The Sequential Agent Pattern
Chaining multiple specialised agents into a pipeline where each one builds on the last. Illustrated with a TypeScript CLI that fetches a quote, researches its author, and writes an inspiration card.
The Parallel Agent Pattern
When agents do not depend on each other, run them at the same time. Illustrated with a TypeScript translation pipeline built with Google ADK that translates a phrase into three languages simultaneously, then aggregates the results with Gemini.
The Single Agent Pattern
A look at the simplest agentic AI pattern: one model, one tool, zero orchestration. Illustrated with a tiny TypeScript agent built with the Google Agent Development Kit (ADK) that uses Gemini and Google Maps to review any place by name.
Watch the Past Move: Animating Historic Photos with Gemini and Veo
What if you could take a dusty old black-and-white photograph and watch it come to life? In this post, I walk through a Node.js pipeline that colorises historic photos with Gemini and then animates them into video using Veo 3.1.
Building a Historical Time Machine with Gemini and Google Maps
Have you ever wondered what your favourite landmark looked like a hundred years ago? In this post, I walk you through a Node.js application that generates historically accurate photographs of any real-world location at any point in time, and even checks its own work for anachronisms.
Why How You Split Your Documents Matters More Than You Think
Before you reach for a more powerful embedding model or a larger context window, look at what you're actually feeding into a RAG pipeline. Sometimes the highest-leverage improvement isn't a better model but rather it's a better split.
Filesystem as Context: Building an AI Detective with bash-tool
Instead of stuffing documents into prompts, give your AI agent a filesystem and let it retrieve its own context. Here's how, using a murder mystery detective as the demo.
The Mind's Eye - Engineering a CLI for Intelligent AI Interaction
This article concludes the series by showing how a deliberately designed CLI becomes a powerful interaction layer, giving users precise control over an AI system's conversational context, short-term memory, and long-term semantic knowledge.
The Autonomous Brain - Engineering AI for Continuous Learning and Memory Enrichment
This piece introduces background processors as autonomous AI agents that summarise conversations and extract critical facts to continuously enrich Long-Term Semantic Memory. By running asynchronously and optimising token usage, these processors enable a self-improving, increasingly personalised AI system that learns from every interaction.
The 'Aha!' Moment - Engineering the Perfect Prompt for Truly Contextual AI
In this article, we show how dynamic prompt engineering—via a `SessionManager` that intelligently layers short-term context, long-term semantic memory, and system instructions turns stateless LLM calls into genuinely contextual and personalised conversations.
Semantic Horizons - Engineering an AI's Enduring Long-Term Memory
In this article, we explain how Long-Term Semantic Memory uses vector embeddings and semantic search to give AI meaningful, persistent memory across conversations.
Building AI Agents with Google ADK: A Practical Guide
Learn how to build multi-agent systems with vector search, tool orchestration, and semantic understanding using Google's Agent Development Kit (JS/TS version).
The Token Economy - Engineering an AI's Working Memory
In this article, we explore how Short-Term Conversational Memory creates the illusion of memory in otherwise stateless LLMs through careful context persistence and structured prompt reconstruction. We also show how token limits, cost, and context degradation are managed using asynchronous, AI-driven summarisation that preserves meaning while keeping conversations efficient and coherent.
The Grand Orchestration - Engineering a Dual-Memory AI for Enduring Conversations
This article explains why LLMs often forget earlier messages and how naive full-history prompting is costly and inefficient. It introduces a dual-memory architecture: a short-term store for immediate conversation flow and a long-term semantic store for durable knowledge across sessions. Together, these systems let an AI maintain coherent dialogue without overloading the context window or budget.
Detecting Hallucinations in Language Models with Natural Language Inference
A practical look at why hallucinations occur in modern language models, why current evaluation methods make them persist, and how to detect them using Natural Language Inference in JavaScript.
The Importance of Precise Function Declarations for LLMs
This article explores how clearly defined functions enable large language models to make accurate tool calls, emphasising the importance of precision and developer intent in the function calling process.
Creating an MCP Client: Connecting LLMs to the Real World
In this article, we walk through the process of building a Model Context Protocol (MCP) client. Learn how to connect to servers, discover tools, and invoke them from your own app or LLM integration.
MCP Servers - The Bridge Between LLMs and Real-World Tools
Model Context Protocol (MCP) servers expose tools, resources, and prompts to LLMs in a unified, structured way. This post explores how they work, how to build one, and why they are a critical part of the future AI stack.
Filling in the Blanks: Teaching AI to Inpaint
A hands-on guide for exploring how to train a simple AI model using TensorFlow.js to inpaint missing parts of images - without needing large datasets or prior machine learning experience.
How Transformers and LLMs Actually Work - A Developer's Guide with Code
A hands-on walkthrough for web developers to demystify large language models by actually building a mini Transformer from scratch.