Mistakes

Prompting mistakes

The vague-prompt traps that waste your time.

Knowledge cards
Mistake
Don't Bury the Question in Backstory
A common mistake of writing a long run-up — background, history, caveats, feelings about the problem — and only at the very end, almost as an afterthought, stating what you actually want. The real request gets lost in the preamble, and the answer misses the point.
L1 · Basic prompts
Mistake
Don't Lead the Witness
The mistake of phrasing a prompt so it signals the answer you're hoping for — 'This is the better option, right?', 'Don't you think X is a mistake?' — and then treating Claude's agreement as independent confirmation. You fished for a conclusion and caught the one you baited.
L2 · Context engineering
Mistake
Don't Make One Prompt Do Five Jobs
The mistake of packing several distinct tasks into a single prompt — research this, then write it up, then edit for tone, then format as a table, and also suggest a title — and expecting all of them done well at once. Some parts land, others get skimmed or dropped.
L1 · Basic prompts
Mistake
Vague Prompts Waste Turns — Specify the Target
The most common prompting mistake: asking for something under-specified ('make this better', 'write about marketing') and getting a generic, average answer.
L1 · Basic prompts
Claude prompting mistakes

Vague prompts force guessing

The most common way to waste a Claude session is to under-specify. Leave out the role, the goal, the constraints, or an example, and Claude has to guess your intent — and even a good guess is still a guess. The fix is not longer prompts but clearer ones: say who Claude is, what outcome you want, and what a good answer looks like. Most disappointing results are not the model failing; they are the prompt failing to give it a clear target to hit.

Overloading and over-steering

Two subtler traps sit either side of vagueness. Overloading crams several unrelated asks into one prompt, so each gets partial attention — break the work into steps instead. Over-steering dictates the exact method when you should describe the outcome and let Claude find the route, which often boxes it into a worse solution than it would have chosen. Aim for the middle: enough direction to be clear, enough freedom to let Claude do the reasoning it is good at.

Frequently asked
Why does Claude misunderstand my prompts?

Usually because the prompt lacked a role, goal, constraints, or an example, forcing it to guess your intent. Being explicit about those removes the guesswork.

Can I over-specify a Claude prompt?

Yes — dictating the exact method when you should describe the outcome can box Claude into a worse solution. Give direction and constraints, but let it find the route.

Should I put everything in one Claude prompt?

No. Overloading a prompt with several unrelated asks gets each handled partially. Break complex work into focused steps so every part gets full attention.