Max Deichmann

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 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

@langfuse launch week 5 starts monday. one release per day, mon to fri. agents, evals, and some long-requested features. we'll be demoing all new features at @ClickHouseDB Open House in San Francisco same week. come say hi. langfuse.com/launch

We're launching Langfuse Cloud in Japan today 🇯🇵 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

@NirantK @marcklingen @NirantK can you share more about this? What edge cases do you have?

@marcklingen @maxdeichmann v4 is great. We still have some edge cases when using with Claude SDK which are a pain though

Big things are cooking, love the tshirt @maxdeichmann

@DanielLockyer @langfuse Here is a talk where I describe what is going on: youtube.com/watch?v=NXYQ5o… We will launch this more broadly over the next weeks. The new APIs are the first product on the new data model.

@maxdeichmann @langfuse Curious if you can share the main diff between the two? Diff tables? Diff architecture?

Been seeing HTTP 502/503 responses from the @langfuse API for a while now - is this normal? Would love to know why this is happening 🙃

@DanielLockyer @langfuse Awesome! Yes, the v2 APIs are very high performance APIs. If you have feedback here, let us know!

@maxdeichmann @langfuse api/public/traces/<id>, BUT I've just followed up with my client and it seems you've recommended the v2 API :) I'll check it out!

@mgill25 @mgill25 love this. We can host in our office at @langfuse and are also happy to share insights about our system architecture. Do you want to chat about this?

#Berlin peeps - thinking of organising another edition of Berlin Systems Group Meetup in January. If you’re interested in speaking - check out berlinsystems.xyz and DM me!

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?

@skylar_b_payne @langfuse @langfuse_dev Hi, im the CTO at Langfuse. Correct, the ClickHouse nodes should never scale to zero. Otherwise you won’t be able to ingest data.

@langfuse / @langfuse_dev - am I right in understanding the architecture that clickhouse query processor will basically never scale down to zero as long as traces are continuously coming through? (unless aggressive batching?) Trying to estimate costs :). I think this is right, but love double checking my work haha

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.

@langfuse More: langfuse.com/blog/2025-10-2…

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.

@langfuse We also added new guides on experimentation and CI/CD integration here: - langfuse.com/blog/2025-11-0… - langfuse.com/blog/2025-10-2…

@langfuse More: langfuse.com/blog/2025-10-2…

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.

@langfuse More: langfuse.com/changelog/2025…

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.

@langfuse More: langfuse.com/changelog/2025…

Today is Day 2 of @Langfuse Launch Week 4, and we're launching features for better team collaboration. You can now use @ Mentions to tag teammates directly on traces, prompts, or sessions, and use Emoji Reactions to quickly acknowledge insights and share feedback.