Live data from Hacker News

Viewing profile — almogbaku

almogbaku

HN member
Joined
Fri, Dec 20, 2013, 10:26 AM UTC
HN karma
18
Public activity
29 items

About almogbaku

A high-tech serial entrepreneur, leader, and developer.

Recent public activity

  1. comment
    Comment #47769869

    Hi @RoiTabach, OP here Yep. We can integrate with every solution that supports OpenTelemetry :) so it's pretty native, just use the integration skill npx skills add kelet-ai/skills…

  2. comment
    Comment #47769845

    Hi @BlueHotDog2, OP here langsmith/langfuse/braintrust collect traces, and then YOU need to look at them and analyze them(error analysis/RCA). Kelet do that for you :) Does that ma…

  3. comment
    Comment #47769771

    Hi @halflife, OP here YEP, Good catch! Kelet as input/prompt in Hebrew :)

  4. comment
    Comment #47769759

    Hi @hadifrt20, OP here From what we discovered analyzing ~33K+ sessions, most of the time when the agent selects the wrong tool, it's because the tool's description (i.e., prompt) …

  5. comment
    Comment #47769724

    Hi @jldugger Great points, but I think there's a domain confusion here . You're describing infra/code RCA. Kelet does an AI agent Quality RCA — the agent returns a 200 OK, but give…

  6. comment
    Comment #47769638

    hey @dwb, OP here Yes. I definitely assisted LLM in writing it. Yeah - I should have stripped it better. Yet it's f*ing painful to do error analysis and go through thousands of tra…

  7. story
    Show HN: Kelet – Root Cause Analysis agent for your LLM apps

    I've spent the past few years building 50+ AI agents in prod (some reached 1M+ sessions/day), and the hardest part was never building them — it was figuring out why they fail. AI a…

  8. story
    Show HN: Stop AI Debugging with Print(). Use a Debugger

    Coding agents debug like a junior dev in 2005: they spam print() and loop until the bug disappears or eats your context window. TL;DR: I gave my agent a debugger and saw it go from…

  9. comment
    Comment #47315454

    This is so funny, i've been working on my HN post for the past hour, then i saw this :) Anyway, in practice, I saw it go from 5-6 print-debug cycles down to 1-2 targeted stops. I b…

  10. story
  11. comment
    Comment #42785116

    Yeah, pytest-harvest is a pretty cool plugin. Originally I had a (very large and unfriendly) conftest file, but it was quite challenging to collaborate with other team members and …

  12. comment
    Comment #42783348

    Hey HN! Creator here. I recently found myself writing evaluations for actual production LLM projects, and kept facing the same dilemma: either reinvent the wheel or use a heavyweig…

  13. story
  14. comment
    Comment #35054560

    Lol that's pretty funny. But the UI is a bit unclear

  15. story
  16. comment
  17. comment
  18. comment
  19. comment
  20. comment
  21. comment
    Comment #29822397

    This is the weirdest code documentation I have ever read.

  22. comment
    Comment #29822341

    this is pretty cool to see how he predicted some things pretty good

  23. comment
    Comment #28920506

    Sounds fascinating. Tools nowadays are so cumbersome it’s so easy to misconfigure them. Thanks for sharing

  24. story
  25. comment
    Comment #10269219

    looks really interesting. thanks for sharing