeted
how awesome would it be if every new table created, every column name change, every column TYPE change is replicated from Postgres to @ClickHouseDB ?
WalShadow does all of these, crazy to see users experience this magic. checkout: clickhouse.com/blog/introduc…
Clemens Rawert retweeted
Based on our experiments, Jev bears big potential for evals
✔️ It is up to 400x cheaper than frontier models, making full scoring of production traces feasible, no more sampling needed, even at huge scale
✔️ It allows for concurrent questions on the same state, where LLMs previously struggled with interaction effects and common wisdom was to not mix evals in the same requests. This makes Jev even cheaper.
✔️ The structure of Jev's output forces thinking in distinct categories during setup, improving the engagement with defining the exact evaluator categories
Play around with this demo here: langfuse.com/blog/2026-09-18…
Clemens Rawert retweeted
Finally got to record a 15 min overview of what @langfuse is based on an end-to-end example
- how it helps build great AI agents/apps
- how to continuously improve them with Lanfguse
- how the integration works
- why langfuse and no closed-source solutions
- how agents use it
@marcklingen sat down to demo all langfuse features in a single video.
Agent observability, monitoring, evals, prompt management, and what is special about Langfuse.
Great place to start if you are new, or catch up on latest changes.
langfuse.com/watch-demo
Clemens Rawert retweeted
Why Jev is interesting for evals
> Every question is evaluated in parallel and in isolation against the same state. So adding a fourth question, or a fourteenth, barely changes response time, costs only the tokens of the question itself, and cannot degrade the answers to the others. You can ask speculatively and throw away what you do not need.
Fits very nicely to how good evals should work. Let's see what competition will do to this segment (make it even better, cheaper, faster).
