Berlin
Joined February 2013
- Tweets1.1K
- Following1.3K
- Followers1.1K
- Likes8.6K
Pinned Tweet
I'll be speaking at @ClickHouseDB user conference Open House in London at the end of September. Registrations are now open & I'm very much looking forward to being in 🇬🇧
- clickhouse.com/openhouse/lon…
I'll be at Shanghai for @aiDotEngineer conference at the end of this week. Looking forward to meeting @langfuse open source community locally 🇨🇳
Clemens Rawert retweeted
Needing to stay on top of big-corp slack, I really like slack now but it took me 6 months to figure it all out
My setup
- started channel (always show)
- prio channel (show when unread)
- ignore all other channels even when you get added back to them, have hundreds of these
- alerts, create a filter for DMs/@ mention; this is the group with my highest service level. If someone tags me, I want to be fast
Feels pretty chill now. Grok bot keeps track of all commitments I make on slack and elsewhere and catches me up on what happened overnight after I wake up
It’s bad that these notifications and read/unread are not available via MCP (like eg linear does it)
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 🤝
nitter.gq/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
just a really good launch video. actually explains plainly what they do.
interesting that that sticks out 🥹
also amazing tech from tim that I’m happy to see come live today!
Introducing Expand Fetch, a new way to scrape and crawl the web.
Your agent has never seen the web. No wonder it gets basic questions wrong.
Traditional Markdown APIs lose critical details. So we trained two System one models to change that:
Iris, a vision model that sees pages like you do, preserving tables, icons, and layouts.
X-Ray, a JSON model that uncovers the hidden data behind every page.
Every fetch also comes with a Wayback Machine. Every line links back to its source, so you can verify exactly what your agent saw.
Three products. One API.
On our benchmark of 1,094 questions across 326 challenging web pages, agents using Expand got 74% right. The next best API got 55%.
Available today at $1 per 1,000 fetches.
Try it at expand.ai
very nice way to spend the morning before @aiDotEngineer conference!
second edition of the @langfuse at @aidotengineer run club, this time in NYC
great morning loop through Central Park with coffee and breakfast afterwards
thanks everyone for joining!
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
🗽 in NYC next week for @aiDotEngineer
highly focussed on financial services industry during the day and 🍻 at night.
we're at @aiDotEngineer NYC next week, oct 12–14
mon 2:20pm: langfuse workshop, the AI engineering loop end to end (by @annabellschfr and @doneyli)
wed 2:55pm: @doneyli on deployment gates for AI agents in financial services
come by the booth too
ai.engineer/nyc/2026/schedul…
