- AI Fire
- Posts
- 🏆 Anthropic & OpenAI Just Changed Prompting Rules! Here’s ONLY 5 Parts Working Right Now
🏆 Anthropic & OpenAI Just Changed Prompting Rules! Here’s ONLY 5 Parts Working Right Now
Our best prompting advice for you months ago doesn’t work anymore. We’ll look at what OpenAI & Anthropic’s latest models truly respond to, and reveal what works now.
Neil Phan
August 28, 2026
TL;DR
AI Prompt Engineering is changing because newer models need less hand-holding. The bigger improvement now comes from giving ChatGPT the right context and a clear workflow.
A strong prompt still needs structure. In this article, I break it into five parts: Task, Context, What Good Looks Like, Format And Length, and Boundaries.
I also show how I use that structure inside a real ChatGPT Project. The workflow is simple: add the right files, set Project Instructions, send the task prompt, then review the final output.
Key points
The five-part prompt framework helps ChatGPT understand the job, context, quality bar, output format, and limits.
ChatGPT Projects can hold reusable files and instructions, so you don’t need to repeat the same background every time.
A final review prompt helps catch unsupported claims, weak assumptions, and sections that still need work.
Table of Contents
Introduction
A lot of the prompting advice we gave you a few months ago is already outdated.
OpenAI and Anthropic have moved fast, many old prompt formulas now feel bloated, rigid, or unnecessary. When models change, the way we write prompts has to change too.
I’ve tested hundreds of AI models and tried more prompting methods than I can count. Prompt engineering in 2026 is shifting toward building better workflows!
Today, I’ll show you what to stop doing, what still works, and the framework I now use to turn prompts into reusable systems instead of one-off instructions.
You’ve reached the locked part! Subscribe to read the rest.
Get access to this post and other subscriber-only content.
Already a paying subscriber? Sign In.
A subscription gets you:
- • Instant access to 700+ AI workflows ($5,800+ Value)
- • Advanced AI tutorials: Master prompt engineering, RAG, model fine-tuning, Hugging Face, and open-source LLMs, etc ($2,997+ Value)
- • Daily AI Tutorials: Unlock new AI tools, money-making strategies, and industry (ecommerce, marketing, coding, teaching, and more) transformations (with videos!) ($3,650+ Value)
- • AI Case studies: Discover how companies use AI for internal success and innovative products ($1,997+ Value)
- • $300,000+ Savings/Discounts: Save big on top AI tools and exclusive startup discounts
Reply