Oct 28, 2026 | Newsletters
📊 “Experts have many advantages. They are better able to see through LLM errors and hallucinations; they are better judges of AI output in their area of interest; they are better able to instruct the AI to do the required job; and they have the opportunity for more trial and error. That lets them unlock the latent expertise within LLMs in ways that others could not.” – Ethan Mollick Hello Reader, The next time you don’t like the results from your AI, use this Expert Feedback prompt: Review…
Oct 21, 2026 | Newsletters
🎓 “The basic DNA of good learning experiences is trying to do something and getting feedback.” – Julie Dirksen Hello Reader, Coaching is a meta-skill that unlocks any other skill. If you’ve never been in my Ai104 workshop, Coaching with AI, I am going to be teaching an interactive workshop this week for the AI Practitioners Summit, called Create an AI Coach to Learn Anything. This will teach you practical techniques that you can use immediately for learning, reflection, and growth. Create an…
Oct 14, 2026 | Newsletters
🧭 “The purpose of meetings is not to talk – the purpose of meetings is to arrive at ideas, solutions, plans, and decisions.” – Alexander Kjerulf Hello Reader, I have tried all the AI meeting notetakers over the past few years. Fireflies, Otter, Fathom, Monologue, and more have all had a turn in my systems. Traditionally, I give them a month or two, and get dissatisfied at some feature or annoying user friction – until six months ago. I found Granola. (Disclaimer: by clicking my affiliate…
Oct 7, 2026 | Newsletters
⏩ “If you want to go fast, go alone. If you want to go far, go together.” – African proverb Hello Reader, An AI Working Group ships projects. Tools are changing faster than humans can keep up. Most teams and organisations are throwing Copilot or Claude licenses to their crew, with a quick ‘good luck!’ and maybe an inscrutable warning about token counts. Making mistakes can be costly, when you rely on a paycheck. There isn’t a structure for risk-taking or innovation with AI in corporate teams,…
Sep 30, 2026 | Newsletters
🏎️ “AI agents don’t have a speed limit, but the person managing them still does.” – Kieran Klaasen Hello Reader, The fastest way to build a disappointing AI agent is to begin with a vague, grand ambition. “Handle my marketing for me.” “Run all our customer service.” “Become my chief of staff.” Those are only aspirations, not workflows. An agent cannot reliably operate within a fog bank. A useful agent starts with clear goals: Turn this meeting transcript into decisions, owners, deadlines, and…
Sep 24, 2026 | Newsletters
📊 “Context engineering is the strategic process of selecting, packaging, and managing the most relevant information for each step.” – Antonio Gullí Hello Reader, In July 2025, Gartner told AI leaders that “context engineering is in, and prompt engineering is out.” The past year, people on the bleeding edge of AI have been paying attention to framing. 💡 Context engineering prepares everything prior to the prompt. Even the best prompts will fail without the right context. Giving AI backstory…
