Software, security & AI, built and delivered by one engineer.
Native C/C++ and Qt applications, COBOL modernization, production AI integration, and real-world security work. You hire me, you work with me. No project managers, no handoffs.
Work directly with me
Every project from first call to delivery. No middlemen.
Full source & docs
Complete source code and documentation handed over on delivery.
Scoped upfront
Fixed scope agreed before any work begins, so there are no surprises.
Post-delivery support
A bug-fix period included after every delivery.
What I Do
Hands-on services for businesses building serious software - custom development, legacy COBOL migration, AI integration, modern edge infrastructure, and real-world security work. Every engagement is delivered personally, with years of production experience behind it.
Latest Tech Tutorials and Insights
Stay up-to-date with my most recent blog posts, covering a wide range of topics in web development, programming, security, infrastructure, and artificial intelligence. Explore new techniques and stay ahead in the ever-evolving world of technology.
Build Voice Agents: OpenAI Realtime API Guide
Building low-latency audio pipelines with the OpenAI Realtime API lets developers launch human-like conversational voice agents in production. Traditionally, building a voice interface meant chaining three separate model layers: automatic speech recognition (ASR), a text-based LLM logic layer, and...
Claude Opus 4.8 vs. OpenAI GPT-5: Which API Is Best?
Choosing between the Claude Opus 4.8 vs OpenAI GPT-5 developer APIs is one of the first critical decisions for teams building enterprise AI applications in 2026. As organisations integrate Large Language Models (LLMs) into production codebases, the model provider you pick dictates your platform’s...
Claude Fable 5 Hybrid Reasoning: Thinking vs. Speed Modes
Anthropic’s new Claude Fable 5 reasoning engine keeps deep thinking switched on for every request and lets developers dial reasoning depth up or down instead. Historically, Large Language Models (LLMs) operated on fixed compute parameters, generating tokens at a uniform speed regardless of query...
How AI Search Engines Read Schema Markup and Structured Data
Implementing schema markup for LLMs is the most reliable way to feed structured data directly to conversational search engines. As Large Language Models (LLMs) take over standard web search queries, traditional keyword indexing is no longer enough to maintain digital visibility. AI search...
Optimizing for Google AI Overviews: A 2026 SEO Guide
Getting Google AI Overviews SEO right has quickly become essential for UK businesses that want to hold onto top search positions. Google’s Search Generative Experience (SGE) has transitioned into AI Overviews, placing synthesised summaries above traditional organic search listings. This pushes...
Optimize Your Website for ChatGPT Search and Perplexity
OpenAI and Perplexity are changing how users discover business platforms, and ChatGPT Search SEO is fast becoming as important as ranking on Google. These conversational engines do not display a traditional list of indexed links. Instead, they synthesise a single unified response and link to source...
Generative Engine Optimization: Future of SEO in 2026
Generative Engine Optimization is the next evolution of digital search strategy. As users migrate from keyword-based search queries to conversational AI interfaces, business owners must adapt how their platforms present information. AI search engines—such as Perplexity, ChatGPT Search, and Google...
Host a Static Web App on Cloudflare Pages: A 2026 Guide
Cloudflare Pages hosting lets frontend teams ship code that is fast, secure, and free of server administration. By using Cloudflare Pages , developers get a high-performance edge-native platform to deploy static web applications, single-page apps (SPAs), and server-side rendered (SSR) frameworks. By...
Building AI Agents With Cloudflare Workers and LangChain
Building a Cloudflare Workers AI agent is the next step in moving from simple AI prompts to autonomous workflows. These systems, known as AI agents, use Large Language Models (LLMs) to call external tools, make decisions, and execute tasks on their own. While running agents traditionally required...
Seeking Additional Resources or Collaboration?
Whether you need in-depth technical guidance, want to collaborate on a project, or have a challenge that requires expert input, I'd welcome the conversation. Let's discuss how I can help you achieve your goals.
Get in touch