Field notes from the engineering floor
How we build AI and software inside real operations: what works, what fails, and the evidence behind each claim.
In Dynodoc, history is a product feature
Why personal drafts, stable identity, and deliberate merging belong in a document workspace. What Dynodoc implements today, and where the limits remain.
Engineering essay · Retrieval systemsWhy enterprise RAG fails quietly, and what to design instead
Bigger context windows did not fix it. The failures sit in versions, permissions and evaluation, and the research from 2024 to 2026 shows where each fix belongs.
Engineering essay · Compliance automationHow to build audit-ready AI systems for regulated workflows
Tamper-evident logs, pinned replays, evidence chains, and the evidence contract you agree with your auditor before launch. Revised for the EU AI Act's new high-risk dates.
Engineering guide · Human-in-the-loopHuman-in-the-loop approval that isn’t a rubber stamp
Putting a person between an AI system and its actions does not make it safe on its own. What the research on automation bias shows, and how to design routing, evidence and feedback so the review step catches errors.