How to Improve AI Responses with Clear Requests

In working with AI, I’m stopping before typing anything into the box to ask myself a question : what do I expect from the AI? 2x2 to the rescue! Which box am I in? On one axis, how much context I provide : not very much to quite a bit. On the other, whether I should watch the AI or let it run. If I provide very little information & let the system run : ‘research Forward Deployed Engineer trends,’ I get throwaway results: broad overviews without relevant detail. Running the same project with a series of short questions produces an iterative conversation that succeeds - an Exploration. “Which companies have implemented Forward Deployed Engineers (FDEs)? What are the typical backgrounds of FDEs? Which types of contract structures & businesses lend themselves to this work?” When I have a very low tolerance for mistakes, I provide extensive context & work iteratively with the AI. For blog posts or financial analysis, I share everything (current drafts, previous writings, detailed requirements) then proceed sentence by sentence. Letting an agent run freely requires defining everything upfront. I rarely succeed here because the upfront work demands tremendous clarity - exact goals, comprehensive information, & detailed task lists with validation criteria - an outline. These prompts end up looking like the product requirements documents I wrote as a product manager. The answer to ‘what do I expect?’ will get easier as AI systems access more of my information & improve at selecting relevant data. As I get better at articulating what I actually want, the collaboration improves. I aim to move many more of my questions out of the top left bucket - how I was trained with Google search - into the other three quadrants. I also expect this habit will help me work with people better.

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?

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