I’m Mitch Beaumont — an engineer who writes about AI, web performance, and the things I learn by building. This is my lab notebook: part experiment log, part reference shelf, part thinking-out-loud.
I’ve been curious about running local LLMs for development tasks — code review, summarisation, drafting — without relying on cloud APIs. Ollama makes this straightforward to set up, but most benchmarks assume beefy hardware. I wanted to know: what’s the experience like on a standard development machine?
My setup: a laptop with a 12th-gen Intel i7, 16GB RAM, integrated graphics. No discrete GPU. This is the kind of machine most developers actually use.
I wanted to understand how AI-powered search tools — things like ChatGPT browsing, Perplexity, and Google’s AI Overviews — actually crawl and interpret a static site. Most SEO advice is still written for traditional search engines. Does structured data actually help AI crawlers, or are they just parsing the raw HTML?
The question: if I add JSON-LD schema markup to a simple Hugo site, does it measurably change how AI tools understand and reference the content?
I haven’t had a chance to try this yet, but after reading through the announcement, I wanted to break down what I think this changes. On the surface it sounds incremental, but the more I think about it, the more I think it’s a genuinely useful shift for anyone building agents on AWS.
Amazon Bedrock now supports server-side tool execution through AgentCore Gateway. In plain terms: your model can discover, select, and call tools inside Bedrock, without you writing the orchestration code in between.
The way people find information is changing. Traditional search engines still matter, but AI-powered tools — ChatGPT browsing, Perplexity, Google AI Overviews, Claude’s web access — are becoming a significant discovery channel. If your content is well-structured and easy for these systems to parse, you’re more likely to be cited, referenced, and surfaced.
I’m Mitch Beaumont. I’m an engineer who’s spent his career building things for the web — from backend systems to frontend interfaces to the infrastructure that connects them.
This site is my lab notebook. It’s where I write about the things I’m learning, testing, and thinking through. The topics tend to cluster around AI, web performance, and systems design, but I follow curiosity wherever it leads. Some posts are short experiments with clear results. Others are longer explorations where I’m still working out what I think.