Handling ambiguity
Prompt Engineering
Every ambiguous prompt forces Claude to make a choice: ask for clarification or make an assumption and proceed. Both behaviours are useful — in the right context. This chapter explains what drives that choice, how to signal which behaviour you want, and how to avoid the two failure modes: Claude asking unnecessary questions, and Claude confidently guessing wrong.
How Claude Decides What to Do with Ambiguity
Claude's default behaviour is to make a reasonable assumption and proceed, often stating the assumption explicitly. This is usually the right call — stopping to ask a question for every minor uncertainty would be exhausting. But the threshold for asking vs. assuming shifts based on signals in the prompt:
- High-stakes or irreversible actions — Claude is more likely to ask before proceeding
- Large ambiguity that changes the entire approach — asking is more useful than guessing and producing something entirely wrong
- Short, conversational prompts — Claude reads these as exploratory and is more likely to answer with a clarifying question
- Long, detailed prompts — the investment of detail signals you want an answer, not more questions
- Explicit signals in the prompt — phrases like "make reasonable assumptions" or "ask me if you need more info" override the default
The Decision in Practice — When Each Behaviour Is Right
| Situation | Right behaviour | Why |
|---|---|---|
| You want a quick answer and the ambiguity is minor | Assume | Stopping for clarification adds friction with no value — the assumption is easy to correct |
| The ambiguity changes the entire approach (e.g. language choice, audience, platform) | Ask | Getting it wrong means producing something useless — one question saves a wasted response |
| You're exploring — you don't know exactly what you want yet | Ask | Clarifying questions help you think through the task; a guess may anchor you in the wrong direction |
| You're in a pipeline or automation — you need a response, not a question | Assume | A clarifying question halts the pipeline; always signal "make assumptions and proceed" in automated contexts |
| The task involves multiple plausible interpretations of roughly equal value | Both | Answer one interpretation, note the assumption, and offer to redo for another — gives value without blocking |
| You've provided a lot of context but one key detail is missing | Ask | The context signals effort invested — Claude asking one focused question is appropriate |
Signalling "Make Assumptions and Proceed"
When you want Claude to get on with it — no questions, just a best-effort response — there are reliable phrases that signal this clearly:
The most direct. Claude will state its assumptions and continue.
Useful when you've had Claude ask too many questions and want it to commit.
Keeps assumptions visible without letting them block progress.
You resolve the most likely ambiguity yourself, removing Claude's need to ask.
Make reasonable assumptions and always return a response — never ask a clarifying question. A question response will break the pipeline.
Signalling "Ask Me First"
Sometimes you genuinely want Claude to check before investing effort — especially for large, time-consuming tasks where a wrong assumption wastes a long response:
Claude will gather what it needs before producing anything. Good for large documents or complex builds.
Targets the specific kind of ambiguity you're worried about.
Inverts the prompt — Claude identifies its own gaps rather than guessing.
Caps the number of questions — useful when you want input but not an interrogation.
The Confident Wrong Guess — The Worse Failure Mode
Claude guessing silently — without stating the assumption — is the most damaging ambiguity failure. You get a confident-sounding response built on a wrong foundation, and you may not realise until you've acted on it.
The Unnecessary Question — The Annoying Failure Mode
The opposite problem: Claude asking for information it could reasonably infer, or asking multiple questions when one would do.
Resolving Your Own Ambiguity Upfront
The fastest way to avoid the guess-or-ask problem is to resolve the most likely ambiguities yourself before sending the prompt. Ask yourself: what would Claude most likely get wrong here? Then specify it.
A Useful Pattern: Answer Then Ask
For cases where Claude isn't sure which interpretation you meant, asking it to answer one interpretation and then check is often more productive than stopping to ask first: