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 🙌

Most people use ChatGPT to write content from scratch every single time. That's the slow way. The faster play is to create one solid piece, then use ChatGPT to repurpose it into everything else. Here's the simple version. Start with your best asset — a blog post, a long email, a webinar transcript, even a detailed voice note you've transcribed. The key is that it already contains your real thinking, not a generic outline. Then work in passes. First pass: ask ChatGPT to pull out the five to seven core ideas as standalone points. Second pass: take each idea and ask for a short social post in your voice — this is where Custom Instructions earn their keep. Third pass: ask it to draft a follow-up email that ties two or three of those ideas together. The reason this works is that you're not asking ChatGPT to be original. You're asking it to reformat thinking that's already good — and that's the job it's genuinely reliable at. One caveat: always do a read-through before anything goes out. ChatGPT will occasionally flatten your sharpest line into something safe. Your edit is what keeps it sounding like you. Hope that helps. Jason 🙌

Most people open ChatGPT, fire off a prompt, get an OK answer, and move on. The thing that quietly separates the people getting incredible results from everyone else isn't a secret prompt — it's that they spent 5 minutes on Custom Instructions and never had to repeat themselves again. Custom Instructions sits in your settings. It's two text boxes ChatGPT reads silently before every reply, in every chat. Set it up once and the model already knows who you are and how you want to be answered. Here's the 5-minute setup that actually moves the needle: Box 1 — "What would you like ChatGPT to know about you?" Drop in three things: what you do, who you serve, and what you're working on right now. Example: "I run a SaaS business in customer support automation. My audience is small-business owners and marketing teams. I'm focused on growth and content right now." Skip hobbies and personal trivia — keep it work-focused. Box 2 — "How would you like ChatGPT to respond?" This is where most people leave money on the table. Tell it the tone, the format, and the things you don't want. Example: "Be direct and concise. Skip disclaimers and preambles. When I ask for copy, give me three variations. When I ask strategy questions, push back if my thinking is weak. Use plain English, not corporate-speak." Save it, open a new chat, ask the same question you've been asking for weeks. The difference is immediate. Two things to watch out for: don't stuff it with everything you can think of (the model weighs it heavier than you'd expect, and bloated instructions make answers worse not better), and revisit it every couple of months as your work shifts. What's in your Custom Instructions right now? Drop a line or two below — happy to suggest tweaks. Jason 🙌

OpenAI just released GPT-5.4… and it’s a pretty big step forward. If you’re using ChatGPT regularly, you’ll probably start noticing a few differences straight away. Here are a few highlights: 1. Much stronger at real workGPT-5.4 is designed for professional tasks like writing documents, building spreadsheets, analysing information, and producing structured outputs. In testing, it performed as well as or better than industry professionals in many knowledge-work tasks. 2. Better coding abilityIt now includes the coding strengths from the latest Codex models. That means stronger debugging, better code generation, and more reliable help when building apps, scripts, or automations. 3. Can work with tools and software more effectivelyOne of the biggest improvements is how it works with external tools, apps, and workflows. This is particularly important for AI agents that need to interact with websites, spreadsheets, APIs, and other systems. 4. Longer memory and contextThe model can handle extremely large inputs (up to 1 million tokens in some environments), which means it can process large documents, projects, or codebases much more effectively. 5. Better at searching the webGPT-5.4 is significantly stronger at deep research tasks where it needs to find and combine information from multiple sources. 6. Fewer factual mistakesOpenAI says responses are about 33% less likely to contain incorrect claims compared with the previous generation. What this means for us For most people in this community, the biggest benefits will be: • better prompts• more reliable outputs• stronger coding help • improved research• fewer hallucinations If you build workflows, automations, prompts, or AI tools, this release should make things noticeably smoother. Have you tried GPT-5.4 yet? What differences have you noticed so far? Chers Jason

How did everyone get on with ChatGPT over the last year? I’ve attached my stats, looks like use it a lot 😄