Start here · 2:53
What chain of thought is
This lesson explains what a prompt framework is, then what chain of thought is, where it came from and why asking for step by step reasoning helps on maths, logic and multi step problems.
- A prompt framework is a reusable structure for a request to an AI tool, usually a short checklist of parts such as role, task, context, audience, format, constraints and examples, often named with an acronym so it is easy to remember. It exists because the AI fills in whatever you leave out with generic guesses.
- Chain of thought asks the model to reason step by step before giving the answer. It was introduced by Wei and colleagues at Google in 2022 and helped most on maths, logic and multi step problems.
- Zero shot chain of thought comes from Kojima in 2022. It showed that simply adding the words let us think step by step improved reasoning, with no examples and no special setup.
- Frameworks help most when a request is complex or open to interpretation. A quick, simple question can stay short, and adding step by step reasoning to a simple lookup usually adds noise rather than value.
- There are well over sixty named frameworks, and most of them remix the same ingredients. Chain of thought is different in kind: it changes how the AI works through a task, and you can add it on top of any fill in framework.
| Term | What it means | Where it helps |
|---|---|---|
| Prompt framework | Reusable checklist of prompt parts | Complex or open requests |
| Chain of thought | Reason step by step before answering | Maths, logic, multi step tasks |
| Zero shot chain of thought | Just add let us think step by step | When you have no examples |
Do this in your own tools, step by step. Ticks are saved on this device.
What is a prompt framework?
A reusable structure or checklist of the parts a good prompt contains.
What does chain of thought ask the model to do?
Reason step by step before giving the answer.
Which problems did it help most with?
Maths, logic and multi step problems.
Wes Welcome to Chain of Thought and Step-Back Prompting. This course is part of Complete AI Training; you'll find the full library at complete A I training dot com. It takes six short chapters.
Laura This part explains what a prompt framework is, then what chain of thought is and why step by step reasoning helps on maths, logic and multi step problems.
Wes A prompt is the request you type into an AI tool such as ChatGPT, Claude or Gemini. A prompt framework is a reusable structure for that request. Think of it as a short checklist of the parts a good prompt contains, usually named with an acronym so it is easy to remember.
Laura Why bother. The AI fills in whatever you leave out with generic guesses. A framework makes sure you include the parts that change the answer, such as who it is for, what you want to achieve and the format you need.
Wes Frameworks also make prompts repeatable. You fill the same parts each time, save the prompt as a template and share it with colleagues. They are not magic words. The value comes from the detail you put in each part.
Laura They help most when a request is complex or open to interpretation. A quick, simple question can stay short. There are well over sixty named frameworks, and most of them remix the same ingredients: role, task, context, audience, format, constraints and examples.
Wes Here is where this course fits. Chain of thought is a prompting technique from AI research. Instead of slots to fill, it changes how the AI works through a task, and you can add it on top of any fill in framework.
Laura Chain of thought asks the model to reason step by step before giving the answer. It was introduced by Wei and colleagues at Google in 2022. It helped most on maths, logic and multi step problems, where jumping straight to an answer goes wrong.
Wes Then in 2022 Kojima and colleagues showed something simpler. Zero shot chain of thought found that simply adding the words let us think step by step improved reasoning, with no examples and no special setup. You just ask for the steps.
Laura Here is how you write it. The anatomy of a chain of thought prompt has three parts: the task, the instruction to reason step by step, and the format you want back, usually the steps plus the final answer.
Wes Watch it in a real job. A finance analyst wants a pricing calculation checked. They paste the numbers, ask for step by step reasoning, and ask for the final total at the end, so they can follow the logic and spot any wrong assumption.
Laura The takeaway. Chain of thought does not add new facts. It changes how the AI works through the task, and that is why it helps most when a problem has several steps. Ask for the reasoning, then check it.
Wes Your turn. Pick one task from your own job that has several steps, such as a calculation, a checklist or a comparison. Write the prompt twice, once as you normally would and once asking the AI to reason step by step first, then compare the answers.
Get the other 5 chapters, the exam and your certificate for LinkedIn, plus all 700+ AI courses.