Topics
Methodology
All articles on Methodology, newest first.
Transparency: I have revised all articles afterwards with the help of AI and translated them from German with its help. The ideas, experience and positions are my own. The audio versions of the German originals are read by a synthetic voice.
Interim Review and System View: Taking Stock of the Series
Months after the conversation where it all began, it’s time for an honest assessment: which expectations from the opening came true, which didn’t, what remains open – and why the most exciting question is no longer what the models can do, but what organizations make of it.
Claims: Small, Sourced, Verifiable
Claims break wiki pages down into individual statements with subject, predicate, object, confidence, status and a verbatim quote as evidence. This makes agreement and disagreement precise.
From Org Chart to Product Ownership
AI makes the path from customer problem to impact more continuous.
2026 9
2026 9
- llms.txt: Docs for MachinesContext for models, not for ranking: why llms.txt and llms-full.txt help coding agents – and what an MCP server makes of them.SoftwareAIMethodology
- Tools That Hold Up: Concepts, Methods, ProcessesYou cannot install an agent for your own domain – but you can very well learn the way there. Which concepts hold up, which methods keep the start small and which processes keep rules from going stale.SoftwareAIMethodologyDelivery
- AI Agents per Domain: Rules, Approvals and EvidenceHow an AI agent enforces domain rules across several tool calls: with case state, checked plans, approvals and traceable execution.SoftwareAIMethodologyDelivery
- Agent, Model, DomainThe model is rented, the agent can be under your own control – what matters is whether the domain lives as prose in the prompt or as a checked interface in the agent.SoftwareAIMethodologyDelivery
- Knowledge That Survives the SessionSession knowledge evaporates when no one curates it – why teams should treat their AI working knowledge like code, and why it’s not the model that gets smarter but the organization that learns.SoftwareAIMethodologyDelivery
- Clean Grounding II: Grounding AnswersMy working model for grounding distinguishes conventions, documents and API descriptions. What stays in the scarce context, I prioritize by task and by the cost of fetching it again.SoftwareAIMethodologyDelivery
- Clean Grounding I: Why AI Guesses So ConvincinglyWhy language models invent plausible things, why more training doesn’t reliably eliminate the problem and what grounding has to do with it.SoftwareAIMethodologyDelivery
- My Success Cannot Be CopiedA colleague takes over my AI setup and gets different results. Tools, tests and conventions can be transferred; how you cut tasks, how you review and the course of an individual session only to a limited degree.SoftwareAIMethodologyDelivery
- What I Am Critical OfFour observations and one open hypothesis after intense months with AI – from a possible loss of skills to the worry about more uniform solutions, and my practical countermeasures.SoftwareAIMethodology
2025 2
2025 2
- Good Enough: The Model Is Rarely the BottleneckFor the everyday tasks I work on with AI myself, the choice of model is rarely the first bottleneck. How the task is cut, the context and the verification usually matter more.SoftwareAIMethodology
- From Tool to Way of WorkingHow a conversation in Berlin, after more than thirty years of software craftsmanship, got me working daily with Claude, ChatGPT and Claude Code – and why I still distrust my own enthusiasm for now.SoftwareAIMethodology