Skip to the writing

Writing

Notes from getting agents past the demo.

Frameworks, primers and field notes on building agent systems that hold up in production, and on proving to somebody else that they do. Written for the people who have to sign off.

Published

Primer / Aug 2026

A data science mindset for agentic assurance

Trust the distribution, not the demo. The four foundations in one place, and the six habits they add up to: golden sets, pass^k against pass@k, grading abstention, verification in the harness, failure review and version pinning. Read → Framework / Jul 2026

Agentic AI Assurance

Testing, ownership and governance for agent systems. A practical framework for deciding what to test, who tests it, and when, across bespoke builds, Foundry and Databricks, Copilot Studio and Agentforce. Eight assurance domains, four platform archetypes, three risk tiers, five lifecycle gates. Read → Primer / Jun 2026

Can a reasoning agent be trusted?

Published research shows that a model’s stated reasoning often leaves out what really drove its answer. What that means if you were planning to audit an agent by reading its chain of thought. Read → Primer / May 2026

What we mean when we say hallucination

Not a bug you patch. It comes out of the way prediction works, and our own scoring keeps it alive. That is why groundedness can be measured, and why “stop hallucinating” is not a requirement anyone can test. Read → Primer / Apr 2026

How a language model actually predicts

Next-token prediction in plain terms, what the context window really is, and why both of those change the tests you should be writing. Read →

The series, in order

Four primers on the science underneath the systems. Enough about how a model works to give you a feel for where an agent will break, without having to read a paper. Each one stands alone, but they were written to be read in this order.