ChatGPT Usage Tips

I use ChatGPT in my work as a writer, every single day. Here's how: 👉 1. I ask it to analyze my writing for any logical reasoning gaps. 3 out of 5 times it points out things I've overlooked. For example, I sometimes skip an explanatory sentence to keep things "succinct". And I've learnt this because it been pointed out to me repeatedly by ChatGPT. Note: it's absolutely no replacement for an editor. It just scratches the surface. 👉 2. I ask it to build analogies. This serves two purposes. One, I sometimes find a creative way to express a common idea. Two, sometimes a non-sensical analogy will reveal a poorly-reasoned argument. The second one is a legit writing hack. 👉 3. I ask it to give me "one word for many words". For example, I couldn't think of one word for "smile very wide", and it came up with "beam". This helps me maintain my creative flow without having to pause for iteration. Put together, these three things save me 20-25 minutes per blog across outlining, writing, and self-editing. So I thought I'd share :D What are some things you use it for?

I use ChatGPT to help managers save time. I developed the 3-4-5 method to get the optimal output on the first try. Steal it and tell me how it works. 3 - The Useful Use Cases While I'm sure this will evolve, there are three common leadership use cases that ChatGPT 4 excels at: - Drafting - Summarizing - Brainstorming Be clear about which use case you're using it for. 4 - The Tailored Output Leaders don't hire anyone; they hire someone with the right capabilities. You need to tell ChatGPT exactly who you need it to be and how you want to see the output. These 4 seem to be the most vital: Expertise  - "An expert copywriter."  - "An experienced CEO advisor." - "A data analyst at a FinTech startup." Tone - "Formal and direct." - "Lighthearted but analytical." - "Conversational and concise." Format - "No empty corporate jargon." - "Bulleted ideas in short sentences." - "Out in a table with columns: [a], [b], [c]..." Optimization - " Most common problems." - " Offer suggestions that are novel and creative." - " Anchor your ideas in statistics from reputable sources." 5 - Optimal Options ChatGPT is thinking, not searching. And it's still imperfect. So I want it to give me options that I can select to refine or possibly combine. 5 options seem to be the sweet spot. Fewer, and I get hallucinations or overly general ideas. More and it stretches into the implausible and irrelevant. Let's put it all together with an example: "I want your help brainstorming ideas for our team offsite. You are an expert corporate event planner who creates engaging and educational experiences. The team is a product marketing team at a rapidly growing FinTech startup. The goal of the offsite is to build meaningful connections and trust across team members and solidify our marketing plan for the next 12 months. Your output should be a two-day agenda with proposed sessions and 3-5 bulleted objectives for each session. Please offer a range of ideas for the sessions, from highly practical to creative and novel." Note: The results on ChatGPT 4 vs the free ChatGPT 3.5 version are well worth the $20/month. As a bonus hack, I subscribed to Poe, which gets me access to ChatGPT 4, Claude, Dall-E, and more, all for the same $20/month. I have no affiliation with any of the above. If you want more help becoming an AI-Accelerated Leader, we've added a bonus module to our next MGMT Accelerator program starting April 30th. AI expert Kevin Williams will join us as we speed through an AI 101/201 primer and explore the top use cases that can give you back hours of time. If you found this post helpful, - Please reshare to help other leaders embrace AI - And follow Dave Kline for more posts like it

I was interviewed by Martine Paris for this article in Entrepreneur Media - it’s the small businesses making the greatest strides in generative AI, driven by sheer necessity. An excerpt: https://lnkd.in/dQad-5W7 Most people think of ChatGPT as a tool for external communications: It writes some marketing copy, you refine its work, and then you share that with your customers. But ChatGPT can also help you refine ideas internally, says Conor Grennan, head of generative AI and dean of students at NYU Stern School of Business — especially if you engage it in role play. "Ask ChatGPT to be a difficult customer who pushes back on every pitch," he says. "It's a great way for your sales teams to learn how to have hard conversations. You can then ask how you could have been more persuasive." Or tell the bot about your product and prompt it to create different pitches to radically different kinds of clients, and ask who else you might try to sell to. Another helpful exercise: After telling ChatGPT about your product, target audience, and sales strategy, ask it to act like a "consultant" to poke holes in that plan. After it answers, have it switch roles and create solutions for all the problems it just brought up. Next, ask it to poke holes in those solutions. As you keep going, says Grennan, ChatGPT will hone its responses until you're able to get at the heart of the issue and the best solutions for it.

ChatGPT can be horrible at writing content. But it doesn't have to be. Here is what I did to make ChatGPT work for me. 1/ Head to the 'custom instructions' section within ChatGPT. Inside of this section you need to tell GPT about yourself in the first section. - Who you are, where you are from, what you do. - What you believe in and why. - Your goals, desires, dreams and ideal future state. It's important to be explicit. ChatGPT is powerful and can behave in many different ways. If it understands what you are trying to achieve it will always be on the same side. 2/ Fill in the second section of the customer instructions. This time talk about output and if you use it like me, audience. - What is your tone of voice and your brand personality. - Where do you do you want it to pull data and research from. - Who is the audience and how do you want to speak to them. 3/ Bonus point - share one of your most successful posts on your main social channel. 4/ Click 'save'. You are now primed to succeed as your ChatGPT experience is optimised for YOU ... but the work is not over. 5/ When writing a prompt, continue to be explicit. Don't use a 1-line prompt. The customer instructions are your foundations but now you need to build your work of art. - Talk about *exactly* what you are looking to achieve. - Why this is the end goal. - The way you think you can best get there. - And any further information you think it would find useful. 6/ Write wicked stuff. Note: I actually don't use ChatGPT to write any of my posts or any of my newsletter. But I do use it to heavily inspire posts and how I should think about my newsletter. For example, when preparing for a deep dive newsletter piece, using my upcoming Jeff Bezos piece as an example, I ask the following: - Can you help draft the outline of a 4000 work piece of Jeff Bezos? - How would you re-write the story in The Heroes Journey format? - What would you change in the structure if optimised for learning? - And why is Jeff Bezos successful? I take all of the detail and start to craft my own outline for the piece from there. Anyway, that's it - happy prompting!

Secret sauce for using AI and ChatGPT effectively! 🌐 Define the Chatbot's Identity: Don't just interact, assign a role! Direct ChatGPT like a seasoned director guiding an actor. For instance, when you need a 'Statistical Sleuth' to dive into data or a 'Grammar Guru' for language learning, this focused identity sharpens the conversation. Example: Instead of "Do something with this data," say "As a statistical analyst, identify and explain key trends in this data set." 🎯 Provide Crystal-Clear Prompts: Be the maestro of your requests. Precise prompts equal precise AI responses. From dissecting datasets to spinning stories, the detail you provide is the detail you'll receive. Example: Swap "Write something on AI ethics" with "Compose a detailed article on AI ethics, emphasizing transparency, accountability, and privacy." 🧠 Break It Down: Approach complex problems like a master chef—layer by layer. Guide ChatGPT through your query's intricacies for a gourmet dish of nuanced answers. Example: Replace "Help me with my project" with "Outline the process for creating a machine learning model for predicting real estate prices, starting with data collection." 📈 Iterate and Optimize: Don't settle. Use ChatGPT's responses as raw material, and refine your inquiries to sculpt your masterpiece of understanding. Example: Transform "Your last response wasn't helpful" into "Elaborate on how overfitting can be identified and mitigated in model training." 🚀 Implement and Innovate: Take the AI-generated knowledge and weave it into your projects. Always be on the lookout for novel ways to integrate AI's prowess into your work. Example: Change "I read your insights" to "Apply the insights on predictive analytics into creating a dynamic recommendation engine for retail platforms." By incorporating these strategies, you're not just querying AI—you're conversing with a dynamic partner in innovation. Get ready to lead the curve with AI as your collaborative ally in the realms of #TechInnovation, #FutureOfWork, #AI, #MachineLearning, #DataScience, and #ChatGPT! Is there anything else you would add to this secret sauce?

Anyone can think better if you explore perspectives: That's what Edward de Bono figured out. At Microsoft, I needed a way to run better meetings, manage conflict, make better decisions, and basically think better in any situation. I turned to Six Thinking Hats, and I consumed Edward de Bono's shelf of books. Six Thinking Hats is a way to think better, together. 𝗧𝗵𝗲 𝗦𝗶𝘅 𝗧𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝗛𝗮𝘁𝘀 𝗮𝘁 𝗮 𝗚𝗹𝗮𝗻𝗰𝗲 Each imaginary "hat" represents a perspective to explore and exploit: 1. 𝗪𝗵𝗶𝘁𝗲 𝗛𝗮𝘁: Facts & Data (Focuses on objective information) 2. 𝗥𝗲𝗱 𝗛𝗮𝘁: Emotions & Intuition (Focuses on feelings and gut reactions) 3. 𝗕𝗹𝗮𝗰𝗸 𝗛𝗮𝘁: Caution & Criticism (Focuses on potential risks and drawbacks) 4. 𝗬𝗲𝗹𝗹𝗼𝘄 𝗛𝗮𝘁: Benefits & Optimism (Focuses on positive aspects and opportunities) 5. 𝗚𝗿𝗲𝗲𝗻 𝗛𝗮𝘁: Creativity & New Ideas (Focuses on generating innovative solutions) 6. 𝗕𝗹𝘂𝗲 𝗛𝗮𝘁: Control & Process (Focuses on managing the discussion and thinking process) You can use the Six Thinking Hats to think better by yourself. But the power comes when you think better together and swarm through a topic. 𝗣𝗮𝗿𝗮𝗹𝗹𝗲𝗹 𝗧𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝘁𝗼 𝗦𝘄𝗮𝗿𝗺 𝗕𝗲𝘁𝘁𝗲𝗿 𝗧𝗼𝗴𝗲𝘁𝗵𝗲𝗿 By default, people tend to argue a point or favor a side or one perspective. With Six Thinking Hats, you do Parallel Thinking. With Parallel Thinking, everyone involved considers the situation or problem from the same perspective at the same time. I've used Six Thinking Hats to turn hostile meetings at Microsoft into true team collaboration. 𝗨𝘀𝗶𝗻𝗴 𝗦𝗶𝘅 𝗧𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝗛𝗮𝘁𝘀 𝘄𝗶𝘁𝗵 𝗔𝗜 / 𝗖𝗵𝗮𝘁𝗚𝗣𝗧 The beauty now is that you can use AI to help you with Six Thinking Hats. First practice so you know how to use the Six Hats, then apply to meetings. Here's how to prompt ChatGPT to help you with Six Thinking Hats: 1. 𝗦𝗲𝘁 𝘁𝗵𝗲 𝗦𝘁𝗮𝗴𝗲: • Introduce the Problem: Briefly explain the situation or problem you're facing. • Introduce Six Thinking Hats: Provide a high-level overview of the Six Thinking Hats method and its different perspectives (White, Red, Black, Yellow, Green, Blue). 2. 𝗙𝗿𝗮𝗺𝗲 𝘁𝗵𝗲 𝗣𝗿𝗼𝗺𝗽𝘁 𝗳𝗼𝗿 𝗘𝗮𝗰𝗵 𝗛𝗮𝘁: • 𝗦𝗽𝗲𝗰𝗶𝗳𝘆 𝘁𝗵𝗲 𝗛𝗮𝘁: Clearly state which thinking hat you want ChatGPT to use for its response. (e.g., "Using the White Hat, summarize the key facts and data relevant to this issue.") • 𝗣𝗿𝗼𝘃𝗶𝗱𝗲 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 (Optional): If necessary, offer additional details or questions specific to the chosen hat. (e.g., "For the Black Hat, consider the potential impact on the budget and timeline.") 3. 𝗟𝗲𝘃𝗲𝗿𝗮𝗴𝗲 𝗙𝗼𝗹𝗹𝗼𝘄-𝘂𝗽 𝗣𝗿𝗼𝗺𝗽𝘁𝘀: • 𝗕𝘂𝗶𝗹𝗱 𝗼𝗻 𝗶𝘁: "Building on the Black Hat perspective, what are some mitigation strategies we could consider?" • 𝗥𝗼𝘁𝗮𝘁𝗲 𝗧𝗵𝗿𝗼𝘂𝗴𝗵 𝗛𝗮𝘁𝘀: Repeat the process for each hat, allowing ChatGPT to generate responses from different viewpoints. Think better my friend, with skill!

The most underrated skill for 2025? (Not code. Not ads. Not funnels.) It's knowing how to talk to AI. Seriously. Prompt writing is becoming the new leverage skill. And no one’s teaching it right until now. I’ve built AI workflows for content, marketing, and growth. They save me 10+ hours/week and cut down on team overhead. The key? 👉 It’s not just asking ChatGPT questions. It’s knowing how to structure your prompts with frameworks like these: Here are 4 frameworks I use to get 🔥 outputs in minutes: 1. R-T-F → Role → Task → Format “Act as a copywriter. Write an Instagram ad script. Format it as a conversation.” 2. T-A-G → Task → Action → Goal “Review my website copy. Suggest changes. Goal: Boost conversion by 15%.” 3. B-A-B → Before → After → Bridge “Traffic is low. I want 10k monthly visitors. Give me a 90-day SEO plan.” 4. C-A-R-E → Context → Action → Result → Example “We’re launching a podcast. Write a guest outreach email. Goal: Book 10 experts.” You’re not just prompting. You’re building AI systems. Mastering this skill will: ✅ 10x your productivity ✅ Reduce dependency on agencies ✅ Help you scale solo (or with a lean team) The AI era belongs to the strategic communicators. Learn how to prompt, and you won’t need to hire half as much. 📌 Save this post. 🔁 Repost if you believe AI is a partner, not a replacement. #ChatGPT #PromptEngineering

𝗛𝗼𝘄 𝗳𝗿𝗲𝗾𝘂𝗲𝗻𝘁𝗹𝘆 𝗱𝗼 𝘆𝗼𝘂 𝗴𝗲𝘁 𝘁𝗵𝗲 𝗿𝗶𝗴𝗵𝘁 𝗼𝘂𝘁𝗽𝘂𝘁 𝗳𝗿𝗼𝗺 𝗖𝗵𝗮𝘁𝗚𝗣𝗧 𝗼𝗻 𝘁𝗵𝗲 𝗳𝗶𝗿𝘀𝘁 𝘁𝗿𝘆? 𝗡𝗼𝘁 𝗲𝗻𝗼𝘂𝗴𝗵? Give these tips a try, check out the attached anatomy of a prompt below. Be Specific: Precision in prompts leads to targeted and useful AI responses. It’s about asking the right questions to get the right answers. Set Constraints: Constraints guide the AI in generating focused and relevant outputs. Think of them as guardrails that keep the AI on track. Provide Context: Context is king. It helps AI understand the 'why' behind a prompt, leading to more meaningful and insightful responses. Seek Creativity: Don't shy away from asking for imaginative or out-of-the-box ideas. AI can surprise us with its creative capabilities. Use Clear Language: Clarity is critical. Clear prompts result in clear responses. Avoid ambiguities to ensure that AI understands your exact needs. Include Criteria for Success: Define what success looks like for your prompt. This helps in evaluating the AI's response and in iterative improvements. Ask for Reasoning: Encourage AI to not just provide answers, but also the rationale behind them. This deepens understanding and trust in AI outputs. Iterate and Refine: AI prompting is an iterative process. Refine your prompts based on responses to achieve the best outcomes. 𝗭𝗲𝗿𝗼, 𝗦𝗶𝗻𝗴𝗹𝗲, 𝗮𝗻𝗱 𝗙𝗲𝘄 𝗦𝗵𝗼𝘁 𝗣𝗿𝗼𝗺𝗽𝘁𝗶𝗻𝗴 In addition to the core strategies for crafting AI prompts, understanding the nuances of zero-shot, single-shot and few-shot prompting can improve your ChatGPT results. 𝗦𝗶𝗻𝗴𝗹𝗲-𝗦𝗵𝗼𝘁 𝗣𝗿𝗼𝗺𝗽𝘁𝘀: 𝗧𝗵𝗲 𝗔𝗿𝘁 𝗼𝗳 𝗣𝗿𝗲𝗰𝗶𝘀𝗶𝗼𝗻 Typically we don't provide any examples to our prompts this is called zero-shot prompting. Single-shot prompting involves providing the AI with one example. This is ideal for straightforward tasks or when you need a quick, creative solution without much context. The key here is specificity and clarity. Since you're only giving one shot or example it's typically good for showing the format of the output you are looking for. 𝗙𝗲𝘄-𝗦𝗵𝗼𝘁 𝗣𝗿𝗼𝗺𝗽𝘁𝘀: 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝘄𝗶𝘁𝗵 𝗘𝘅𝗮𝗺𝗽𝗹𝗲𝘀 Few-shot prompting means providing the AI with a small number of examples to guide its output.Perfect for tasks where you want the AI to follow a certain style or format, or when more complex understanding is required.Choose your examples wisely. They should be representative of the task at hand and demonstrate the variety you expect in responses. Mastering these skills can significantly enhance the results from ChatGPT and other chatbots that use LLMs. What tips do you have for crafting effective AI prompts?

Prompting tips from someone that spends probably $13k+ per month on OpenAI API calls. I'll break the tips into chatGPT user interface tips as well as API tips. My bias is of course going to be about outbound sales and cold email because this is where we spend from and 100% of this spend is on 4o mini API calls. Chat GPT Prompting Tips 1. Use transcription as much as possible. Straight in the UI or use whisprflow(dot)ai (can't tag them for some reason). I personally get frustrated with a prompt when I'm typing it out vs. talking and can add so much more detail. 2. Got this one from Yash Tekriwal 🤔 - When you're working on something complex like a deep research request or something you want o3 to run or analyzing a lot of data, ask chatgpt to give you any follow up questions it might have before it runs fully. Helps you increase your prompt accuracy like crazy. 3. I've found that o3 is pretty good at building simple automations in make as well so we will ask it to output what we want in a format that we can input into make and often we can build automations just by explaining what we need and then plugging in our logins in Make. API prompting tips 1. Throwing back to the Chat GPT UI, but we will often create our complex prompts in the user interface first and then bring it into the API via Clay asking ChatGPT along the way on how to improve the prompt and help us think of edge cases. This can take any team member to a prompting pro immediately. 2. Examples are your best friend. Giving examples of what you would want the output to be is how we can get our outputs to be the same format and not put "synergies" in every email we are sending. I tell the team, minimum 2 examples for single line outputs. 4 examples for anything more complex than that. 6 examples for industry tagging because that gets so odd. Save on costs by putting some real examples in your system prompt. 3. Request the output in JSON. It keeps everything more uniform in the format you need. 4. Speaking of JSON, ask the API to prove to you why it thinks what it thinks and then output the answer. Especially for company category tagging, I find this works really well. I see this greatly increase the accuracy of our results for 2 reasons. I think if AI has to take the extra second to prove to you why a company is an ecommerce brand, the results are demonstrably better. This is just a guess, but I also think that because LLMs basically work by guessing what the next best word is, if you have it tell you why it thinks something is a certain industry and then it gives the output, I think it's much more likely to be correct. Anything else you've found?

Why I Treat Every ChatGPT Prompt as a Job Description When I work with ChatGPT or any other large language models, I approach it with the precision and expectation you'd use for hiring a key team member. Here's how a well-crafted prompt can transform your content strategy: 1. Set Clear Expectations: → Just as a job description outlines roles and responsibilities, your ChatGPT prompt should clearly define what you expect from the model. This ensures that the output is aligned with your objectives. 2. Specify the Role: → Tell ChatGPT exactly who you want it to be. Whether it’s an expert copywriter, a knowledgeable advisor, or a creative designer, shaping its identity will tailor its responses to fit your needs precisely. 3. Define the Task: → What do you want ChatGPT to do? Whether it’s crafting compelling ad hooks, generating engaging blog content, or providing technical explanations, spell it out. The more specific you are, the better the results. 4. Provide the Right Tools: → Equip ChatGPT with the best resources. If you're looking to generate catchy hooks, provide examples of top-performing ones. This "training" through examples, best practices, and clear guidelines not only enhances performance but ensures consistency. Why This Matters? Using ChatGPT without a clear prompt strategy is like hiring someone without a job description — inefficient and ineffective. By treating each prompt as a critical component of your strategy, you optimize your results and get the most out of this powerful tool.