Blog

Thoughts on Python, Agentic Systems, AI Projects, and Web Development.

• Lesson 1: LLMs Are Not Functions (And Why That Changes Everything)
  2025-12-14

  My first real AI engineering lesson: large language models are not functions. They're probabilistic generators — and unless you constrain them, they will break your system.

• How to Architect a Real AI Application in 2025
  2025-12-11

  Everyone builds AI demos. Here's how to build production-grade AI systems with layers, tools, memory, observability, and fault tolerance.

• AI Agents Under the Hood: What They Actually Do (Not the Hype Version)
  2025-12-11

  Everyone talks about AI agents. Few understand how they work. Here's a developer-first breakdown of tools, loops, memory, state, and why most agents explode at 2am.

• Vector Embeddings: The AI Superpower Every Developer Should Understand
  2025-12-11

  Embeddings are the quiet engine behind RAG, search, similarity, memory, clustering, and half the AI tools you use. Here's how they really work.

• How LLMs Actually Work: The Mental Model Every AI Developer Needs
  2025-12-11

  Forget the mystical hype. Here's a blunt, developer-friendly explanation of how transformers think, plan, and hallucinate.

• The Birth of Bob + Chad: My Local Agentic Coding Environment
  2025-11-29

  I built a self-improving AI pair-programming system that runs locally, fixes its own code, and evolves over time.

• Making Virtual Environments Invisible: How I Stopped Fighting Python
  2025-11-29

  Switching venvs is annoying. Here’s how I made it automatic, effortless, and impossible to mess up — even across multiple projects.

• GhostFrog: Building a Data-Driven eBay Arbitrage Engine
  2025-11-27

  I built a full pipeline that scrapes eBay listings, classifies products, calculates ROI, and sends alerts.

• Building AI Tools to Help People Land UK Civil Service Roles
  2025-11-25

  I built a STAR interview generator, a CV matcher, and a downloadable Flask app to help candidates succeed.

• Building My Python + Flask Portfolio While Learning Publicly
  2025-11-24

  I built my portfolio by stacking real tools, not tutorial projects. Everything deployed, everything usable.

• Learning AI Engineering by Doing: My 6-Month Journey
  2025-11-20

  I stopped reading tutorials and started building real systems — and the results changed everything.

• What Are Agentic Systems? A Clear Explanation for Developers
  2025-11-18

  A simple explanation of what 'agents' really are, how they work, and why they're different from normal LLM chatbots.

• What Is Retrieval-Augmented Generation (RAG)? A Practical Breakdown
  2025-11-16

  RAG is one of the most important AI patterns. Here’s the clearest, no-nonsense explanation of how it works.

• The Planner–Executor Pattern in AI: Explained Simply
  2025-11-15

  The core design that powers modern agent systems, including my own Bob + Chad setup.

• Understanding Vector Embeddings (The Real Way)
  2025-11-14

  A simple mental model for embeddings that actually makes sense without maths.

• LLM Studio: What It Is and Whether You Actually Need It
  2025-11-12

  Everyone on YouTube is talking about LLM Studio. Here’s what it actually does, what it doesn’t do, and when you should skip it.

• LangChain: Great Idea, Terrible Reputation — Here’s Why
  2025-11-11

  LangChain exploded in popularity, then the dev community turned on it. Here’s exactly what happened and when you should or shouldn’t use it.

• LlamaIndex: The RAG Framework That Actually Makes Sense
  2025-11-10

  If you need a structured way to build retrieval systems, LlamaIndex is the cleanest option right now. Here’s why.

• Weights & Biases: Why Serious AI Builders Use It
  2025-11-09

  W&B is the secret weapon behind proper training runs, experiments, and model evaluation. Here’s what it does.

• Why Not Just Use X? The Truth About AI SaaS Tools
  2025-11-08

  From Jasper.ai to Notion AI to Flowise to LM Studio — everyone asks ‘why not just use a tool?’ Here’s the honest answer.