Articles

Dynamically updating infographics and content (so you don't have to)

I built a statistics site where every number updates itself. The harder half turned out to be the prose - so a Claude routine now reads the site against its data every morning. Here's how the whole thing works, and the patterns you can take for your own site.

· claude-code · Automation

The parts Shopify Plus B2B doesn't do (and how we built them)

Shopify Plus does more B2B than most people think - right up until a customer sits on two catalogues and their negotiated volume pricing disappears. I put an industrial hardware distributor's ERP pricing live on it, with one first-party app and nothing extra to host. Here's what native covers, and what I had to build.

· Automation · shopify-plus

vLLM settings for a pair of RTX 4090s: the flags I run for twelve local models, and why

The flag-by-flag vLLM settings page for a dual-4090 rig: the baseline every preset shares, the six flags that change per model, the rig discipline you set once, and one verified launch block for each of twelve open-weight models with the reason attached.

· local-llm · vllm

The 26%: what the companies actually making money from AI do differently

Google Cloud surveyed 2,403 executives and found a 26% cohort whose AI returns are accelerating year on year - and BCG independently landed on the same number. Meanwhile MIT says 95% of pilots die. Both are true, and the difference between the two groups is where they aim the technology, not how much they spend on it.

Which AI model pitches the best content ideas?

Content Marketing Ideas lets you choose which AI does the thinking. I ran the same brief through all eight models: how the pitches differ, which are worth the wait, and why the free ones are slow.

· Local LLMs · content marketing

The VRAM traps: why a 16GB model wouldn't load on a 48GB card

A 16GB model would not load on my 48GB card, and the reason was a shortfall of one kilobyte in a memory no spec sheet mentions. These are the fit traps a VRAM figure will never warn you about.

· local-llm · vllm

The Dual-4090 96GB vLLM Benchmark & Runbook

Can a £6,200 modified Ada rig match enterprise MoE throughput? The living measurement record for a dual RTX 4090 48GB vLLM rig - every number measured here.

The broken rules of local LLM inference

I used to lock the clocks on my mining GPUs. The same instinct just helped kill five rules of local LLM inference on a £6,200, 96GB rig.

· local-llm · vllm

How to Stop MCP Servers Eating Your PC: One Docker Gateway for Every Claude Client

My MCP list grew until orphaned node.exe were quietly eating a 128GB workstation by mid-afternoon. Here's how I put every server behind one Docker gateway - node on bare metal gone, secrets in one gitignored file, and a single URL every Claude client points at. One evening's work you'll feel every day after.

· Claude · mcp

How to Use the Gemini API (and Why I Run It Next to Claude)

Get a Gemini API key, make your first call in curl and Python, dodge the thinking-token trap that returns an empty answer, and see why running Gemini next to Claude is the real unlock. Written from production - and the bills.

· Claude · mcp

Which AI is right for your job? ChatGPT, Claude, Gemini and Copilot, task by task

Everyone's talking about AI assistants - ChatGPT, Claude, Gemini, Copilot - and if you've a real job to get through, you mostly want to know one thing: which of them will build Monday's deck, sort the badly-exported spreadsheet, write up the meeting, and clear the inbox? Here's the answer, task by task.

· Claude · gemini

Muse Glimmer 30B vs qwen: my day-one local benchmark on a dual RTX 4090 rig

Meta dropped Muse Glimmer 30B and I spent the day trying to unseat my qwen daily driver on the dual-4090 rig. Four apparent hangs, one day-one bug, and a same-harness bench later, I had my answer - and it wasn't the coronation I'd half expected. So, is it better than my daily driver?

· gpu · hardware

How to Plan and Begin Your First AI-Assisted Coding Session

You don't need to know how to code to build something with AI - but the calm ten minutes you spend planning before you start is what keeps your first session from spiralling. Here's the whole thing, gently: what the tools are in 2026, how to plan, and exactly what your first session looks like.

· claude-code · AI coding

How to Write a PRD an AI Can Build From (with a template)

A PRD is the difference between an AI coding tool that guesses and one that builds the thing you meant. Here's what a PRD is, a copyable seven-part template, a worked example, and the two lines that do most of the work - written for the era where the thing reading your spec is an agent, not just your engineering team.

· claude-code · PRD

How I work with Claude Code: PRD to deploy

I write the PRD, we agree an execution plan, pick the environment, get the keys out of the way, prototype, then test. Six steps, same order every time. Here's the real workflow with the files from two things I've shipped, and which model I hand each job to.

· claude-code · mcp

The best local coding setup isn't one model: how I route across Claude, Kimi and my own rig

The question I get asked is which local model is best for coding. Wrong question. The setup that works routes three tiers - Claude reasons, Kimi builds, and a Qwen coder on my own rig does the volume for nothing. Here's the whole thing, wired up.

· claude-code · local-llm

How to set up vLLM in Docker on Windows (WSL2): serve an open-weight model on your own GPU

vLLM doesn't run on Windows natively, so this is the Docker Desktop and WSL2 route my rig has served on since July: the compose file, the image pin that stops it upgrading itself, the walls WSL2 puts in your way, and how the settings were found, with Claude writing the test harness.

· local-llm · vllm

Moving houtini-lm to vLLM: What I learned

I decommissioned Hopper (my local LLM bootstrapped server) and moved my local models to a two-card 4090 rig with vLLM on Docker. It's so much faster - but houtini-lm spat its dummy. Two bugs, one hiding behind the other, and how v3.2.1 fixes it.

· claude-code · mcp

From Chat to Deploy: How to Fully Understand Claude, AI Assistants and Claude Code

I started in the chat box like everyone else. Three years later the boring parts of my work run themselves, from PRD to deploy. This is the ladder, stage by stage, with a starter task for each rung.

· Claude · claude-code

How to Do a Technical SEO Audit with Claude

A free, step-by-step technical SEO audit with Claude: your Search Console history and a first-party crawl merged in one local database, ranked by recoverable clicks - the Screaming Frog alternative you run by conversation.

· mcp · claude-desktop

Best GPUs for Running Local LLMs (2026): VRAM, Bandwidth & Picks

In today's guide, we're picking the best GPUs for running local LLMs - why memory bandwidth beats FLOPS, why VRAM decides everything, what I'd buy at each budget from the used RTX 3090 to my own pair of modded 48GB 4090s, the PCIe lanes a second card needs on a gaming board, and a calculator to check whether your model fits.

· local-llm · gpu

Claude Desktop System Requirements (2026): Minimum & Recommended Specs

Claude Desktop was my introduction to AI and it's still the best on-ramp to useful AI at work, so in today's guide I'm taking the system-requirements question the way I'd answer it for a client: the official minimums, the September change that moved Cowork into the cloud, what still runs on your machine, and why the laptop you own is probably fine.

· mcp · system-requirements

Claude Code System Requirements (2026): Specs, Setup, Gotchas

In today's guide, we're setting up Claude Code on Mac, Windows and Linux in the forms it now ships in: the terminal CLI, the Code tab in the Claude Desktop app, and the VS Code and Cursor extension. The published spec, the install routes Anthropic recommends, Fable 5.1 on every paid plan, and why the machine matters less than the way you work.

· claude-code · cli