What is applied AI?
Applied AI means using artificial intelligence to do real work — not studying models, but building with them. Here is what the term covers, why it matters more than the...
Emerging software and AI
Applied AI is the practice of using artificial intelligence models to solve real-world problems and build practical tools, rather than researching the models themselves. You can read my full definition of what applied AI is (and isn't) here, or browse my case studies, tools, and writing on the subject below.
Featured writing
OpenClaw: What It Is and Why It Matters for Serious AI Workflows
OpenClaw is an open source AI agent framework that runs on your own infrastructure. Here's what it actually does, how it's different from chatbot wrappers, and why I chose it...
Latest in Emerging software and AI
OpenCode let me switch models, but I wanted more control
OpenCode let me use MiniMax M2.7 for planning and a local Qwen3.5 27B model for overnight implementation. Human review found missed edge cases, but model choice alone did not...
OpenClaw's Dreaming: Background Memory Consolidation That Actually Works
OpenClaw's new dreaming system solves the memory management problem every AI agent practitioner faces, too much noise or too much loss. Here's how it works and why the three...
When Claude Code became useful enough to keep using
Claude Code did not make agentic coding useful because it produced one impressive answer. It made the same Sonnet workflow more predictable, with fewer mistakes and fewer...
Archive writing (10 items)
Why I could not fairly rank Codex, Copilot, and Claude
Codex CLI offered control, Copilot agent mode felt less inspectable, and Claude Code needed less rescue. I kept all three because different work and missing measurements made a...
The AI That Can Break Into Your Software Has Been Built. Here's What's Happening About It.
A company called Anthropic built the most powerful AI yet. It can find hidden doors in software everyone uses — your phone, your browser, your accounting tool. They've decided...
An Actress Built an AI Memory Tool. Here's Why It Might Actually Matter for Your Work.
Milla Jovovich, you know, the actress, has released an AI tool that's outperforming systems built by major tech companies. It could change how you use AI assistants for your...
What Claude Code taught me about agentic coding costs
Claude Code made sustained delegation practical, but not predictable in cost. Longer sessions, corrections, and manual context trimming pushed me to judge cost per accepted...
10 Real-World AI Use Cases for SMEs: Practical Solutions for Growth
Artificial Intelligence isn't just for tech giants. SMEs across the UK and EU are using AI to reduce costs, increase revenue, and improve customer experience often for less...
Save Time with ChatGPT: Practical AI Strategies for Busy Professionals and Business Owners
Struggling to keep up with your growing to do list? ChatGPT can help. This AI assistant handles routine writing, planning, and problem solving so you can focus on higher value...
10 Things Developers of All Skill Levels May Be Surprised to Learn About AI Coding Assistants
AI coding assistants are changing how developers work, but they come with surprising quirks and challenges. From context window limits to prompt engineering, this post covers...
Real-World AI Applications for UK Businesses: From Solopreneurs to Scaling Enterprises
AI isn't just for tech giants. UK businesses — from sole traders to 250 person companies — are using it right now to handle client proposals, manage inventory, automate...
Generative AI Predictions for 2025: Stay Ahead of the Curve
Generative AI is moving too fast for annual predictions to keep up — but here are 6 trends that will matter in 2025 regardless. Hyper specialised models, million token context...
Google Gemini 2.0: The Catalyst for Agentic Generative AI in Enterprises
Google's Gemini 2.0 handles text, images, and speech simultaneously, runs agentic tasks autonomously, and costs less to operate than GPU dependent alternatives. That...
