Sabitlenmiş Tweet
shubham
2K posts
shubham
@ShubhamInTech
infra for self-improving agents • https://t.co/Fq3PewMpH3 • backed by @join_ef • founding engg @formbricks • youngest engg at cisco analytics
Katılım Temmuz 2022
2.1K Takip Edilen1.4K Takipçiler
Presented Nometria at @join_ef Demo Day in front of hundreds of investors.
35M apps have been vibe coded in the last 9 months. Most run on shared infra and are starting to break as they scale.
Nometria is the production OS for these businesses.
San Francisco, CA 🇺🇸 English
Introducing Agnost AI.
The first infrastructure that lets your AI agents learn from every user.
It catches every raw intent, connects it back to what your agent did wrong, and improves the agent. Autonomously.
Because with AI agents, there's no complaint, just churn.
English
I'm looking for a coworking/office space to work from today.
Paid for Frontier Tower but they are being too slow to let me in, and won't grant temporary access. Also the monitors suck and the atmosphere is a bit stifling.
Extremely sad because the people working there were cool when I visited.
Will give them a chance but looking for something else, either just for the day or permanently.
English
@ShubhamInTech @Scobleizer Sounds cool, but how accurate is it tho?
English
@ShubhamInTech Looking forward to Project Ayurved 🔥
#insider
PS: great video!
English
and that's the bigger problem! an llm will say "i dont know that" with a status code 200.
analytics are gonna be redefined!
Ivan Burazin@ivanburazin
The co-founder of a $1B VoiceAI infra company says you can't test agents the same way you test traditional software. According to @dsa, you have to test these things almost like you test human beings. Like college degrees, resumes, job interviews, reference checks, etc. What you're really trying to do is build statistical confidence that the person you're hiring can do the task with 99% precision/confidence. Have to test agents the same way by running thousands of end-to-end simulations. Permute accent, language, system prompt, instructions, etc, and see how it performs against the success criteria spit out by your observability stack. This way, you're building confidence, deploying it, and observing which bugs/issues require tweaking. Take those back and make changes to the agent code. Test again, run simulations, and make sure there's no regression. Then deploy again, scale, and observe. That's how the loop goes.
English
@ninadwrites try it out and tell me what you hate about it, ill fix it
English
@ShubhamInTech If it works the way you’ve promised, this is definitely solving a huge gap in the market right now
English
