HackerTrans
TopNewTrendsCommentsPastAskShowJobs

sfox100

no profile record

Submissions

Show HN: Deterministic evals API – the alt for LLMasJudge (free credits)

1 points·by sfox100·12 mesi fa·0 comments

Free evals API for AI startups (ship 10x faster with evals you can trust)

2 points·by sfox100·12 mesi fa·0 comments

Show HN: Composo – Evaluating and improving performance of LLM applications

composo.ai
30 points·by sfox100·3 anni fa·6 comments

comments

sfox100
·3 anni fa·discuss
Love this, and will use this daily
sfox100
·3 anni fa·discuss
Yes, great point, difference is that this Langsmith is more focussed on dev users, rather than the PM/domain expert users. And langsmith is also more on the observability, monitoring side, whereas we are more about testing & optimisation while in development
sfox100
·3 anni fa·discuss
Great question!

We see ourselves targeting different segments of the market.

1) Composo focusses on non-technical users like PMs or domain experts (in contrast to dev-focussed & open-source tools like Agenta).

2) With Composo, you build your application in code in a codebase (rather than building it in a low-code UI builder, like Humanloop). This enables teams to develop & test applications of any level of complexity, with no constraints on functionality.