Practical write-ups on production AI: clinical data quality, RAG architecture and evaluation, enterprise AI agents, computer vision and AI infrastructure.
2026-08-26 · 14 min read · Computer Vision
A classifier tells you something is there. A detector tells you where. Neither alone is enough for clinical triage. Here is the two-stage chest X-ray pipeline I built, why the architecture is deliberately unfashionable, what the preprocessing actually contributes, and how to read the 96.93% accuracy and 99.71% AUC honestly.
2026-08-26 · 14 min read · Medical AI
A medical RAG assistant that answered fluently, cited real sources, and passed every informal check was missing half of all emergency cases. Here is the architecture, the evaluation harness that caught it, the actual bug, and what it cost to fix.
2026-08-26 · 16 min read · AI Engineering
Most AI agent architectures are designed for capability and then retrofitted for control, which is why so few reach production inside a real company. Here is what changes when an agent has to pass an audit — permissions, data boundaries, cost governance, human approval, and the evidence trail — and how to build for it from the start.
2026-08-26 · 18 min read · Medical AI
A medical AI model can score 96% on a held-out test set and still be unsafe in a hospital. The gap is almost never the architecture — it is the data. Here are the five data-quality failures that decide whether clinical AI survives contact with production, and how to catch each one before a patient does.
2026-08-26 · 15 min read · AI Engineering
The three ways to make a language model do what you want are constantly compared as if they were competitors. They solve different problems. Here is the decision rule, what each one actually costs, why most teams reach for fine-tuning when they needed retrieval, and how to tell which situation you are in.
2026-08-12 · 16 min read · AI Engineering
An AI agent demo takes a weekend. Making one safe to point at real users takes considerably longer. A practical guide to the five things that break — unbounded loops, bad tool design, context rot, prompt injection, and zero observability — and how to engineer around each.
2026-08-12 · 14 min read · AI Engineering
Most RAG systems are tested by asking them a few questions and reading the answers. That is not evaluation. Here is how to build a golden dataset, use an LLM as a judge without fooling yourself, and why aggregate accuracy hides the failures that matter most.
2026-07-29 · 14 min read · Infrastructure
A practical framework for choosing GPUs for internal AI infrastructure — from A100 and H100 to H200 and B200 — based on real workload, memory bandwidth, and company size, not just VRAM.