Why are vague words a problem in prompts?

Words like good, better, or appropriate leave the model to guess your intent, producing inconsistent output. Replacing them with measurable criteria gives the model a concrete target and makes results repeatable.

What counts as a vague word?

Subjective qualifiers (good, better, appropriate, relevant, high-quality), fuzzy quantifiers (some, few, several, many), and hedges (try to, as needed, etc.). The tool detects these and groups them by type.

Does it rewrite my prompt automatically?

No — it flags each vague term and suggests a specific replacement, but you choose the precise criterion that fits your task. This keeps you in control of intent.

How specific should a replacement be?

Specific enough to verify. "Good summary" becomes "summary under 100 words covering all three key findings." If you could not check whether the output met the bar, it is still too vague.

Does it send my prompt anywhere?

No. All detection runs locally in your browser using a built-in dictionary of vague terms. Nothing is uploaded or stored.

Prompt Specificity Amplifier

Prompt specificity amplifier

The fastest way to get inconsistent output from a model is to use vague words. “Write a good summary,” “use an appropriate tone,” “include some examples” — each hands the decision back to the model, and it guesses differently every time. This tool scans your prompt for vague qualifiers, fuzzy quantifiers, and hedges, then suggests specific, measurable replacements so the model has a target it can actually hit. You stay in control: it flags and recommends, you decide the exact criterion.

How it works

You paste a prompt and optionally name the domain. The tool tokenizes the text and matches against a built-in dictionary of vague terms grouped into three classes — subjective qualifiers (“good,” “better,” “appropriate”), fuzzy quantifiers (“some,” “few,” “several”), and hedges (“try to,” “as needed”). For each hit it surfaces the offending word with context and a concrete replacement pattern, such as turning “good” into “meets all listed criteria” or “few” into “a specific number.” It also computes a specificity score so you can see progress as you tighten the wording. Everything runs locally in your browser.

Tips and examples

Make it checkable. If you cannot verify whether the output met a word’s bar, replace the word. “High quality” → “no spelling errors and under 200 words.”
Replace quantifiers with numbers. “Some examples” → “exactly 3 examples.”
Kill the hedges. “Try to keep it short” → “keep it under 50 words.” Hedges invite the model to ignore the instruction.
Label the domain. Noting that you are writing a legal or marketing prompt tags the copied report so you know which prompt it belongs to.