Archive
AI
-
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…
-
Connect Claude to Revit Using PyRevit’s MCP Server
Model Context Protocol (MCP) is a standard way to give an AI assistant access to applications. In the context of Revit, I can have an LLM talk to Revit directly rather than building a Revit addin or macro. In this post, I’ll show you how to create a pipeline with three pieces: Claude → MCP…
-
Revit Macro First, Revit Addin Later
Add-ins are undeniably the gold standard for deploying scalable tools in Revit (yes, even better than Dynamo Player in most cases). But if your goal is rapid automation and getting things done ASAP, going straight to Add-in development can slow you down. Here’s how to start with a macro.
-
Give Your Windows Apps a Facelift With Our AI-Friendly WPF Theme
Let’s paint a familiar picture: you spin up a new WPF project, drop a basic Button onto your MainWindow, hit F5, and are instantly transported back to 2008. The default controls are, to put it mildly, visually offensive. Those harsh gray gradients, cramped borders, and rigid shapes make it painfully obvious you are building on…
-
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 Used AI to Downgrade a Revit Family From 2024 to 2022
What if Revit families were backwards compatible? Could we use AI and a little C# coding to force Revit 2024 to talk to Revit 2022?
-
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…
-
Decluttering Your Data: Why AI Alone Won’t Solve the Mess
Imagine your home is overflowing with clutter. You hire a professional organizer who tidies everything up—but without proper shelves and storage, the clean items just end up in a neat pile on the floor. That’s what happens when you rely solely on AI to clean up your asset data, especially when managing furniture, fixtures, and…
