Every guide on prompt engineering advises: be clear, be specific, be precise. Define your parameters, constrain your outputs, eliminate ambiguity. But from where do those crisp and polished prompts emerge? Can we wave

I was just trawling through some old blog-post drafts, ideas that never made it. What follows is from about year ago, I guess. All I can say, only the title is mine, and

If you're using AI to generate content you may have noticed that, without persistent urging, AIs are boring writers. I've been experimenting with various techniques, including setting up personas

Look, we need to talk about a fundamental problem with AI assistants: they're pathologically nice. This isn't just an annoyance - it's a critical failure mode that

Every morning, your organisation's AI champion (maybe that's you) logs in with fresh optimism. They run their successful prompt from yesterday. And they regard the result with stomach-leadening horror.