Contents# Introduction# Prerequisites# Workflow 1: Automated Exploratory Data Analysis Agent# Workflow 2: Agentic Feature Engineering and Selection# Workflow 3: Agentic Hyperparameter Optimization# Workflow 4: Automated Model Monitoring and Drift Detection Agent# Workflow 5: Agentic Pipeline Orchestration and Self-Healing# Wrapping Up # Introduction  The average data scientist spends roughly 45% of their working time on data preparation and cleaning, not on modeling, not on …

5 Agentic Workflows to Automate Your Data Science Pipeline Read More »

cut their AI inference bill by more than half last quarter. Eight weeks of clean engineering work. It was the win the engineering team had been chasing all year. It was also the wrong optimization. Three months later, customer satisfaction was dropping, churn was ticking up, and the cost savings were structurally tied to the …

We Built a Routing Layer to Cut Our AI Costs. It Broke the Product. Read More »

  Contents# Fine-Tuning Language Models on Apple Silicon with MLX# Understanding Why MLX Suits Apple Silicon# Setting Up Your Environment# Preparing Your Dataset# Training Your First LoRA Adapter# Choosing a Base Model and Adapter Settings# Reducing Memory Use with Quantization# Testing and Generating with Your Adapter# Fusing and Serving the Model# Wrapping Up # Fine-Tuning Language Models on Apple Silicon with MLX  Fine-tuning a language model …

Fine-tuning Language Models on Apple Silicon with MLX Read More »

Making computer use safe in 3.5 Flash To mitigate some of the prompt injection risks for agents operating in live environments, we use targeted adversarial training for computer use in Gemini 3.5 Flash. We’re also releasing two optional enterprise safeguard systems that enable enterprises to: Require explicit user confirmation for sensitive or irreversible actions. Automatically …

Introducing computer use in Gemini 3.5 Flash Read More »

All code used in this article is available on GitHub. The business logic and modeling functions are located in the src/selection directory, specifically in the following file: src/modeling/score_computation.py The corresponding analysis and results are documented in: 09_score_computation.qmd The images, tables, and charts were generated with the help of the Codex coding assistant. , your credit score follows you …

How to Build a Credit Scoring Grid From a Logistic Regression Model Read More »

  Contents# Introduction# 1. Qwen3.6 27B MTP# 2. Gemma 4 31B IT QAT# 3. DiffusionGemma 26B A4B# 4. Nemotron Cascade 2 30B A3B# 5. Qwen3.5 9B MTP# 6. EXAONE 4.5 33B# 7. North Mini Code 1.0# Final Thoughts # Introduction  Local coding models are finally getting serious. I have been a big fan of this new wave of local large language models (LLMs), especially the …

Top 7 Coding Models You Can Run Locally in 2026 Read More »

my series on Outlier Detection. In this article, we look at working with categorical data.  Generally when performing outlier detection with tabular data, we start by converting the data so that it is either entirely categorical or entirely numeric. There are some exceptions, but for the most part this is necessary: most outlier detection algorithms …

Encoding Categorical Data for Outlier Detection Read More »

  Contents# Introduction# Setting Up the Dataset# 1. Measuring Time Between Events with LAG()# 2. Comparing a Row to Other Rows in the Same Table with a Self-Join# 3. Selecting the Top Row per Group with ROW_NUMBER()# 4. Segmenting Customers by Spend with NTILE(n)# 5. Smoothing Noisy Data with a Rolling Window# 6. Aggregating Conditionally with FILTER# 7. Detecting Consecutive Activity Streaks with Window …

Practical SQL Tricks Every Data Scientist Should Know Read More »

ContentsIntroductionBarrier 1 | Context and failure recallBarrier 2 | Elastic infrastructureBarrier 3 | Operational Agents and Quality DataBarrier 4 | Git for DataBarrier 5 | Pervasion through the industryBarrier 6 | Agent Sandboxes and New OrchestratorsBarrier 7 | Standards for Proxy Servers and Agent DefinitionPutting it all together | A Single Pane of Glass for AI Introduction , AI examples …

7 Crucial Barriers Between Data Teams and Self-Healing Data Architecture Read More »

  Contents# Introduction# What Is a Loss Function?# Mean Squared Error# Mean Absolute Error# Cross-Entropy Loss# Loss vs. Accuracy# The Training Loop# Final Thoughts # Introduction  I know that when beginners start learning machine learning, things seem easy at first. You follow a tutorial that asks you to load a dataset, train a model, and then you see something like this: loss = “mse” …

Loss Function Explained For Noobs (How Models Know They Are Wrong) Read More »