Max Deichmann

building (YC W23)

[Max Deichmann @maxdeichmann]

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.

[Max Deichmann @maxdeichmann]

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.

[langfuse.com @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; https://t.co/jBHM8WeA5e

[Max Deichmann @maxdeichmann]

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.

[Max Deichmann @maxdeichmann]

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 !

[langfuse.com @langfuse]

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: https://t.co/jBHM8WeA5e

[Max Deichmann @maxdeichmann]

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?

[Max Deichmann @maxdeichmann]

Lucky we dont have to build our own Iceberg + Trino wrapper. We rather have Alexey build it and optimizing every millisecond possible

[ClickHouse @ClickHouseDB]

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!

https://t.co/ua22RvNDWM

[langfuse.com @langfuse]

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; https://t.co/jBHM8WeA5e

[Max Deichmann @maxdeichmann]

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.

[langfuse.com @langfuse]

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; https://t.co/jBHM8WeA5e

[langfuse.com @langfuse]

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.

https://t.co/jBHM8WeA5e

[langfuse.com @langfuse]

@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.

https://t.co/isf5XmqcVr

[Marc Klingen @marcklingen]

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: https://t.co/GRXG5vByws
+ follow @langfusejp for Japanese updates

[Max Deichmann @maxdeichmann]

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

[Max Deichmann @maxdeichmann]

@DanielLockyer @langfuse Here is a talk where I describe what is going on: https://t.co/nG6uC0cMiJ

We will launch this more broadly over the next weeks. The new APIs are the first product on the new data model.

[Max Deichmann @maxdeichmann]

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

[Max Deichmann @maxdeichmann]

@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?

[Max Deichmann @maxdeichmann]

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?

[Marc Klingen @marcklingen]

New office who dis

[Max Deichmann @maxdeichmann]

@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.

[Max Deichmann @maxdeichmann]

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.

[Max Deichmann @maxdeichmann]

@langfuse More: https://t.co/nKbTderJVr

[Max Deichmann @maxdeichmann]

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.