Writing

My articles on enterprise AI development, agent reliability, evaluation, and model infrastructure, published in O’Reilly, Lenny’s Newsletter, and Substack.

Why I’m Leaving OpenAI and Lessons
September 28, 2026EssayKiriti Badam
What building Codex taught me about small teams, product intuition, and the work I want to take on next.
Agent-Native Infrastructure: APIs, Interfaces, and Authorization
September 18, 2026The Nuanced Perspective
Prahitha Movva, Aiza Hasib, and Kiriti Badam
What Would You Build With a Much Faster Classifier Model?
September 17, 2026Substack
Agent Skills Work but the Research Shows Most Teams Are Building Them Wrong
May 18, 2026O’Reilly
Evals Are NOT All You Need
January 28, 2026O’Reilly
Why your AI product needs a different development lifecycle
August 19, 2025Lenny’s Newsletter
MCP: Overhyped, Misunderstood, and Actually Useful
April 5, 2025Substack

Conversations

Why most AI products fail: Lessons from 50+ AI deployments at OpenAI, Google, and Amazon

January 11, 2026 · Lenny’s Podcast

Aishwarya Naresh Reganti and I joined Lenny Rachitsky to discuss building AI products, earning customer trust, and improving systems after deployment.

Mentions

Building Codex’s Slack integration

Slack customer story

Slack’s story on OpenAI quotes me about bringing Codex into the conversations where teams work.