enterprise ai · platform engineering · devops
I write about enterprise AI, platform engineering, and DevOps — practical lessons from taking real projects through architecture review, security assessment, and into production.
Read the blog About me// latest
LLMs pick libraries by remembering, not evaluating: frozen favourites, hallucinated packages, vulnerable version pins. Where the risk comes from and the guardrails that work.
2026-07-18 · 07 Mins read
On September 8, 2025, someone phished the maintainer of chalk and debug, two of the most downloaded packages on npm. The malicious versions were live for about two hours before they were pulled. In th
read more
I've now written two articles arguing that data organizations need an Internal Developer Platform: one on why the layer is missing, one on the organizational forces that kill it after you build it. Bo
read more
In a previous article I argued that most data organizations have a platform but no developer experience on top of it, and that an Internal Developer Platform (a self-service layer of templates, golden
read more
Your organization spent millions on Databricks, Snowflake, or a carefully assembled stack of Azure services. Leadership declared the data platform "modern." And yet, every time a data team needs to bu
read more
As I work with teams deploying chatbots in enterprise settings, I've noticed a recurring pattern: people consistently underestimate what's involved. They see the chat interface — a text box, some resp
read moreNew posts, no algorithm — subscribe via RSS.
rss.xml