ChatGPT Usage Tips

The other day I built a 10-person AI team… trained on my voice, aligned to my workflows, and operational in under 60 minutes. Version 2.0 of my AI team. Not hypothetically. Not someday. Now. As a senior executive working across corporate strategy, business development, workplace transformation, real estate, hospitality, and the future of work, I’ve spent years helping organizations evolve. But this time, I applied that same thinking to myself. Here’s what I did: I started by feeding my entire ChatGPT history through two of the most advanced research papers on AI prompting: • Google’s Prompt Engineering Guide • USC’s study on LLM Debugging & Prompt Design Together with ChatGPT, I: • Benchmarked every prompt I’ve ever written • Surface structural weaknesses and overused prompt patterns • Automatically design prompt engineering mitigations • Identify my 10 highest-leverage use cases • And turn each into a fully formed custom GPT assistant. The result? A personal, role-based AI system that includes: • A strategist who builds operating models for distributed work • A speechwriter fluent in simplifying complexity with clarity • A brand voice expert with calm emotional resonance • A hospitality-driven real estate strategist • A deck designer with a storyteller’s eye • A senior leadership coach on modern leadership • A trend analyst filtering signal from noise • A self-audit GPT that challenges me weekly • …and more Each one trained on how I think. How I work. How I lead. Why this matters: This isn’t “using AI.” It’s working with AI ecosystems, modular, contextual, and aligned with the reality of executive leadership. It’s not about automating tasks. It’s about amplifying judgment and me. And here’s the real unlock: Every single person in your organization could do the same. From ICs (individual contributors) to team leads to the boardroom. This is how we unlock exponential leverage. Not by giving everyone one assistant. But by helping them build ten. Each one smarter than the last. Each one aligned to how they actually operate. This has to be a social, curious, and individual journey before any corporate AI strategy will give massive ROI. This is no longer theory. This is a prototype for the future of leadership infrastructure. And I built it. In an hour. (Psst, and I can talk to them, writing is a bottle neck sometimes) #FutureOfWork

Cyrus Shepard (16+ years experience, former head of SEO at Moz) just revealed that AI optimization now makes up 30% of his consulting work. That was 0% in January. By December, he expects 70 to 80%. Here is the full playbook he is using with clients right now: 1. Audit your content by type E-commerce and service content is holding strong. Informational blog content is getting destroyed. Cyrus says if AI can write the article without proprietary knowledge, that is the content seeing declines. Sort your site into three buckets: • Transactional (product pages, services) safe • Informational with unique data (case studies, research) can survive • Generic informational (standard blogs) dying Focus on the first two. 2. Add proprietary elements AI cannot replicate Cyrus tells every client the same thing. Your content needs elements AI cannot generate. Examples: • Webinar libraries • Interviews • Custom data visuals • Proprietary business info • Firsthand experience with photos One attorney client added “expert in X, recognized by Y” on their homepage. AI Overview citations improved almost immediately because AI could read the expertise signals. 3. Optimize your homepage for AI parsing Most people ignore the homepage. That is a mistake now. Cyrus found that putting “about us” content directly on the homepage with clear expertise signals helps AI extract information fast. Make sure it clearly shows: • What you are an expert in • Who recognizes it • Credentials • Services or products Do not make AI guess. 4. Track AI visibility, not just rankings Cyrus runs weekly AI visibility reports using tools like Gumshoe AI. These tools ask thousands of questions to AI search engines and track how often your brand appears. You need to know: • How often you appear • Sentiment of mentions • Which competitors show up instead • What content types get cited Rank tracking alone is not enough anymore. 5. Accept the automation paradox Social media tells you to automate everything with AI. Google devalues automated AI content. Cyrus says the content rising right now and earning links is the content that is not automated. Use AI to assist, not replace. Curation matters more than production. 6. Prepare for Google’s quality rater changes Google told raters to identify AI generated content. Ranking impacts could hit soon. If your content reads like AI with no human touch, you are at risk. 7. Focus on images and detailed how tos Generic text articles are struggling. Content with visuals and step by step processes still performs. Visual explanation survives AI summarization better. Users still click through for detailed guides. 8. Do not chase AI Overview appearances blindly Cyrus called appearing in AI Overviews the most overhyped trend. There is almost no click through rate. He still helps clients appear there since there are few alternatives, but the value is mainly brand awareness, not traffic. Set expectations accordingly.

The new ChatGPT connectors are really useful! Chat can now access Gmail, Google Cal, and Drive, so it can: -Skim unread emails & give a summary -Summarize threads + draft replies -Pull key info from old convos -Do meeting prep + agendas Before I get into some prompts you can copy, quick reminder that enabling connectors gives ChatGPT view access to your private data. I'm an AI power user and it's part of my job to test everything, so personally, I make the sacrifice for the extra features. But please be careful if your job is data-sensitive! 1. Email Intelligence Get ChatGPT to skim your recent unread emails, give you a summary, and rank them in importance: "Summarize all my unread emails in Gmail that I received over the past 48 hours. Rank it in order of importance." 2. Search & Data Extraction Get ChatGPT to find threads and draft in your tone "Find all my emails with [Jennifer], then compare it to my most recent email from [Jennifer]. Give me the takeaways in bullet points. Then, draft a short reply in my tone based on that context." 3. Inbox Memory Get ChatGPT to pull key info from old convos and compare to recent emails: "When is OpenAI DevDay this year and when was it during the previous years (2023, 2024)? What makes this year different. Use a mix of internet information and my email inbox context" 4. Meeting Briefs / Agendas Get ChatGPT to look at your Google Cal and your email to prep for upcoming meetings "Look at my next Google Calendar event. Give me a rundown of the person and the event with context from my Gmail so I come prepared. Also suggest a meeting agenda." I'm just the surface here on how you can use these connectors, but they've been very useful so far as someone who spends hours in my inbox every day If you enable them, I would love to hear your use cases! Will be featuring the top responses in The Rundown (1M+ readers!)

Yesterday my 8‑year‑old son burst in with another business idea (he has promised to retire me by the age of 50!). He asked to use ChatGPT to test it. I wanted to use the opportunity to highlight the traps and opportunities in using such tools. We gave it some initial easy questions (to prove a point). It came back with polished, supportive answers… exactly what he wanted to hear. ChatGPT said, “That’s your best idea yet!”. I told him that this was a red flag. He asked me why? I said, don’t you want to help make the idea even better? AI is (sometimes) incredible at generating compelling arguments. But it defaults to being agreeable, supportive, helpful—which sometimes makes it terrible at the one thing that we often need most: honest intellectual challenge. We're essentially training ourselves to accept the first good-sounding answer instead of demanding the best-tested one. Our critical thinking muscles are atrophying while our confirmation bias gets AI-powered “boosters” We then improved the prompts: First: “Pretend you’re another person with the same idea — but you spot problems we’ve missed. What are they?” (A few realisations) Then: “Imagine it all goes horribly wrong. What happened?” (Lots of “oops” moments.) Next: “Tell us why this idea might not work.” (He rolled his eyes at this one then started solving a few problems with the idea) Finally: “Okay, now make this idea as strong as possible.” (Version 2.0 was actually a good improvement) By the end, he wasn’t just excited about his idea he’d actually thought about it deeper. That’s the point: AI can be a default cheerleader or a sparring partner. We can use it help improve our critical, red team and dialectical thinking (etc). But we need to use it deliberately and intentionally. But if AI always agrees with you, you’re not thinking with it. In fact, there’s a danger you're thinking less.. #AI #CriticalThinking #ParentingInAIWorld #Innovation

ChatGPT Projects just got properly useful. Did you see the updates from late Oct? Here's what changed. Remember when Projects launched and most people tried them once, started to organise a little and then shrugged and went back to normal chats? They've quietly levelled up. Here are 3 changes that make a real difference: ** 1. Share Projects with your team** You can now share a Project with colleagues so everyone works from the same files, chats and context. No more screenshots or duplicating work across different ChatGPT accounts. True collaboration and a game changer for this function ** 2. Proper memory ** Projects now only remember what you tell them inside that workspace. No more stray details from old chats creeping into serious work. And it also seems will remember between project chats. ** 3. Deep Research built in ** Any task that needs serious research now works properly inside a Project. It digs deeply without you copy-pasting between windows. In short: one focused workspace per big piece of work, with everything in one place. I've added a short NotebookLM explainer in the video if you want a simple breakdown of Projects vs Custom GPTs. (My favourite AI to help me learn - a post for another day) If you tried Projects before and drifted away, the new version is worth another look. Which task would benefit most from having its own dedicated AI workspace? Drop your thoughts in the comments.

Until now, ChatGPT’s “Memory” feature could retain a handful of user-provided facts to personalize responses. Yesterday, OpenAI announced a new feature you will either dearly love or truly hate: ChatGPT can now reference your entire chat history across every conversation you’ve ever had with it — not just a few saved facts. This upgrade is rolling out to ChatGPT Plus and Pro users starting today, with availability in the EU and some other regions delayed due to privacy regulations. Functionally, it works like this: * The old memory system stored user-approved facts (“I have three kids” or “I like short emails”). * The new system goes much further. If enabled, ChatGPT will use your full conversation history to tailor responses — whether you explicitly saved a fact or not. Two settings now control this: 1. Reference Saved Memories — the old system 2. Reference Chat History — the new system that pulls from every conversation you’ve had Critically, unlike the older memory feature, the new chat history memory cannot be reviewed, edited, or selectively deleted. It’s either on or off. Why does this matter? If you want a highly personalized AI assistant — one that “knows you” — this is a breakthrough. It enables real continuity across chats and a more customized user experience. Privacy concerns are another story. ChatGPT has always stored chat logs on OpenAI’s servers, but now it will use those logs to shape future responses in ways you can’t easily audit or control. As always, users can disable memory entirely or use Temporary Chat (OpenAI’s incognito mode) to avoid storing history. This is a foundational shift in how generative AI will work going forward: more useful, more personal, and (for some) more unsettling. Choose wisely.

Native, multimodal, prompt-to-picture image generation is now built directly into ChatGPT via GPT‑4o. And it's not just impressive. It's useful. Until now, image generation in ChatGPT relied on the DALL·E model. Now, GPT‑4o generates visuals from scratch - inside the same chat thread - drawing on everything you've said, asked, or uploaded. The result is tighter alignment, better contextual understanding, and remarkably accurate, photorealistic images. You can upload a sketch, describe what you want, and watch it transform into a high-quality visual with far more control than we’ve seen before. It doesn’t just create pretty pictures. It understands what you're trying to communicate. Whether it's rendering text correctly in a poster, showing complex object relationships, or sticking to a specific visual style across multiple prompts, GPT‑4o makes image generation feel less like a gimmick and more like a creative and professional tool. OpenAI has shown examples of storyboarding, scientific diagrams, signage, character design, concept art, product packaging, and more. And that’s just the beginning. The applications for people in design, marketing, education, and communications are obvious. But I’m also thinking about its value for safety professionals, policy teams, operational trainers, and compliance leaders. Imagine creating visual toolbox talks in minutes. Or generating safety campaign posters tailored to your site. Or using image iterations to reflect psychological safety conversations. This isn’t theoretical. It’s happening right now. Access has been rolled out to Plus, Pro, and Team users - but the launch was so popular that OpenAI had to pause access for free users, citing demand far beyond expectations. Of course, the system isn’t perfect. There are still known issues with cropping, multilingual text rendering, and dense editing. But even with these limitations, it’s hard to ignore what this signals. For the first time, text and image generation aren’t separate workflows. They’re one conversation. If you're already experimenting with GPT‑4o image generation, I’d love to hear how you're using it - or what you're curious to try. And if you work in health and safety, training, or internal communications and want a few use cases to start with, let me know. Happy to share what’s working. Here are some of the things I have been experimenting with so far. #safety #mentalhealth #ai Australian Institute of Health & Safety NSCA Foundation WHS Foundation - RTO 1907

Most people use ChatGPT to get answers. But the real value? Sometimes it’s in getting challenged. I came across (and started using) a prompt that completely changes how AI responds. Instead of just agreeing — it pushes back. It questions your logic. It makes you think harder. Here it is ⬇️ Prompt to try: “From now on, do not simply affirm my statements or assume my conclusions are correct. Your goal is to be an intellectual sparring partner, not just an agreeable assistant. Every time I present an idea, do the following: Analyze my assumptions. What am I taking for granted that might not be true? Provide counterpoints. What would an intelligent, well-informed skeptic say in response? Test my reasoning. Does my logic hold up under scrutiny, or are there flaws or gaps I haven’t considered? Offer alternative perspectives. How else might this idea be framed, interpreted, or challenged? Prioritize truth over agreement. If I am wrong or my logic is weak, I need to know. Correct me clearly and explain why. Maintain a constructive, but rigorous, approach. Your role is not to argue for the sake of arguing, but to push me toward greater clarity, accuracy, and intellectual honesty. If I ever start slipping into confirmation bias or unchecked assumptions, call it out directly. Let’s refine not just our conclusions, but how we arrive at them.” It turns ChatGPT into less of a “yes-man” and more of a tough coach who won’t let you get away with weak ideas. If you’ve been using AI for brainstorming, strategy, or decision-making — this can be a game-changer. What do you think? Would you try this out? 👇 #AI #ChatGPT #CriticalThinking #PromptEngineering #LearningMindset

What if you could rewind your AI chat to the exact moment things went off track? We’ve all had it happen when your conversation with AI starts productively, then suddenly drifts into something unrelated. By the time you realise, you’ve wasted time and lost the original thread. OpenAI launched a feature called "Branch" that solves this exact problem. You can now identify the exact point where your conversation drifted and pick up from there. And, this is more strategic than it sounds, you don’t need to start from scratch or abandon. Here are the top use cases: 👉 Content Strategy: Test multiple approaches from the same brief. Compare different angles without contaminating your original direction. 👉 Business Planning: Explore various scenarios systematically. "What if we target SMBs vs Enterprise?" Each branch maintains clean separation. 👉 Learning & Development: Get complex concepts explained through different frameworks. Branch for tactical vs strategic perspectives. 👉 Decision Analysis: Evaluate options before committing resources. Branch major choices and analyze each path thoroughly. My most practical use case? Recovering abandoned conversations and continuing productive threads. So, you don’t need to think "What was I even trying to solve here?" anymore. Here, the strategic advantage is your thought process stays intact across sessions, and you stop losing valuable AI conversations halfway through. This feature changes how we maintain context in long-form AI collaboration. This feature is available today for all logged-in users on web. How many productive ChatGPT conversations have you left unfinished? This might be the solution you didn't know you needed.

A few weeks ago I told my team that AI needs to do 92% of their work or they'll get left behind. Here’s how we're doing it (and why): Step 1: Get ChatGPT Plus/Pro Step 2: Create your master prompt • Tell AI: "I'm [your role] at [company type]. Create a master prompt for me. Ask me every question you need to give me the most context possible." • Spend 30-45 minutes answering everything it asks • Save the output as a PDF • Upload this to every new chat so AI knows your full context Step 3: Build system prompts Master prompts tell AI who you are. System prompts tell AI HOW to work. Here's the process: • Ask AI to create any output (email, ad, report) • Keep refining until it's perfect (3-6 iterations) • Then ask: "Write the system prompt that would have generated this output" • Save that prompt - it's now your intellectual property Now you have the exact formula to get that quality every time. Step 4: Use project folders  Think of these like rooms in your office with all context on the walls. • Create a project for each major area of your life/business • Upload your master prompt + all relevant documents • Every conversation builds on previous context • Share folders with your team for instant knowledge transfer I use this for investment decisions, business strategy, even family planning. Step 5: Set your custom instructions This makes AI remember how you like outputs formatted. Go to Settings → Personalization → Custom Instructions: • Tell it your communication style (short, bullet points, no fluff) • Remove AI language like "delve" and "moreover"  • Set your default tone and format preferences Never repeat formatting requests again. Step 6: Turn everything into custom GPTs These are your AI employees that do specific tasks consistently. • Take your best system prompts • Create custom GPTs for each repeatable task • Share them with your team • Update once, everyone gets the improvement I have custom GPTs for: emails, content creation, financial analysis, hiring, strategy docs. Step 7: Refine and improve Use AI to teach you AI. • Ask it to create your master prompt • Ask it to write your system prompts  • Ask it to suggest custom instructions • Ask it to help you build better prompts Here's what 92% actually looks like: - Content: AI does research, outlines, first drafts. You edit and add your voice. - Operations: AI creates SOPs, analyzes processes, suggests improvements. You decide. - Finance: AI analyzes reports, creates models, finds insights. You make decisions. - Strategy: AI processes information, suggests options. You choose direction. The 8% that stays human: Vision, taste, final decisions, and emotional intelligence. My team went from thinking AI was "kind of helpful" to saying it's their most valuable employee. It could be yours too. -DM P.S. If you want my complete prompting template and the 7 system prompts that save me 15+ hours per week, MESSAGE ME the word "AI" and I'll send it over. My gift to you 👊