Section

Articles

Longer pieces, each with an argument and a date. Every one is here to change what you do on Monday, and says so in its first paragraph.

  1. Software handover Accepting a handover How do you know a software handover is actually finished? Handovers are signed off when the documents arrive, which is the wrong moment. A handover is finished when the new team can answer the questions that matter without calling the old one. How to write those questions early, test the materials against them and use the overlap well.
  2. Developer dependency Dependency, measured How do you measure how much you depend on one developer? Dependency on a developer or an agency feels like a relationship and behaves like three lists: questions only one person can answer, accounts only one person holds, and changes only one person can judge. How to write them down, measure them in hours and shorten them without a conflict.
  3. Technical memory The second analysis Why is the second look at your system worth more than the first? One picture of a system is out of date by the next release. The difference between two pictures is what an owner can act on: what arrived, what changed, what went away, and which earlier answers no longer hold. How to read it and take it into a meeting.
  4. AI-built software A filter is not the architecture What role should a prompt injection filter play in a real system? A filter guesses from text, and language is too varied to guess right every time. What guardrails are good at, why a polite business letter gets through, the two errors that both cost money, a one-hour test with the filter switched off, and how to read a vendor claim.
  5. AI-built software Maturity levels How do you pick the next security step for your agents without doing everything at once? A backlog of forty security items has no order and no finish line. Five levels, from an experiment on a broad key to measured resilience, the evidence that proves each one, what triggers a move up, and why a level belongs to an agent and not to a company.
  6. Technical ownership What to pay for now Which security does a small company pay for now, and which can honestly wait? The question is not how much security to buy but how much damage is left once the basic limits are in place. Six cheap measures that are never postponed, the triggers that end a postponement, what a retrofit costs, and accepted risk on one page.
  7. AI-built software Not a chatbot any more When did your AI assistant stop being a chatbot? The same model is a low-risk adviser and a high-risk executor, and the difference is one connected tool. An inventory you can finish this week: what the agent may read, change, send and delete, and what each costs when it is wrong.
  8. Evidence and unknowns Breaking the cascade How does one small mistake reach five systems, and where do you break it? In a chain of automated steps, an uncertain output arrives at the next step as a trusted input. Chain depth, retry budgets, idempotency, a re-check of the critical fact before anything irreversible, and operations that can be compensated.
  9. Understanding without the code Where the model runs Does running the model yourself actually make it safer? Bringing a model in-house changes who controls the infrastructure and where data goes. It changes nothing about prompt injection, over-broad permissions or unsafe tools. Four questions that decide the choice, and the risks that survive it.
  10. AI-built software The blast radius How do you keep one wrong decision by an agent from becoming an incident? An agent is safe because of what your infrastructure physically lets it do, not because the model is good. What to bound: scope per object, a ceiling on volume, an expiry on every permission, confirmation before the irreversible, and a way back.
  11. Technical ownership Code is not the advantage Code stopped being the advantage. It did not stop being the constraint. Software is written faster than it has ever been, so the scarce thing moved. What an owner runs short of now is not engineering hours but a dependable answer to how their own system works. What that shortage costs, and how to end it.

How these are written

  • One transition per piece. Each article takes a reader from "this is probably a problem for somebody" to "this is a problem for me and here is the first thing I will do about it". If it cannot name that move, it does not get written.
  • The cost of waiting is made explicit, and only with things that can be checked: what accumulates, what it looks like in three months, what the next big change will make of it.
  • Every article ends in your hands, not in a warning. A sequence, a checklist or a way to test your own position, and a first step small enough to take today.
  • Every invented example says so. There are no customer stories here, because there are no customers to write about yet.
  • A date on every piece. An argument about a moving subject is read differently when you can see how old it is.

Find out what you actually own.

No repository access. No source-code upload. No card.

Build your project map — free