Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Prompt framework course · 6 chapters · 16 min · certificate

What Anthropic, OpenAI and Google Say About Prompting

The official prompting advice for Claude, ChatGPT and Gemini in 2026, side by side, and what it means for your prompts.

Become a memberAlready a member? Sign in

What you'll learn

  • Compare the official prompting advice from Anthropic, OpenAI and Google
  • Apply Google's Persona, Task, Context and Format checklist to real prompts
  • Use Anthropic's golden rule and XML tags to structure prompts
  • Write outcome first prompts with success criteria and constraints
  • Adjust prompts for reasoning models without over-prompting
  • Match prompts and features to ChatGPT, Claude or Gemini

Chapters

6 chapters · 15:39
  1. 3:01 01Start here Members Three companies, one message This lesson explains what a prompt framework is and shows that Anthropic, OpenAI and Google agree on clarity, context, examples and defining the outcome.
  2. 2:31 02Gemini Members Google: Persona, Task, Context, Format This lesson teaches Google's four prompt areas, Persona, Task, Context and Format, why the verb matters most, and why effective prompts run about twenty-one words rather than nine.
  3. 2:29 03Claude Members Anthropic: the golden rule and structure This lesson teaches Anthropic's golden rule, its four structure habits, and the long input ordering that puts documents first and the question last.
  4. 2:29 04ChatGPT Members OpenAI: outcome first This lesson teaches OpenAI's outcome first approach: define the target, success criteria, constraints and context, remove contradictory instructions, tune reasoning effort and verbosity, and ask the model to improve your prompt.
  5. 2:16 052026 Members What changed with reasoning models This lesson shows why reasoning models need less step-by-step direction and more context and clear outcomes, and how over-prompting causes over-eager behaviour.
  6. 2:53 06Apply it Members Applying the official advice This lesson teaches you to apply the official prompting advice by running the colleague test, writing outcome, context, constraints and an example, leaving the method open, and using each assistant's own features.

Study guide

What the AI Makers Say About Prompting

Anthropic, OpenAI and Google each publish their own prompting guidance, and most people never read any of it. This course puts all three side by side and shows you where they agree. The short answer is that all three want clear prompts with real context, a few examples and a defined outcome, and none of them asks you to memorise a rigid formula. You will learn Google's four prompt areas, Persona, Task, Context and Format, Anthropic's golden rule and its habit of wrapping prompt parts in XML tags, and OpenAI's outcome first approach with success criteria and constraints.

In the full study guide

  • What is a prompt framework?
  • Three companies, one message
  • Google: Persona, Task, Context, Format
  • Anthropic: the golden rule and structure
  • OpenAI: outcome first
  • What changed with reasoning models
  • Applying the official advice
  • 5 frequently asked questions
The full study guide is for members, with the course, the exam and your certificate.Get the full course