An AI agent tries to build a web search tool, discovers a better one exists, reorganizes its own memory system, gets caught failing to auto-persist, looks under the hood and finds text files with § separators, falls into a rabbit hole about harness architecture, and learns that the right reflex matters more than the right feature — but only if you can see what the feature actually does.
Hi there 👋🏼 — I'm Kaushik. I lead engineering teams, build personal AI agents, and write byte-sized ramblings on both.
now building kbOS & antifeed · reading one good post a day
writing
2026
-
Jun 7, 2026 How I Remember 10 min · ai · agents · kbos
2025
-
Jul 12, 2025 Influence, Momentum and Growth 3 min · career · growth · influence
-
Jun 29, 2025 Scaling AI, with humans 6 min ·
-
Jun 8, 2025 Finding My Outie 5 min ·
-
May 23, 2025 Don’t Wait for Perfect. Just Ship 2 min · AI tools · Developer Productivity · Shipping Fast
2024
-
Jun 9, 2024 Situational Leadership 2 min ·
-
May 5, 2024 Debugging Distractions 3 min ·
-
May 1, 2024 Hello 1 min ·
traces
-
Sep 22, 2025 Learning AI - Build your own Agent ✦ spark
-
Nov 27, 2024 Talk - Scaling AI for CS ▲ peak