The Scenario to report on seat ownership. Each seat in the office building must be assigned to an organisational unit (OU). There is a list of all seats, and the owning OU should be set for each seat. But some seats don’t have an owning OU set. Therefore, they decided to assign all unassigned seats …
Automatically Assign a Category to Uncategorized Rows in Power Query and DAX Read More »
The European Commission’s latest draft guidelines provide much-needed clarity on how organizations should classify high-risk AI systems under Article 6 of the EU AI Act. However, they also raise an important question for enterprises: could your existing AI systems already be considered high-risk without you realizing it? The answer may depend on more …
Could Your AI Systems Already Be High-Risk Under the EU AI Act? Read More »
, I will give my first impressions of the newest OpenAI model, GPT-5.6. The model was released a few days ago, and I’ve gotten the chance to test it extensively since the release and compare it against other models such as GPT-5.5, Opus 4.8, and Fable 5. I’ll give my judgment on the model, share …
# Introduction Everyone is building agents. Far fewer people can explain, precisely, why their agent loops forever, ignores a tool it was given, or confidently reports success on a task it never finished. The gap between shipping an agent and understanding one is where these five resources live, and every one of them is completely …
a marketing mix model to a senior director. The slide showed two beta coefficients side by side: Linear TV at +2.4, Digital TV at +1.8. He nodded, satisfied. Then he asked the question I was dreading. “Let’s assume we run this with last week’s refreshed data. Same channels, same model, same everything, but one extra …
Why Your Betas Explode: The Hidden Geometry of Multicollinearity Read More »
# Introduction An agent that calls a cloud API for every decision is renting its intelligence. It needs a key, it racks up a bill per token, and every request leaves your machine before you get an answer back. An agent built to run locally skips all of that. No API key, no per-call cost …
7 Python Frameworks for Orchestrating Local AI Agents Read More »
In my latest post on structured outputs, the three main approaches for getting machine-readable responses from an LLM. Those are JSON Mode, Function Calling, and OpenAI’s Structured Outputs. If you haven’t read that post yet, it’s worth a quick read before this one, since we’ll be building directly on top of it. So, today, we’ll …
Pydantic + OpenAI: The Cleanest Way to Get Structured Outputs from LLMs Read More »
# Introduction SQL is still one of the most important skills for data analysts, data scientists, business intelligence analysts, and analytics engineers. But learning SQL syntax is only the first step. To stand out, you need to show that you can use SQL to solve real business problems. That is where portfolio projects help. A …
5 Real-World SQL Projects to Build Your Data Portfolio Read More »
I’ve worked on, conversation state tends to grow quickly over time. It’s common to resend large portions of the history on each turn—including older tool outputs, repeated RAG retrievals, and context that’s no longer relevant. As this accumulates, prompts can become significantly larger, which may increase inference cost and latency, and in some cases affect …
# Inroduction This article is part of my noob series where we write about the questions people Google most but may not understand well because of complex math and everything. So, if you are here, you might have heard fine-tuning somewhere in the context of large language models (LLMs) especially. This concept already existed in …
Fine-Tuning Explained for Noobs (How Pretrained Models Learn New Skills) Read More »
