05 / writing
Notes on AI adoption, Microsoft 365, and building operations software. Nothing gets published unless I'd want to read it twice.
The fastest way to tell whether an AI purchase will produce value is to ask what it replaces. If nothing stops, nothing changed, and you bought a subscription.
A reconciliation engine that actually works is a pipeline, not a chat window. Four phases, and a structured three-part prompt, replace a single request asking AI to do everything at once.
Enterprise buyers don't just want the right answer. They want to know why the system believed it, and what it does when it isn't sure. That distinction is what makes an AI system explainable rather than merely accurate.
Security teams need to know exactly how sensitive data is handled before they'll approve an AI system. The right architecture and a phased rollout plan are what actually get this approved and trusted by the operations team.
Reconciliation rarely fails loudly. It fails in micro-discrepancies too small to catch alone and too numerous to ignore together, and the real cost isn't the errors, it's what your best people aren't doing instead.
Not every reconciliation task is a good candidate for AI. The most successful enterprise systems split the workload explicitly, using AI where judgment is needed and deterministic code where certainty is required.
IT has spent a decade trying to automate reconciliation, and it stalls in one of two predictable ways. Understanding both failures is what points to the actual fix.
Skip the prompt libraries. Office work runs on five repeatable patterns, and knowing them beats memorizing prompts you’ll never look up under deadline.
If an AI rollout is running in your organization right now, one question tells you whether it will still exist in six months. Ask it before your first meeting today.
A perfect preview box is why broken LinkedIn links go unnoticed, by you and by the AI systems reading your content. Three ten-second checks that catch it first.
Copilot solves real problems for operations teams. It also gets credit for problems it can't touch. A framework for when to stay, extend, or build.
Unglamorous, high-frequency, genuinely shippable. Five operations workflows where AI works today, with what each replaces, what it needs, and the effort in weeks.
The actual stack and workflow I use to take an AI product from idea to production. What each stage is for, where the handoffs happen, and what breaks.
The license fee is the smallest number in a failed AI pilot. The real math: staff hours, opportunity cost, and the credibility you don't get back.
Most AI pilots don't fail on technology. They fail because the team bought a tool when the job was changing a workflow. Three questions fix that.
A plain-English guide to Intelligent Document Processing: how AI reads documents, how it differs from OCR, and what it delivers for operations teams.
What this section is for and what to expect from it.