Archive

Thoughts

  • Cross-Functional Data: MCP Servers vs. Standard APIs

    If you’re used to building apps by prompting, you’ve probably heard of the Model Context Protocol (MCP). It’s the magic bridge that lets your AI assistant actually do things like read your local files, browse a database, or trigger actions. It feels like an absolute superpower for open-ended tasks. But as more of us use…

    Cross-Functional Data: MCP Servers vs. Standard APIs
  • Are We Bragging About the Wrong Number?

    One question to ask yourself (and your team) should be, how much of your last 40M tokens produced code that’s still being used? Not code that got written. Code that survived. If you and your agent built a data layer, rewrote it, rewrote it again when feature three exposed a bad assumption, and shipped version…

    Are We Bragging About the Wrong Number?
  • The 100kb Parameter: An Extensible Way To Store BIM Data?

    Story time: I was working on developing a Revit addin for a client which required a JSON blob as an input (generated from another application). Of course the BIM manager in me immediately thought, “I’m going to need a ton of shared parameters for this data.” Then my developer brain questioned, “but wait, is there…

    The 100kb Parameter: An Extensible Way To Store BIM Data?
  • Dynamo vs Revit Macros

    I have an unpopular opinion, and if you are a BIM Manager, Computational Designer, or Revit power user, it might ruffle a few feathers: Revit macros are now significantly more powerful than Dynamo.

    Dynamo vs Revit Macros
  • How I Develop Apps On My Phone While Sitting in Manila Traffic

    Dev tools have officially gotten to the point where a mobile phone is now a legitimate place to ship code from. Not “read the code.” Not “approve a PR.” Actually implement a feature and have it live on your server two minutes later.

    How I Develop Apps On My Phone While Sitting in Manila Traffic
  • We Want Digital Perfection, but We’re Building with Analog Hands

    Let’s face it, we’re living in the future, right? We have self-driving cars (sort of), phones that can practically read our minds, and we’re sending rockets to Mars for fun. So why, oh why, are we still building things with paper plans and tape measures? Everyone in architecture, engineering, and construction (AEC) is buzzing about…

    We Want Digital Perfection, but We’re Building with Analog Hands
  • How I Used AI To Recreate The Iconic Structure in King’s Cross Station With A Revit Macro

    Here’s what happened when I challenged an AI to model the complex structure of King’s Cross Station in Revit. No Dynamo, just raw C# as a Revit macro.

    How I Used AI To Recreate The Iconic Structure in King’s Cross Station With A Revit Macro
  • Is Dynamo Dead? Here’s How AI is Bringing Revit Macros (C#) Back To The Forefront.

    With the emergence of AI as a coding partner, I’ve found myself leaning back into the Revit Macro Manager. The barrier to entry for text-based coding has nearly vanished, and the results are cleaner, faster, and more robust than anything I could “wire up” in Dynamo.

    Is Dynamo Dead? Here’s How AI is Bringing Revit Macros (C#) Back To The Forefront.
  • Common Construction-Phase Issues in Retail FF&E (and How to Mitigate Them) – Part Two

    Cost Overruns Budget overruns are a pervasive issue in construction, and retail store projects are no exception. Changes, delays, and misestimates during construction all compound to drive final costs above what was planned. Industry surveys consistently show a majority of projects go over budget. For example, one survey of real estate construction owners found 75%…

    Common Construction-Phase Issues in Retail FF&E (and How to Mitigate Them) – Part Two
  • Even AI Needs a Second Set of Eyes: How Ephany Uses Agentic AI to Double-Check Data

    Artificial intelligence might seem like magic, but even magic needs rules. One of the biggest misconceptions about AI is that it always gets things right. In reality, AI is only as useful as the data it works with. And when you’re managing complex asset catalogs across thousands of projects, bad data can snowball into real-world…

    Even AI Needs a Second Set of Eyes: How Ephany Uses Agentic AI to Double-Check Data