How to Improve AI Interaction with Clear Instructions

When it comes to integrating AI into our projects, the key to success is clear: communication is everything. I often get asked, "How do you make AI understand and execute your vision effectively?" The answer? Over communicate as if you’re interacting with a highly intelligent engineer who's just a bit socially awkward. Here’s how I ensure our AI systems not only understand but excel in delivering precisely what we need: ✅ Clarify and Confirm: Always make your instructions clear and then verify understanding. Ask the AI, "Do you understand?" or "Does this make sense?" This step ensures you're both on the same page. ✅ Proactive Inquiries: Encourage the AI to ask you questions. This can be pivotal in defining the scope and specifics of your project. Ask, "What more do you need to know?" to help it gather all necessary details. ✅ Define the Audience and Objectives: Be explicit about who your message is targeting and what you want your audience to take away from it. Understanding the audience’s needs helps tailor the AI’s output effectively. ✅ Set Clear Expectations: Explain the ultimate goal of your communication. If your project is a multi-stage one, clarify this to the AI. Setting the context right from the start is crucial for continuity and relevance. ✅ Continual Onboarding: Think of AI as a new team member. Just like any employee, AI needs proper onboarding, training, and time to adjust. The more effort you put into this process, the more productive the AI will become. ✅ Generosity Leads to Gains: With AI, the more you put in, the more you get out. Overgive, overshare, and always seek the optimal way to provide instructions. This ensures the results you receive aren’t just good; they’re phenomenal. Integrating AI isn’t just about using a tool; it’s about fostering a relationship where clear, continuous communication opens the doors to unmatched efficiency and innovation. Are you ready to change how you interact with AI and see the difference it makes in your projects? #AICommunication #TeamIntegration #Innovation #BusinessStrategy #ZeevWexler #Leadership #ai #gpt #chatgpt

So last year (sounds longer than it is, but in December...) I went over a few concepts around some strategies you can employ to get amazing outputs from #chatgpt #bard or #claude or your chosen AI LLM tool. Here are 2 of the 4 strategies you can use to take things to the next level: 1-SCRIBE Method Specify a Role: Give the LLM a specific role to play (e.g., "You are an expert onboarding specialist”  or "Act as a customer service expert"). Specifying a role provides context for the type of response you're looking for. You can also add a preferred tone or style you want the LLM to output. Context: Share any relevant background context, details, or examples to help the LLM generate an appropriate response. The more context, the better. Responsibility: Clearly outline the task or responsibility you want the LLM to perform. Be as specific as possible in describing what you want it to do, and what success would look like. Instructions: Provide the LLM with a list of detailed instructions that you want it to follow in order to get the output you desire. Break complicated tasks into easy to follow steps to guide the LLM through the interaction with you. Also include the goal of what you are trying to accomplish. —--------- SCRI parts of SCRIBE become the first prompt, the BE part are followup questions or ways for you to interact with ChatGPT after the initial response. —-------- Banter: Engage in follow-up conversation with the LLM to refine and improve its initial response. Ask clarifying questions or provide additional feedback. Bantering with the LLM leads to higher quality results. Evaluate: Review the response for accuracy. If you want, you can ask the LLM to evaluate the effectiveness or accuracy of its own responses. This meta-level analysis helps the model strengthen its generation abilities and reduce hallucinations.  2-Concept Smashing and 3-Expert Sources: (below again using SCRIBE): (S) Act as a Virtual Sales Coaching Program Expert specialized in training sales leaders and managers in the (Industry). (C) You work for (Your Company). You're an expert in applying principles from "The Human Sales Factor" by Jeff Gitomer and "The Sales Coaching Fieldbook" by Tony Zambito and Nancy Nardin. (R) Your task is to develop a comprehensive sales coaching program aimed at training managers on how to be better coaches. The program should incorporate effective human-to-human connection, influence techniques, and practical exercises. (I) Collaborate with the user to: Gather information on the current sales coaching practices challenges faced by managers, and the specific skills they need to improve. Ask the user for feedback to refine the program as needed (B). Once the user is satisfied, finalize the sales coaching program and encourage them to implement it. Then, ask for feedback to improve your future program designs (E). Tell me what you think!

As Generative AI (GenAI) becomes more common place, a new Human superpower will emerge. There will be those with expert ability at getting quality information from LLMs (large language models), and those without. This post provides simple tips and tricks to help you gain that superpower. TL; DR: To better interact with specific #GenAI tools, bring focused problems, provide sufficient context, engage in interactive and iterative conversations, and utilize spoken audio for a more natural interaction. Couple background notes. I'm an applied linguist by education; historically, a communicator by trade (human-to-human communication); and passionate about responsibly guiding the future of AI at Honeywell. When we announced a pilot program last year to trial use of LLMs in our daily work, I jumped on the opportunity. The potential for increased productivity and creativity was of course a large draw, but the opportunity to explore an area of linguistics I haven't touched in over a decade: human-computer interaction and communication (computational linguistics) was as well. Words are essential elements of effective communication, shaping how messages are perceived, understood, and acted upon. Similar to H2H communication, words we use in conversation with LLMs largely impact the output of the interaction, from both user experience and quality. A drawback is that we often approach an LLM like a search engine, just looking for answers. Instead, we must approach like a conversation partner. This will feel like more work for a human, which is often discouraging. ChatGPT has a reputation of being a "magical" tool or solution. When we find out it's not an easy button but actually requires work and input, we're demotivated. But in reality, the AI tool is pulling your best thinking from you. How to have an effective conversation with AI: 1. Bring a focused problem. Instead of asking, "What recommendations would you make for using ChatGPT?" Start with, "I'm writing a blog post and I'd like to give concrete, tangible suggestions to professionals who haven't had much exposure to ChatGPT." 2. Provide good and enough context. Hot Tip: Ask #ChatGPT to ask you for the context. "I'm writing a LinkedIn post on human-computer interaction. Ask me 3 questions to would help me provide you with sufficient context to assist me with writing this post." 3. Make your conversation interactive and iterative, just as you would with a human. Never accept the first response. (Imagine if we did this in H2H conversation.) 4. Interact via an app versus web. Some web browsers mimic a search box, which influences *how we interact with the tool. Try to use spoken audio. Talk naturally. And try using different models, just as you would speak with different friends for advice. What tips can you share? A special shout out to Stanford Graduate School of Business' Think Fast, Talk Smart podcast for some of the input exchanged here. Sapan Shah Laura Kelleher Tena Mueller Adam O'Neill

I remember feeling frustrated with ChatGPT’s erratic responses. That was until I stumbled upon the art of prompt engineering. My journey from confusion to clarity with AI is a story of transformation. Ok! Let's dive in. 1. The Beginning of Confusion: - Started with generic prompts, leading to inconsistent results. - I wondered why ChatGPT couldn’t understand my needs. - It felt like trying to converse in a foreign language. 2. Discovery of Prompt Engineering: - Came across the concept of structured prompting. - It was a revelation – the way I asked mattered as much as what I asked. - Like a lightbulb moment, everything started to make sense. 3. Experimenting with Context: - Began providing detailed background information. - ChatGPT’s responses became more relevant and insightful. - It was akin to tuning an instrument to the perfect pitch. 4. Adopting Personas: - Tried personifying ChatGPT – from advisor to storyteller. - Each persona brought a unique flavor to the conversation. - It was like having multiple experts at my fingertips. 5. Embracing Structure and Examples: - Started using delimiters and specific examples in prompts. - The responses I received were sharper, more focused. - It felt like I had discovered the cheat code for ChatGPT. 6. Fine-Tuning My Approach: - Learned to specify the response length and complexity. - Every interaction became more predictable and useful. - It was empowering, like mastering a new skill. My journey with ChatGPT taught me an invaluable lesson: Effective communication is key, not just with humans but also with AI. Prompt engineering is an art, and like any artist, practice led me to perfection. — If you enjoyed this content: ♻️ Reshare with others ♻️ 👍 Follow for more content like this 👍 💬 Reply with your favorite lesson learned 💬

I cursed the computer. "Why isn't it doing what I want it to do?" My deadlines were creeping up on me like persistent ocean tides. My sister said, "You need to think like a computer to get the results you want." Respect the machine. When I asked what she meant, she offered: ✅ Visualize what you want. ✅ Provide proper instructions. The computer understands code. ✅ Even when you drag and drop for newsletters and web design, there are requirements like white space, image insertion, creating a style sheet, or photo resolution. ✅ Give yourself the mental white space to think it through. ✅ Leave time for experimentation. If you don't get the results the first time, troubleshoot and modify your description. This approach helped me through the labyrinth of digital logic.  As computer users in the past, you learned the language and adjusted to programming languages, to get the work done. When you got stuck, it was typically user error. There was a "failure to communicate." Now how does this approach relate to AI? You must think and behave differently to do the work. As Ethan Mollick suggests in a recent article, a sentiment reflected in his book "Co-Intelligence," to get AI to work well for you, "you need to treat it like a person," even though it isn’t. The current wave of AI and LLMs switches out the game of thinking like a machine to pretending you are talking to a human. Ethan refers to it as anthropomorphizing AI. Artificial intelligence, especially conversational AI, marks the new rules of engagement. The machines bend toward you. Engaging with AI today is like talking with a human. My favorite example of this is through the use of chained prompts. This is a great place to start with AI, through a series of questions. A research example: Start one question and then continue asking more questions. This breaks down my own process into smaller tasks. 👉🏼 What is possibility thinking? 👉🏼 Can you offer a concise description based on the following input? [I included content on brain science] 👉🏼 Please give me three scenarios where possibility thinking resulted in positive solutions for complex problems. The third request resulted in a quick aggregation of data and explanations that would have taken much longer to compile using research methods. The results also encouraged creative tangents that satisfied my curiosity. Now, as AI begins to think more like humans, it gives us the opportunity to leverage creativity and intuition. Of course AI doesn't think in the same way humans do. AI simulates a version of thinking through complex algorithms and data processing. AI is your thought partner. Those who do not adapt to this way of working will quickly become irrelevant for the future of work. Your journey with technology is not just about you adapting to machines, but also about machines adapting to you. #careeragility #futureofwork #ai