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 »
Contents# Introduction# 1. Ollama# 2. Smolagents# 3. PydanticAI# 4. CrewAI# 5. AgentScope# 6. LangGraph# 7. Microsoft Agent Framework# Wrapping Up # 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 …
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 »
Contents# Introduction# 1. E-commerce Customer Churn Analysis Using SQL# 2. SQL Data Warehouse Project# 3. Sales Data Analysis Using SQL# 4. Bank Customer Segmentation Analysis# 5. Healthcare Data Analysis Using SQL# Final Thoughts # 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 …
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 …
Contents# Inroduction# What Is Pretraining?# What Is Fine-Tuning?# How Is Fine-Tuning Done?# Two Common Types of Fine-Tuning# Is Fine-Tuning Always the Answer?# Extra Resources # 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 …
Fine-Tuning Explained for Noobs (How Pretrained Models Learn New Skills) Read More »
latest wave of articles, opinion pieces, and forecasts from consultants and AI vendors, all confidently predicting the imminent takeover of human work by agentic AI, I recently found myself thinking about my first year at Imperial College London, back in 2009. Our lecturer for the introductory programming course would often tell us to sketch out …
Contents# Introduction# 1. Setting Up Your Environment and Loading the Data# 2. Getting the Baseline with df.describe()# 3. Pushing Pandas Further with include, .agg(), and groupby# 4. Getting a Richer Console Summary with skimpy# 5. Generating a Full Interactive Report with Profiling# 6. Building a Real “Table 1” with tableone# 7. Polishing It into a Publication-Quality Table with Great Tables# Tying It Together: …
7 Steps to Automating Descriptive Statistics with Python Read More »
Image by Pexels Coming out of the pandemic, statisticians have run into a slew of geo-political complications further augmenting the inability to forecast business variables with accuracy. Did Ukraine drive retail prices higher in 2022 or was it the quantitative easing in 2021 that was the culprit? Some models say one thing and some say …
Contents# Introduction# Orchestrating and Managing Multi-Agent Systems# Supervising Agents and Closing the Production Gap# Evaluating Models and Engineering Prompts# Governing and Regulating AI Systems# Interpreting Business Impact# Conclusion # Introduction Data scientists at companies running AI in production are spending more time on AI oversight and system supervision than on model construction. Job postings and salary data from 2025 and 2026 confirm …
Data Scientists Are Becoming AI Managers, Not Model Builders Read More »
