Skip to main content

Writing

Notes on AI, agents, web technologies, and building with LLMs

Technical articles on building with LLMs: agents and agent harnesses, MCP, evaluation, and the web technologies underneath. Worked examples with code, written for working developers.

  1. 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.

    InteractiveLLMAI
  2. Routing: Building Step-by-Step AI Reasoning

    Explore how to intelligently route AI queries using schema-guided function calling and contextual categorisation.

    InteractiveAgentic AI
  3. Prompt Chaining: Building Step-by-Step AI Reasoning

    Learn how prompt chaining enables AI to tackle complex tasks through step-by-step reasoning, boosting both accuracy and interpretability.

    InteractiveAgentic AI
  4. LCP and low-entropy images

    In this article we take a look at how to see if an image has low-entropy for LCP calculation.

  5. Compare how different image formats load on the web

    WebP, AVIF, JPEG XL, Progressive JPEG - how do these image formats compare in terms of their load speeds and how can we measure it? In this article we review a small app that gives us a visual answer.

  6. Google Chrome introduces a new Performance Insights panel

    A new performance insight panel has been added to Chrome which helps with tracking down performance bottlenecks in a much easier fashion compared to the classic performance panel

  7. call vs apply vs bind

    In this article we take a look at the differences between call(), apply() and bind().

  8. contains vs includes

    This article explains the two, often mixed-up, contains and includes methods.

  9. slice vs splice

    This article explains the two, often mixed-up, slice and splice methods.

  10. AVIF - Another Video based Image Format

    In this article we take a look at AVIF - a next generation image format that was first introduced by Netflix and it promises optimised performance over the widely used and popular JPEG.