Category: AI in Production
Practical lessons from shipping AI systems — not theory, not demos. RAG, agents, prompt engineering, and production failures worth learning from.
How I Think About Context Windows in Production LLM Apps
Every token you send to an LLM costs money, adds latency, and past a threshold, degrades quality. Here’s how I manage context windows in production — and why bigger isn’t better.
I Built Conversational AI in 2017 — Here’s What I’d Do Differently with LLMs
built production conversational AI in 2017 using Rasa, spaCy, and hand-coded dialogue flows. Here’s what broke, what held up, and what I’d do differently with LLMs today.
LLM Output Validation in Production: What Actually Works
Raw LLM output breaks production systems in ways that have nothing to do with hallucination. Here’s the validation stack that actually works.
What Rasa Production NLP Taught Me That LLMs Still Can’t Replace
I built production NLP systems with Rasa before LLMs changed everything. The constraints Rasa imposed — on intent design, training data, and dialogue control — still apply today.
Prompt Engineering Is Not a Skill. It’s a Process.
Most teams treat prompt engineering as a creative act. It’s not. Here’s the repeatable process I use to version, test, and improve LLM prompts in production.
What I Learned the First Time I Ran an LLM in Production
The first time I ran an LLM in production, nothing worked the way I expected. Here’s what actually surprised me.