Writing
Writing on AI systems and production engineering
Practical writing on building AI systems that work at scale — retrieval quality, observability, access control, and the delivery problems most tutorials skip.
January 22, 2025
Evaluating retrieval quality when the corpus won’t sit still
How we measure retrieval quality across offline harnesses, production sampling, and observability pipelines when documents change daily.
January 18, 2025
LLM IAM patterns for agentic teams
A field guide for propagating identity, enforcing least privilege, and keeping audit trails intact inside modern agentic stacks.
January 12, 2025
Production RAG checklist for leaders who need measurable answers
A pragmatic checklist for shipping retrieval-augmented generation systems that auditors, analysts, and operations teams can trust.
January 5, 2025
Why agentic applications fail before they ever see production
The most common failure patterns we see when teams ship AI agents without IAM, retrieval evaluation, or observability baked in from day zero.
Ready to talk?
If you're dealing with a specific problem — or you're not sure yet whether what you're building is going to hold up — I'm happy to spend 30 minutes on a call to find out.
No sales process. Just a conversation.