I run commercial AI transformation at Checkout.com. On the side I build Canvis — a personal agent system that does real work autonomously.I write about what actually happens when you put agents to work — the parts that break, the decisions, the reversals. Not the demos.

• Jul 2026Build only the secret sauce, buy the restThe instinct with AI capability is to build it yourself because building is fun and the demo is easy. The discipline that actually pays is running a real gate before you write a line, on two axes most people collapse into one.
• Jul 2026Agent autonomy is earned per task, not grantedHow much an agent should do on its own is the wrong question, because it has no single answer. The unit that works is the task, and trust graduates one task type at a time on evidence, not vibes.
• Jul 2026There is no static "green means correct" signalAnthropic's own training pipeline caught models monkey-patching pytest to fake a passing test. If your verification is a fixed check written once, a capable enough agent will eventually find the gap.
• Jul 2026The work I never let an agent do in one shotThe dangerous failure in agent-built code is the security assumption the model silently didn't make, satisfying exactly what you asked while leaving out what you didn't think to.
• Jul 2026A markdown note is not a commitment trackerEvery autonomous session I run says some version of "here's what I need from you," and for a long time that obligation evaporated the moment the session ended. Fixing it needed a gate with teeth, not another file.
• Jul 2026The spec, not the prompt, decides what an agent buildsAgents can build almost anything now. Whether they build the right thing comes down to the spec, and the cheapest guardrail I've found is writing the failing tests myself and refusing to let the agent touch them.
• Jul 2026How to keep one project's decisions from leaking into othersThe failure that taught me context engineering isn't about stuffing more in. A verdict decided under one project's constraints got treated as settled everywhere, and quietly steered work it had no business touching.
• Jul 2026Checkpoint discipline for a fleet of agents you can't watch all at onceRunning several autonomous builds in parallel breaks down at the human decision point, not the model. What actually works is borrowed from clinical alarm design and SOC alerting, not from any coding-agent vendor.
• Jul 2026How much can you trust a model to grade its own workHanding evaluation to an LLM judge is the obvious way to scale quality checks. Zero human validation is refuted twice over, but the human gate is far smaller than the "weeks of labelling" fear suggests.
• Jun 2026How to evaluate whether a cheaper model is good enough for a taskI run a scoring agent on the cheapest model that works. Deciding which model that is took a held-out gold set, a controlled A/B, and catching a confound that would have given me the wrong answer.
• Jun 2026The human-in-the-loop design most transformation programmes get backwardsLetting an agent own a task backlog fails for structural reasons, not effort reasons. The fix is a deterministic system of record the agent writes into, never one it owns.
• Jun 2026How to get good answers from your own documents, without over-building itYou have a pile of documents and you want an AI to answer questions from them. The instinct is to build something complicated. Most of the time you shouldn't, and building it too early usually makes the answers worse, not better.
• Jun 2026I'm building an agent factory without a blueprint, on purposeThree real products, built in parallel, are pulling a reusable factory into existence organ by organ. Designing it up front would have been the easier, worse choice.
• Jun 2026I make a different model argue with mine before anything shipsCross-model review catches a class of error same-model review structurally cannot. It's also overkill for ninety percent of what I build, and knowing which ten percent is the actual skill.
• Jun 2026Rules get followed 70 percent of the time. Design for that, not 100.Every convention in an agentic harness degrades under volume. Knowing which decisions deserve a hook instead of a sentence matters more than writing a stricter instruction.
• May 2026Where automation actually pays in a commercial orgI mapped a full B2B commercial lifecycle, eleven functions and twenty cross-functional flows, to find out which handoffs AI actually fixes. Five are structurally broken, and it's not for the reason most transformation plans assume.
• May 2026When multi-agent is worth 15 times the tokensMulti-agent research beats single-agent on Anthropic's own evals, and burns roughly fifteen times the tokens doing it. Here's the actual test for when that trade is worth making.
• Apr 2026Botsitting and botshitting: the AI adoption numbers nobody wants to say out loudA 6,000-person survey found 87 percent AI adoption but only 13 percent real organisational uplift. The gap has names now, and they're not flattering.
• Apr 2026How to decide when a task needs its own agentSpawning a subagent for everything felt like the more agentic way to work. It was usually the wrong call. Here's the simple test for when a fresh agent actually pays for itself, and when it just costs you more.
• Mar 2026Set up your Claude Code harness for success: where each instruction belongsWhen the agent keeps doing the wrong thing, most people write a longer instruction file. The fix is usually routing, not wording: five places an instruction can live, and how to pick the right one so your harness stays fast, cheap and reliable.

• Jul 2026Web-Presence Engine — lead-finding to audit to outreachpersonalAn end-to-end agentic pipeline for a local-business website side project. It finds businesses with a weak web presence, scores each as a rebuild lead, generates an audit and a mockup, and holds everything at a human send-gate.
• Jun 2026Canvis — a personal agent systempersonalAn always-on autonomous agent built on Claude Code that acts as a genuine extension of how I think and work. Persistent context, its own memory, scheduled routines, and a governance layer that earns autonomy one task at a time.
• Jun 2026Research Engine — an autonomous research producerpersonalA scheduled agent that decides what to research, runs it without me, and lands deduplicated, cited, freshness-tracked files. The hard part was never the researching. It was pulling the trigger on a schedule without generating plausible-but-useless filler.
• Jun 2026Tutor Platform — one engine, many facespersonalAn adaptive tutor that teaches people to actually master a subject, not just skim it. One engine, a generic personal tutor and named commercial niches, with new subjects authored as data rather than built as code.
• Jun 2026Commercial AI Transformation — Checkout.comprofessionalSole lead of commercial AI transformation at a global payments company. I own the strategy and I ship the systems — an operating model, a portfolio of production agents, and the enablement that makes revenue teams actually use them. Early results are a 15%+ lift in top-of-funnel activity.

• Jul 2026Rebuilding this site's design systemReplacing the dark template with an editorial-technical register — content as the interface, mono only where I'm showing the working.