The Hollowing Has Already Happened Let's be honest: most enterprise "data science" in 2026 is really just pattern matching with extra steps. The craft isn't dying - it died while everyone was busy getting certificates. Five years ago, a data scientist needed to understand
The Multi-Million Dollar Spreadsheet Problem Every enterprise has them: isolated teams building their own data fiefdoms. Marketing tracks customers one way, Sales another. Finance maintains their "source of truth" Excel sheets. Data Science builds models on exported snapshots. Each group swears their numbers are right. The real cost
The Press Release Version Every Fortune 500 CEO is touting their "AI transformation." Press releases trumpet large language models analyzing customer data, autonomous agents handling support tickets, and machine learning optimizing supply chains. The keynotes are full of demos showing AI perfectly executing complex workflows. The Reality Inside
The Observability Crisis: Why Your AI Agent Is a Production Nightmare You're Pretending Is Innovation I've seen your future, and it's a cascade of silent failures wrapped in venture capital and self-congratulation. Right now, thousands of "AI agents" are shipping to production
We built the highway before inventing brakes Every major enterprise right now is scaling AI infrastructure — compute, multi-model orchestration, data centers drinking billions of gallons of water — while systematically ignoring the one thing that would make any of it deployable: a reliability layer. We have no standard way to know
The Illusion of Progress — Where Pilot Purgatory Lives Enterprise AI strategies often look like expensive charades. Companies chase the latest models, throw money at consultants, and launch pilots. But over 95% of these pilots never reach production. The problem isn't the model's accuracy — it's
AI Isn't Replacing Your Job. It's Revealing Which Ones Were Already Redundant. This isn't about faster models. It’s about consolidating data, tagging, and governance at scale so pilots actually become durable business value—and yes, your big-company constraints aren’t barriers, they’re
The New AI Strategy for Enterprises: Treating It as a Consultants’ Jobs Program This post argues that in large organizations the AI push is too often a consultant-led revenue stream rather than a durable capability. Real value comes from consolidating data governance, context, and ownership; otherwise pilots drift and budgets
The inconvenient truth nobody in your all-hands is saying Every major tech company right now is racing to deploy AI. They're hiring prompt engineers, standing up LLM platforms, demoing copilots to the board. And underneath all of it sits five years of technical debt, seventeen different data pipelines
The bottleneck isn't your model Most AI pilots die in the gap between a promising demo and production value. The culprit isn't the algorithm — it's the data underneath it. Missing contracts, broken lineage, dashboards that measure activity instead of outcomes. Governance is the product
News
This is Hey Mullett!, a brand new site by Bracey that's just getting started. Things will be up and running here shortly, but you can subscribe in the meantime if you'd like to stay up to date and receive emails when new content is published!