Checkpoint: talk to it well

You know what's on the other end now: a next-token guesser, trained on a mountain of text, shaped into an assistant, and blind to anything you don't tell it. That last part is the key to prompting.

Claude only has your words to go on. So a good prompt is mostly the context you'd give a smart new colleague on their first day. Here's one request, sent bare and then with that context added.

The right column came from adding one line: it's for nervous beginners, keep it friendly and under 40 words, and mention the Saturday slow group. Same model. Very different answer.

Six habits that do most of the work:

Put the facts in the prompt. Lesson 6's rule. If Claude needs a name, a date, a document or a decision you've already made, it's not there unless you type it.

Say exactly what you want. Anthropic's test: would a colleague with no background understand your prompt? If not, neither will Claude.

Say who it's for and why. The reason behind a request helps Claude make the calls you'd make.

Give it a shape. A length, a format, a number of options.

Show an example when style matters. Claude copies examples closely, so pick good ones.

Let it say “I don't know”, or ask you questions. Then read the answer, tweak the prompt and run it again. Prompting is a loop, not a spell.

Checkpoint time. Write a prompt for something you actually need: an email, a plan, an explanation. Hit all four checks, then run it.

Finish this checkpoint and the course badge is yours. Two good next steps: Tokens & temperature goes deeper into tokens, odds and randomness, and Prompting that works turns these six habits into a toolkit.