Chain-of-thought
Chain-of-thought (CoT) is when an AI model works through a problem in written steps before giving its final answer. It can be prompted or built into reasoning models, and it often improves accuracy on maths and logic.
Prompting
How to instruct an AI model and get answers you can use.
c
- Chain-of-thought - Chain-of-thought (CoT) is when an AI model works through a problem in written steps before giving its final answer. It can be... More
- Context Engineering - Context engineering is the practice of giving an AI model all the information it needs to do a task well. That means... More
f
- Few-shot Prompting - Few-shot prompting means including a handful of worked examples in your prompt so an AI model can copy the pattern. It is... More
g
p
- Prompt - A prompt is the instruction, question or material you give an AI tool to tell it what you want. The clearer and... More
- Prompt Chaining - Prompt chaining is splitting a large AI task into a series of smaller prompts, where the output of each step becomes the... More
- Prompt Engineering - Prompt engineering is the skill of writing and testing instructions for an AI model so it gives accurate, useful and consistent answers.... More
s
- System Prompt - A system prompt is a set of hidden instructions that an AI tool's builder gives the model before any user types. It... More
t
- Temperature - Temperature is a setting that controls how random an AI model's answers are. A low temperature gives more predictable, focused replies. A... More
z
- Zero-shot Prompting - Zero-shot prompting means asking an AI model to do a task with instructions only, without showing it any worked examples. The model... More
Context Engineering
Context engineering is the practice of giving an AI model all the information it needs to do a task well. That means instructions, relevant documents, past conversation, data and access to tools, in the right amount and order.
Few-shot Prompting
Few-shot prompting means including a handful of worked examples in your prompt so an AI model can copy the pattern. It is a quick way to get answers in your format, style or categories without retraining the model.
Grounding
Grounding is the practice of tying an AI tool's answers to a trusted source, such as your company documents, a database or live search results, so it answers from facts rather than from memory alone.
Prompt
A prompt is the instruction, question or material you give an AI tool to tell it what you want. The clearer and more specific the prompt, the more useful the answer tends to be.
Prompt Chaining
Prompt chaining is splitting a large AI task into a series of smaller prompts, where the output of each step becomes the input for the next. It makes complex work more accurate and easier to check.
Prompt Engineering
Prompt engineering is the skill of writing and testing instructions for an AI model so it gives accurate, useful and consistent answers. It covers wording, structure, examples and the order of information.
System Prompt
A system prompt is a set of hidden instructions that an AI tool's builder gives the model before any user types. It sets the assistant's role, tone, rules and limits for every conversation.
Temperature
Temperature is a setting that controls how random an AI model's answers are. A low temperature gives more predictable, focused replies. A higher temperature gives more varied and creative ones, with more risk of errors.
Zero-shot Prompting
Zero-shot prompting means asking an AI model to do a task with instructions only, without showing it any worked examples. The model relies on what it learned in training to work out what you want.