Lately, OpenAI has released o1-preview with a chain-of-thought model. It's very interesting that I have been using another tool with automated prompt generation that helps us do the same things. You could also use other AI models with API, input many types of data, and connect to many apps. The great thing is you don’t need to jump between tools, just use this one and generate all things you need. Try it and let me know what you think.

A simple guide on prompt-chaining with human inputs, even for beginner. I want to share with you all a tip I regularly use to maximize the output quality when using LLMs. Prompt chaining may be familiar with some of you. However, my tip take a step further by incorporating “human inputs” into the chain. This method helps maximize AI’s efficiency + human’s expertise and creativity. I temporarily called it “human-in-loop-capability” in a prompt chain or an AI workflow. So what does this look like? Basically, we break down a large task into smaller, manageable subtasks. In each task, we - as human, provide AI with resources to make sure these subtasks be completed with high-quality. The final output we receive from AI will be of highest quality possible. Let take a practical example of how this technique can be applied to create high-quality SEO blog posts with AI. We design a process for AI to work just like how a human writes a good blog post: (1) brainstorming unique ideas → (2) researching (keywords, competitor’s blog post, the topic,…) → (3) drafting the first outline → (4) first draft: writing each subtopic comprehensively → before (5) finalizing the final SEO blog post → (6) on-page SEO optimization. → Next, we provide AI in each step with every possible “human inputs” for AI to learn from, and process the results that we expect. Inputs could be a resource, your ideas, your requirements in any form of text, files, images, url. 1- Brainstorming Unique Ideas: - Human inputs: • Company details • Target audience information • Desired topic In this initial stage, the AI is provided with essential information to generate relevant and unique ideas tailored to the company's target audience. The human reviewer then selects the most promising concept that aligns with the overall content strategy. 2 - Researching: - Human inputs: • Selection of the best idea that matches expectations from AI-generated list • Refinement of AI-conducted research • Focus on most relevant and valuable insights

I’ve been deep into one of my go-to AI tools, and I just stumbled upon this super cool feature that I had to share with you all, it gives real-time feedback on landing pages! I started thinking… what if we could integrate this into our web design process and build an entire agency around it? Here’s the idea: Imagine offering clients not just beautifully designed landing pages, but ones that are fine-tuned by AI to maximize conversions and engagement from the get-go. This tool can analyze everything like layout, copy, CTA placement, and suggest improvements instantly. I’m thinking this could really set us apart in the web design world. Like, a new way of website agency :v I have a web designer, integrated with this AI, then wow :)) I’d love to hear your thoughts on this. Do you think it’s something clients would find valuable? How would you promote this kind of service? I’m also brainstorming ways to enhance this idea, maybe by adding some personalized AI-driven marketing strategies or even creating a full-blown automation suite for small businesses. I'm open to all your suggestions, these days I just practice to come up with many ideas to validate in the market to see whether it really works or not =))

You're designing a landing page, and you're totally vibing with your art direction, but then your client wants something... different. We've all been there, right? This tool I found is like a secret weapon for web designers, it’s a website feedback generator! You can customize it based on your needs, whether you want more business-focused insights or if you’re looking to keep that artistic flair alive. Plus, you can even tweak the level of critical feedback it gives. How awesome is that? But I’m really curious, how do you guys balance those moments when your vision and your client’s vision don’t exactly line up? Have you tried anything like this before? I’d love to hear your thoughts and learn from your experiences! Let me know what you think about this. Just wonder is it really work as I imagine?

This is the problem I saw among chatGPT users. I do not know whether you experience it or not. Have you ever been in this situation. You receive a nice answer with chatGPT but do not remember prompts? - You have to scroll over history chats to find your previous prompts, and copy/paste it to current chat. Your work pile up. You have many things to do on ChatGPT. You have difficulty organizing your prompts. Would love to share with you a solution: Organize your prompts in an AI workflow → with just a simple input. AI can understand how to provide answer for that specific requirement. Imagine not having to write a long prompt again after 1 time, but just provide a simple input, ChatGPT can provide you high-quality answers. The technique is quite simple: everytime you got a really good prompt that generate best answers, and you need to use that prompts more time in the future → just put it into an AI workflow → design a mutual input (for example: for a blog post, the inputs are content ideas and target audience, for lesson plan, the inputs are grade level, subject,…) You can try to input it in any AI agent/AI workflow builder platform. If our group has any other ideas, please share with me so that I could learn more from you.