Anthropic Prompt Engineering Documentation
The official prompting guide from the team that trains the model, covering clarity, examples, chain of thought, structured output and long context techniques. Vendor documentation is usually marketing, and this is not.
Guide
AI & Machine Learning
Anthropic
A few hours
All
Free
What it is
Anthropic's own documentation on getting good results out of Claude, organised as a sequence of techniques from most to least impactful.
Why to read the vendor version
Prompting advice ages fast, and third party guides frequently recommend techniques that were necessary two model generations ago and are now counterproductive. The people who trained the model know what it responds to, and they update the guidance when the model changes.
The techniques worth internalising
Being explicit rather than clever, giving examples of the output shape you want, letting the model reason before it answers, using structure to separate instructions from data, and prefilling responses to constrain format. Most quality problems are solved by one of these.
Best for: anyone building on a large language model, regardless of which provider they use, since most of it transfers.
Ready to start?
Opens on Anthropic in a new tab.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Every session is free; a few slots open each week.
Follow along
New writing, resources and project ideas land here first.