I’ve been testing the new ChatGPT experience with Codex, ChatGPT Work, and the redesigned app, and I’m curious what everyone thinks so far. For those who’ve tried it, how does it compare to Claude (especially Fable)? What are you using the most today, and why? Has the update changed your workflow at all, or are you still reaching for Claude first?

Hi AI builders!😃 I created a free Claude Fable 5 Prompting Best Practices guide to help you get better results from Fable 5. I created this guide by referencing Anthropic’s official Claude Platform documentation for Prompting Claude Fable 5, then simplified into a cleaner, beginner-friendly workflow. Inside, you’ll learn: ✅ When to use Fable 5 for harder, longer, more complex tasks ✅ How to choose the right effort level without wasting time or credits ✅ A simple prompt formula you can reuse ✅ How to set better boundaries so Claude does not overbuild ✅ How to structure long-running agent workflows This is especially helpful if you are building AI skills, agents, automations, workflows, prompts, or anything where better planning and execution quality matter. ✅ How to Get It: 💥 Free Users → Access your free Claude Fable 5 Prompting Best Practices guide here! ❤️ Premium Members → You get access to this guide, our growing learning resources, and my full growing collection of premium AI Agent Skills and resources! If you are Premium, you get access to every custom skill and resource I build to help automate and improve your workflows. What are you currently building, or want to build?😃 Share with the group below.👇 - Diana

In my app I built an agent to extract my positioning and offer ladder. I upload my knowledge documents, they are stored safely on cloud storage. A cloud task picks them up to send to vertex who extract the vectors an put it in a postgress datastore on cloud run. Then I aks the agent to create my positioning and offer ladder. It uses researcher, writer, evaluator to create my ideal positioning and offer ladder. Pretty impressed with the quality of results it gives.I probably could have used Notebook LLM for this as well, but I don’t Want to push all my IP and client notes (confidentiality) to public LLM. Now it is in private storage.