Posts
All the articles I've posted.
-
MCP a Year In: What Held Up, What Didn't
Sixteen months of building production systems on the Model Context Protocol. The interoperability bet paid off. Auth, versioning, and the demo-to-production gap are still where teams bleed.
-
Fine-Tuning Small Models in 2026: A Practical Pipeline
An end-to-end pipeline for fine-tuning a small model in 2026: distill the data, train adapters, hold an eval bar, ship behind a canary, and watch for the drift that quietly eats your accuracy.
-
Human-in-the-Loop Is a Design Problem, Not a Safety Net
Bolting a human approval step onto a badly designed agent does not make it safe. It makes a rubber stamp. The human-in-the-loop work is UX and architecture, not a checkbox.
-
The Cost of Agents: A FinOps Model for Token-Hungry Systems
An agent that loops and calls tools spends tokens like a single prompt never does. Here is the cost model that explains the bill, and the levers that cut it without making the agent dumber.