I doubt this is a brand new thought, but I figured I’d share it here since we’ve talked about project instructions quite a bit. I’m relaunching my blog and plan on using ChatGPT to write the articles. BUT I didn’t want information that isn’t mine in any of my posts. They’ll be my work, I’m just using AI to help with phrasing and so on. So I linked my project folders where I work on my content, linked my website, and gave specific instructions to only use info that I give and my sources. Once a detailed outline is set, it can suggest outside info and include links so I can verify it. Secondary sources are flagged as such and social media only info is also flagged. Then I opened a new chat in the project folder and asked ChatGPT to review the instructions for clarity and tell me its interpretation of them. After I reviewed that I asked for any suggested additions to the instructions. It had some great ones! After I reviewed it all, I asked for all suggestions to be listed together so I could copy and paste them. As a result, I have a VERY long set of instructions for my blog project folders that will help me and keep it authentically me!

OpenAI has released GPT-Live, a new generation of voice models that now powers ChatGPT Voice. It started rolling out globally yesterday across iOS, Android and the web. The headline change: it can listen and speak at the same time. Every previous version of Voice worked in turns. You talked, it waited for silence, then it answered. That is why it kept butting in when you paused to think, and why the whole thing felt a bit like a walkie talkie. GPT-Live processes what you say continuously, so you can interrupt it mid-sentence, pause to gather your thoughts without it jumping in, or tell it to stay quiet and just listen. It even gives the small acknowledgements a real person does, the odd "mhmm" so you know it is following. The second change is the one I think matters most for business use. When you ask for something that needs real work, a web search, proper reasoning, digging through a file, it hands that job to GPT-5.5 in the background and keeps the conversation going while it runs. You can also pick a reasoning level: Instant for quick answers, Medium or High when you want it to think harder before it speaks. A few practical details worth knowing. GPT-Live-1 becomes the default for paid plans, with a mini version as the default for free users. It can now show visual cards while you talk, things like weather, stocks and sports. It is better at ignoring background noise. And at launch it does not support video or screen sharing, so if you use those, the older voice modes are still available. Here is my take on why this deserves your attention. Voice has been the feature most business owners try once and quietly abandon, because talking to a turn-based bot feels like effort. The interesting shift is that voice can now hold a natural conversation while real work happens underneath it. That starts to look less like a gimmick and more like thinking out loud with an assistant. The obvious first test: next time you are driving or walking, talk through a business problem with it for ten minutes and see what you come back with.

One of the most common frustrations I see in here is that ChatGPT writes well, but it does not write like you. Everything comes out a bit polished and generic, and you end up rewriting half of it anyway. The fix is simpler than most people expect. Instead of describing your style in words, you show it. Grab three or four things you have already written that sound like you. Emails, posts, a page from your website, anything in your natural voice. Paste them in and give ChatGPT this job: "Study these samples and describe my writing style back to me. Cover tone, sentence length, how formal or casual I am, words and phrases I lean on, and how I open and close. Turn it into a short style brief I can reuse." Read what it gives you and correct anything that feels off. Now you have a style brief written in your own voice. From then on, you paste that brief at the top of any writing task: "Write this in the style described below," then the brief, then the task. The output lands much closer to how you actually sound, so you spend your time refining instead of rewriting from scratch. If you use Custom Instructions or a Project, drop the brief in there once and it applies automatically. Have you tried getting ChatGPT to match your voice yet? What has worked, and where does it still fall down? Drop it below.

A question I keep seeing from business owners here: should I build a Custom GPT, or is a good saved prompt enough? The honest answer is that most people reach for a Custom GPT too early, when a saved prompt would do the same job with a lot less faff. Here is the simple way to decide. Use a saved prompt when the task is a one-off shape you repeat. Things like "turn these notes into a follow-up email" or "summarise this article in five bullets". You paste the prompt, drop in your content, and you are done. Keep these in a notes file or a doc so you are not rewriting them from scratch every time. Build a Custom GPT when you need the same instructions, tone, and reference material applied again and again, especially if other people on your team will use it too. A Custom GPT lets you bake in the role, the rules, and any files it should always refer to. Good examples: a support assistant that already knows your refund policy, or one that writes in your brand voice every single time. Rough rule of thumb: if you would have to paste the same background into the chat more than a few times a week, it is worth turning into a Custom GPT. If not, a saved prompt is faster to set up and easier to tweak when you change your mind. What are you leaning on more right now, Custom GPTs or a prompt library?

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 🙌