Writing
I use this section for case studies, postmortems, and technical notes from systems I have led, stabilized, or shaped through selective consulting.
Method
The unified perspective behind everything else: six principles, four playbooks.
Explicit Control Loops · Evidence First, Measure Before You Optimize · Warnings Over Errors, Graceful Degradation by Default · One Config, Many Surfaces · Contract-Driven Integration · GitOps as the Boring Substrate
AI-Assisted Dev Adoption Loop · AI Infrastructure Readiness Audit · Healthcare Integration Onboarding · Agent Rollout With Guardrails
Introducing AI-Assisted Dev to a New Team · Auditing and Stabilizing GPU Infrastructure · Healthcare Integration From Scratch · Rolling Out Production Agents
Every post and case study with its principle and playbook tags — filter by any of them.
Case Studies
Delivery write-ups with metrics, stack choices, and the tradeoffs that mattered.
Blog
Technical notes, incident lessons, and implementation patterns worth keeping.
Finding the Real Context Ceiling: Needle-Benchmarking Forced RoPE Extrapolation
A served model can load at 96K context and still be useless past 64K. Loading is not the same as staying coherent. Here is how we mapped the exact cliff with a progressive needle-in-haystack bench — and why the limit was the model, not the GPU.
The First 90 Days: Introducing AI-Assisted Dev to a New Team
How I would roll out AI-assisted development on a team that has not standardized: what to do in week one, what to earn the right to argue about later, and what almost always goes wrong.