Chain AI models from different vendors to catch blind spots
Don’t run AI models in parallel. Chain them in series, across vendors. The output of one becomes the input to a critique from another. Different training data means different blind spots.
Don’t run everything in one chat session
Running multiple topic-based chat sessions in parallel beats one monolithic chat. Tighter focus, faster context, easier to review weeks later.
VS Code for everything that isn’t code
I use VS Code as a personal productivity environment, not a coding tool. Customer notes, briefings, emails, research, diaries, presentations, planning. Almost no actual code. This is the first post in a series writing down the setup.
The Impact of Primary Keys on DAX Query Performance in Power BI
When writing DAX queries, performance tuning often comes down to small design decisions that have big consequences. One such decision is whether to include Primary Key columns from Dimension tables in your SUMMARIZECOLUMNS statements. This is particularly important when those Dimension tables use DUAL or IMPORT storage modes. This article explains why doing so can … Continue reading The Impact of Primary Keys on DAX Query Performance in Power BI