Why You're Burning Tokens in Three Turns
Operators on X keep saying they're four turns into an AI session and the context window's full. The replies miss the actual problem — they've been taught the wrong physics.
The Art of Reduction
"The more you add, the more you're taking away. Know when you need to stop."
A working document. Not a portfolio, not a blog. Practitioner notes from inside.
One operator. One codebase. One operating system that boots in seconds and maintains state across sessions. 26 years of digital craft compressed into infrastructure that makes a solo practitioner move at the speed of a team.
This is the practice of building with AI from the inside. Not tips. Not tutorials. The actual work — documented as it happens, proven by the commit history, refined by the corrections.
The model is a commodity. The situation is the edge.
Start here
Latest Writing
Working notes and the daily argument: @tonycooperuk →
The Nest, Not the Magpie
This morning I read thirteen open-source repositories and pulled seven patterns worth borrowing — in one session. The lesson wasn't that borrowing is free. It's that the haul is a function of the substrate you've built, not the source you took it from.
Context Discipline Is the Skill
Every few weeks someone on X burns through their AI allowance in two turns and blames the model. The model is fine. They're paying for synthesis they could have externalised — and context discipline is the entire skill.
The API Without a Front End
Government departments are funded to collect data, not to present it. The gap between what the state holds and what an ordinary person can use is structural, durable, and almost entirely unclaimed.
The API Selection Pressure
Suppliers with APIs get wired into the pipeline. Suppliers still emailing CSV files get checked when someone remembers. Not preference. Physics.
The Imperial Rise of the Context Engineer
Prompt engineering is the wrong name. Context engineering — what I've been calling ingeniculture for a year — is the practice of building the room the LLM stands in.
Why Your AI Workflow Produces Fluent Nonsense
Most AI workflows are prompts applied to empty rooms. This is what an operating system looks like instead — document tiers, named characters, a wiki the model can read, and a boot sequence that loads context before the first prompt arrives.
Who Is Holding the Mirror?
The AI reflects whatever substrate it meets. The dangerous case isn't where it refuses to answer. It's where it answers fluently and nobody in the room can tell it's wrong.
The Digital Trail That Speaks For Itself
Every profession that charges for opaque expertise is about to discover the trail was always there. AI doesn't invent evidence — it surfaces what's already readable. The age of 'we did the work, trust us' is ending.
Does Your Website Pass the Grep Test?
I'd never heard of grep and I've been building websites for twenty-six years. It turns out the simplest operation in computing — searching your own content — is the one most platforms make impossible.
The LLM Test: Who Does the LLM Think You Are?
I fed the same article to four frontier AI models. Three returned confident summaries — of articles I hadn't written. They didn't misread the content. They didn't know who I was. The insight that survived had vocabulary with no escape route.