Agentic Practices insights https://agenticpractices.com/insights/ Practical writing on AI adoption for leadership teams: context, checking AI output, skills, agents, measurement and training whole teams on Claude Code. en-gb Sun, 08 Nov 2026 08:00:00 +0000 AI adoption after the licences: what leadership teams actually have to change https://agenticpractices.com/insights/ai-adoption-after-the-licences/ https://agenticpractices.com/insights/ai-adoption-after-the-licences/ Sun, 08 Nov 2026 08:00:00 +0000 AI adoption stalls when nothing changes after the licences are bought. Here is what leaders must change so engineering teams practise on their real work. Stephan Swart Why AI training works better with the whole team https://agenticpractices.com/insights/ai-training-whole-team/ https://agenticpractices.com/insights/ai-training-whole-team/ Sun, 08 Nov 2026 08:00:00 +0000 This guide to AI training for engineering managers explains why I train developers, testers, analysts, designers and product people together on one shared spec. Stephan Swart Can a non-developer use Claude Code? https://agenticpractices.com/insights/can-non-developers-use-claude-code/ https://agenticpractices.com/insights/can-non-developers-use-claude-code/ Sun, 08 Nov 2026 08:00:00 +0000 Claude Code for non-technical people starts with real work. See the tasks marketers, PMO, QA and admin staff brought to my training and where they got stuck. Stephan Swart Context matters: why more instructions can make AI output worse https://agenticpractices.com/insights/context-matters-claude-md/ https://agenticpractices.com/insights/context-matters-claude-md/ Sun, 08 Nov 2026 08:00:00 +0000 More instructions can make AI output worse. These CLAUDE.md best practices keep the file small, decide where knowledge lives and prove Claude is reading it. Stephan Swart How to check AI output before you trust it https://agenticpractices.com/insights/check-ai-output/ https://agenticpractices.com/insights/check-ai-output/ Sun, 08 Nov 2026 08:00:00 +0000 This is how to verify AI output without rereading every line. Keep review apart from verification, ask what proves the work, and automate the checks you repeat. Stephan Swart Turn repeated work into a reusable skill https://agenticpractices.com/insights/turn-repeated-work-into-a-skill/ https://agenticpractices.com/insights/turn-repeated-work-into-a-skill/ Sun, 08 Nov 2026 08:00:00 +0000 Claude skills for business turn repeated jobs into written procedures. Find the work you repeat, build from your own transcripts and judge any skill you borrow. Stephan Swart What can you safely let an AI agent run without you? https://agenticpractices.com/insights/what-ai-agents-can-run-without-you/ https://agenticpractices.com/insights/what-ai-agents-can-run-without-you/ Sun, 08 Nov 2026 08:00:00 +0000 AI agents for business owners can save time on the right jobs. Learn three tests a job must pass and what to know before an agent reads your email and files. Stephan Swart How to measure AI adoption in a software team https://agenticpractices.com/insights/measure-ai-adoption-software-teams/ https://agenticpractices.com/insights/measure-ai-adoption-software-teams/ Sun, 08 Nov 2026 08:00:00 +0000 Token counts and commit totals prove nothing about learning. This is how to measure AI adoption in software teams with situation questions and a baseline. Stephan Swart Coaching AI adoption from how your team actually uses it https://agenticpractices.com/insights/coaching-from-real-usage/ https://agenticpractices.com/insights/coaching-from-real-usage/ Sun, 08 Nov 2026 08:00:00 +0000 Surveys show what people believe they do. Claude Code usage analytics show what they actually do. I capture sessions with consent and coach the real gaps. Stephan Swart