Most prompting advice tells you to write the perfect instruction up front. For everyday business tasks, I think that's backwards. You're guessing at what matters before you've really thought it through, and you end up with a vague answer because you handed it a vague brief. Here's a simpler move: tell ChatGPT to interview you first. Instead of asking for the finished thing, add one line to your prompt: "Before you answer, ask me up to five questions that would help you give a better response." Now ChatGPT does the hard part. It surfaces the gaps: who the audience is, what the goal is, what tone you want, what you've already tried. Then you just answer in plain language. The final output gets built on real context instead of assumptions. This works best on the messy, higher-stakes stuff: a sales email, an awkward client reply, pricing for a new offer, a job description. Anything where the quality depends on details only you know. Two tips. Cap the questions. Five is plenty, or it spirals. And if a question doesn't matter, just say "skip that one." You're steering, not filling in a form. It feels slower for about ten seconds. Then the answer comes back sharper than anything a one-shot prompt would have produced. What's the last thing you asked ChatGPT for that came back generic? That's exactly the kind of task to try this on. Drop it below. Jason 🙌

I've been playing around with it today, and so far I quite like it. It's actually based on the Chromium browser, so it won't feel altogether too unfamiliar if you've been using Chrome. It's been quite helpful having ChatGPT in the sidebar and also having the agent be able to interact with whatever website you're on, perhaps to carry out some searches or create some summaries and things. I haven't found anything groundbreaking so far, and it always feels weird changing from a browser you have used for years, but I can see it becoming very useful the more I discover how to get the best from it. If you've given it a try, let me know what you think below! Cheers Jason

I’ve just uploaded a new video where I test out the brand-new Synthesia v3, and it’s easily the biggest update I’ve seen from them yet. This version isn’t just about talking avatars anymore — you can now build interactive AI agents that actually move, gesture, and react naturally. The realism has taken a big leap forward… the hand movements, body language, and eye contact all feel much more lifelike. In the video, I go through how you can: ✅ Create your own AI avatar just by describing it – background, outfit, the lot ✅ Use the new Copilot editor that helps you write, visualise, and brand your videos automatically ✅ Add interactive features like quizzes, feedback, and call scheduling directly inside your videos ✅ Translate your videos instantly into multiple languages while keeping your original voice and perfect lip sync ✅ Build full training courses or onboarding videos with live stats and branded avatars It’s honestly a huge time-saver if you create content for training, marketing, or SaaS like I do. I also show how I’m planning to use it myself to reach a global audience with FastBots. 🎥 Watch the Synthesia v3 demo here Let me know in the comments how you’d use this kind of AI avatar tech in your business or content — I’m curious to hear your thoughts and ideas 👇 Cheers Jason