How to kill your SaaS: what we learned replacing a $43K/yr tool with AI agents
Source
youtube.com
Author
Latent Space
Date
Why it matters
Shows how top builders divided work between Claude Code and Codex to clone a $43K/yr SaaS, and why an LLM-as-judgeUsing one model to score another's output against a rubric, so quality can be measured at a scale human grading cannot reach.Full definition → misranked the human-preferred winner. Useful evidence on AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →-built software and on evaluating it.
Terms in this piece · Glossary
LLM-as-judge — Using one model to score another's output against a rubric, so quality can be measured at a scale human grading cannot reach.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
videoWorld Models & General Intuition: Khosla's largest bet since LLMs & OpenAI
videoExtreme Harness Engineering: 1M LOC, 1B toks/day, 0% human code or review — Ryan Lopopolo, OpenAI
videoInside Abridge: The AI Listening to 100 Million Doctor Visits — Abridge's Janie Lee & Chai Asawa
videoExo: Harnesses should see their own code and logs — Alex Krentsel, UC Berekeley / Google Research
