← home
Topic

AI & LLMs in production

On building with LLMs where it counts, and where it breaks.

22 posts

2026

  1. How we use AI to write and review code without losing ownership
  2. What I'm watching in 2026: reasoning models, long-context, and the next shift

2025

  1. The agentic engineering loop
  2. Why I don't have a separate AI team
  3. Agentic workflows: the ones that work and the ones that blow up
  4. The Claude API in production: a working engineer's notes

2024

  1. Multi-agent systems: what actually works in production

2023

  1. AI-assisted sprint planning: the actual workflow
  2. Prompt engineering is engineering
  3. Benchmarks vs. production: why they tell you different things
  4. Why I switched from GPT-4 to Claude for internal tooling
  5. The compliance problem with LLMs
  6. AI-assisted code review: the system we built and what it actually catches
  7. LLMs as infrastructure, not features
  8. Six weeks of GPT-4 in our workflow: what changed and what didn't

2022

  1. ChatGPT launched. Here's what I actually think.

2020

  1. GPT-3 and the moment the ceiling got removed

2019

  1. Why most AI features in startup products are theater
  2. GPT-2 dropped. Here's what I think it means.

2018

  1. IBM Watson: the gap between the demo and the integration

2017

  1. The Gap Between "AI-Powered" and AI That Actually Works
  2. Azure Cognitive Services in 2017: An Honest Review From a Startup CTO