building langfuse.com (YC W23)

Joined January 2022
16 Photos and videos
The best integrations are boring. SDKs, exporters, wrappers, and runtimes all produce slightly different telemetry. Sometimes numeric OTLP attributes arrive string-encoded. Sometimes metadata shape differs by provider. We keep investing in these small edge cases so Langfuse observability works out of the box, not only in the happy-path demo.
1
2
138
One of the coolest clickhouse fetures: the query log. When working with postgres i was always missing a table to see how queries actually performed and how many resources they consumed. Today, we use this to tag all queries with feature tenant metadata to attribute infra cost.
1
4
537
Its important to have a mix of signals when judging quality of traces: human annotation, LLMs, and now deterministic code. super excited to finally allow running small cloud functions on each observation ingested into Langfuse.
day 4 of langfuse launch week: code evaluators. write a python or typescript `evaluate` function in the langfuse UI. attach it to live observations or an experiment. scores land natively next to your existing ones. @wochinge demos below; langfuse.com/launch
1
4
280
This is one of the most powerful recent launches of us. As Langfuse is increasingly used by Agents, FTS is the best way to help agents to find what it needs in terrabytes of user data. Thanks for the ship @sum3rman !
day 3 of langfuse launch week: full-text search. multi-GB scans drop from many seconds to sub-second on @ClickHouseDB's new text indexes. great work from @sum3rman. available via UI and API. more: langfuse.com/launch
1
5
287
This also shows me how valuable the @ClickHouseDB acquisition was! Our team meet at our Tokyo offsite with the engineer who built CH FTS to discuss scalability, access patterns, and potential performance bottlenecks.
2
66
I am listening to many podcasts about how to use AI to be a better engineer. But what are the best ones talking in depth about how to build agentic apps?
1
53
Lucky we dont have to build our own Iceberg Trino wrapper. We rather have Alexey build it and optimizing every millisecond possible
Langfuse already had the momentum: 19 of the Fortune 50, 27k GitHub stars, 59M monthly SDK installs, and an enterprise-grade platform for LLM engineering. Together with ClickHouse, they now have fast OLAP, global support, flexible deployment … and yes, Alexey! langfuse.com/
1
45
Max Deichmann retweeted
day 2 of langfuse launch week 5: langfuse agent skill. bringing an agent to production is hard. using the skill you can ask your coding agent to instrument your app, calibrate a judge, or set up evaluators. @marliessophie demos below; langfuse.com/launch
2
7
23
3,042
We should be able to operate all devtools natively and headless out of codex/claude. UI is then the interface to revisit results regularly or change some finer settings.
day 2 of langfuse launch week 5: langfuse agent skill. bringing an agent to production is hard. using the skill you can ask your coding agent to instrument your app, calibrate a judge, or set up evaluators. @marliessophie demos below; langfuse.com/launch
1
55
Max Deichmann retweeted
day 1 of langfuse launch week 5: a github action that runs your langfuse experiments on every PR. fails the workflow when scores drop below your threshold. posts pass/fail to the PR. every run is tracked in langfuse. langfuse.com/launch
7
29
3,424
Max Deichmann retweeted
We're launching Langfuse Cloud in Japan today πŸ‡―πŸ‡΅ Hosted in ap-northeast-1 (Tokyo). The full @langfuse platform now with @clickhousedb team in Tokyo on the ground. if you're building with LLMs in japan: langfuse.com/japan follow @langfusejp for Japanese updates
1
5
21
1,401
We don’t only want to show taste in product design but also in office design. Next to the neon logo, what are best ways to make an office unique?
New office who dis
2
4
603
The team is excited to watch Steffen launching his new Rust container which he build over night to fix some of our big data challenges we were not able to solve in our database.
11
901
Last day of @Langfuse Launch Week. Schema Enforcement: Guarantee a consistent data structure for all dataset items, making your experiments reliable. Second, Dataset Folders. As your app matures, test datasets multiply. Easily organize them in folders.
1
4
280
Day 4 of Launch Week brings major upgrades to Experiments in @Langfuse. You can now annotate traces side-by-side in the compare view, set baselines to instantly spot regressions, and filter for outliers.
1
5
188
Day 3 of @Langfuse Launch Week is all about Agents. We have released major improvements to help you debug and evaluate complex agents. This includes a new tools overview to validate tool choices, new observation types, a log view, and agent graphs.
1
5
156