Deep dives on building production data pipelines, cloud warehouses and analytics systems: the decisions, trade-offs and numbers behind real engineering work.
A robot-arm benchmark found GPT-6 Astra refused 2 of 100 hazardous instructions. The same gap applies to any LLM agent with write access to your data.
Why LLM features fail in production when the demo worked: messy real inputs, queues that starve each other, and failures that never raise an alarm.
A practical AI cost optimization guide from a real build: how task-based model routing cut one platform's AI spend by 99%, and trims most LLM bills 30 to 50%.
Occasional write-ups from real AWS data work: what the bill actually did, what broke, and how long it took. No roundups, no thought leadership. Unsubscribe whenever.
Whether that is ongoing technical ownership, one independent read on a problem, or someone to run the project. Let's scope it — I reply within one business day.