Minimum Viable Founder
Subscribe
Sign in
Home
Notes
Archive
About
AI Evals Aren't Just for Big Tech
How a small bootstrapped team measures its AI the way frontier labs do: a practical approach to evals that you can copy.
Jul 29
•
Jai Juneja
2
2
Why AI 'Company Brains' Fail (and How We Built One that Doesn't)
Traditional RAG retrieval fails on the questions that matter. Knowledge graphs answer them at 1000x the cost. We shipped the middle path.
Jul 20
•
Jai Juneja
8
1
March 2025
Deep Research: How It Works and How to Build It
The architecture behind OpenAI, Google and Perplexity's research agents, explained by someone who built one. Code included.
Mar 25, 2025
•
Jai Juneja
3
2
February 2025
New beginnings
Let's get it started.
Feb 25, 2025
•
Jai Juneja
3
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts