Enterprise AI Engineering
I write and speak about how enterprise AI gets built.
The work starts below the application surface. I use this model to explain the infrastructure, runtimes, and control layers that make AI usable in production.
Ideas
Start here.
Begin with the core framework, then explore recent essays, build notes, and security briefs on the systems that make enterprise AI work in production.
ChatGPT Astra vs Claude Fable 5.1: They're Not Competing Anymore
Astra and Fable 5.1 have diverged so fundamentally that comparing them on benchmarks misses the point - route by workload, not leaderboard.
Read the pieceRecent writing
Recent essays, frameworks, and operating notes from the archive.
Stop Hiring AI Engineers. Design Your AI Team First.
CTOs who hire AI talent without a structural blueprint waste 6-12 months on misaligned teams that can't ship to production.
AI Engineer Career Path: 5 Skills You Actually Need in 2025
The five skills required for an AI engineer career form a dependency stack, not a checklist, and skipping a layer breaks everything above it.
AI Agent Hallucinations: A Practitioner's Guide to Detection and Fixes
Agent hallucinations are systematic failures with structure, and structure means you can build specific guardrails, evaluation pipelines, and fixes against them.
Context Layer for AI Agents: The Architecture That Makes Agents Useful
The context layer is the architectural component that separates production AI agents from stateless chatbots, and it deserves more engineering effort than model selection.
Watch
Video briefings and walkthroughs.
Architecture explainers, stack walkthroughs, and shorter briefings on what changes when AI moves into enterprise operations.
0:00 Featured briefing
Why Does AI Need to Talk to Other Tools? | Tutorial Ch.1
Recent briefings
Talks that extend the written work, not duplicate it.
About
Built across enterprise systems, data platforms, and applied AI.
Technical enough for architects and engineers. Clear enough for executive teams making operating bets.
I work where implementation detail meets business consequence: the infrastructure, runtimes, and operating patterns that make enterprise AI usable outside the demo.
The throughline is consistent. Identity, governance, integration, data platforms, runtime design, and execution all have to hold before AI becomes operationally real.