AI Agents for Real-Time IT Incident Response
In this guide, we’ll build two different AI approaches for real-time IT incident management, tools that can automatically analyze alerts, prioritize fixes, and recommend solutions during a system outage. We’ll compare two distinct styles for building AI Agents: We will use the Databricks Free Edition to implement one Python notebook for each case, leveraging one […]
The Red Team Mindset: Why You Should Attack Your Own AI
What’s a Red Team and why it matters Originating in military stress-testing, Red Teaming uses an “adversarial mindset” to find vulnerabilities that standard testing misses. While a Blue Team defends, the Red Team acts as the enemy to exploit weaknesses before a real adversary can. In the context of AI, this means moving beyond verifying […]
Choosing the Right LLM: A Decision Matrix
Posted by Tony S. in Machine-Learning on November 19, 2025
Introduction Choosing the right Large Language Model (LLM) can feel overwhelming. The landscape changes fast, model names blend together, and benchmark charts don’t always tell us what actually works for our use case. This guide will attempt to provide a simple, practical way to pick the right model without getting lost in technical hype. It […]
AI Engineering: A Practical Introduction
Posted by Tony S. in AI, data architecture, Machine-Learning on August 21, 2025
AI Engineering moves beyond training models. It’s the discipline of building robust production systems powered by foundation models. Introduction: What AI Engineering is and is not AI Engineering is not about training large models from scratch. Instead, it’s about building production systems on top of foundation models like GPT-4, Claude, and Llama. Traditional ML workflows […]
Absolute Zero: How AI is Learning without Data
Posted by Tony S. in AI, Machine-Learning on June 5, 2025
The Absolute Zero Reasoner (AZR) is a recent AI innovation that presents a new methodology for AI models to learn and reason. This method diverges from traditional AI learning approaches by enabling AI to learn from scratch, without the need for pre-existing human-provided data. This is a key point: It is given zero data and […]
Drift Detection in Large Language Models: A Practical Guide
Posted by Tony S. in AI, Machine-Learning on March 14, 2025
Introduction Basically, LLM drift happens when AI models start to lose their edge over time, and don’t perform as well. This is a real problem if we want them to keep working consistently in the real world. Types of Drift in LLMs Input Data Drift These are changes in the input data the model receives, […]
The LLM Project Lifecycle: A Practical Guide
Posted by Tony S. in AI, Machine-Learning on January 20, 2025
Executive Summary Large Language Models (LLMs) are revolutionizing how AI works across many fields. This guide will walk through the key steps of building an LLM project, using a customer support chatbot as an example. We’ll focus on: Along the way, we’ll discuss important things to consider and common mistakes to avoid. The diagram emphasizes […]
Deep Learning in Fraud detection: AutoML
Posted by Tony S. in AI, Machine-Learning on November 30, 2024
Last of Four: Deep Learning Basics for Engineers This is the final installment of a four-part series of self-contained articles on deep learning, using real-world examples. It’s aimed at engineers and techies who want to learn more about AI. We already covered the basics of machine learning in a previous series, but this one focuses […]
Deep Learning in Fraud detection: Graph Neural Networks
Posted by Tony S. in AI, Machine-Learning on November 30, 2024
Third of Four: Deep Learning Basics for Engineers This is part 3 of a four-part series of self-contained articles on deep learning, using real-world examples. It’s aimed at engineers and techies who want to learn more about AI. We already covered the basics of machine learning in a previous series, but this one focuses specifically […]
Deep Learning in Fraud detection: Hybrid models
Posted by Tony S. in AI, Machine-Learning on November 30, 2024
Second of Four: Deep Learning Basics for Engineers This is part 2 of a four-part series of self-contained articles on deep learning, using real-world examples. It’s aimed at engineers and techies who want to learn more about AI. We already covered the basics of machine learning in a previous series, but this one focuses specifically […]
Blog T 