Click any words you think contain an error. Click again to unmark.
Mark at least one word to submit.
This prompt has three directives, and every one of them is a **vague adjective** with no observable target. Helpful, thorough, accurate, and good all sound like quality words, but none of them tells the model anything it can act on. The model cannot check whether its output is thorough enough or good enough because those words do not point at anything measurable.
The fix is to walk each directive and replace it with either a concrete action the model can perform or a measurable property of the output. Instead of you are a helpful assistant, name a specific role and scope. Instead of be thorough and accurate, list the testable behaviors you want, like cite sources from the provided context. Instead of give a good answer, give a length cap and a structure.
The rewrite forces you to say what good output actually looks like. That is the more useful constraint anyway, and it gives your eval suite something to check. The original three sentences are token padding without any behavioral signal.
Every directive in the prompt fails the operational test. You are a helpful assistant gives the model a vague register cue but no concrete role or scope. Be thorough and accurate names two unfalsifiable properties the model has no way to self-check. Give a good answer is the same failure repeated with a different adjective.
The fix is mechanical. Replace each vague directive with one of two operational shapes: an action the model can perform, or a measurable property of the output. You are a Python tutor explaining concepts to beginners gives a concrete role and scope. Cite specific sources from the provided context and flag any unsupported claim is a testable action. Answer in under 200 words; structure as definition, example, common pitfall is a measurable property plus a structural constraint.
The three rewrites do two things at once. They give the model targets it can actually hit, and they give the eval suite metrics it can check. Citation rate, format compliance, word count, structural conformance, refusal rate. Each maps to a Promptfoo or Braintrust assertion in two lines of code.
The broader pattern is that prompt engineering and evaluation are two sides of the same contract. If the directive is unfalsifiable, the model cannot follow it and you cannot improve it. Refactoring vague to operational is the most consequential edit you can make on a production prompt.
Quick reference
TL;DR
Every directive is a vague adjective with no observable target. Replace 'helpful', 'thorough', 'accurate', 'good' with concrete actions or measurable properties the eval suite can check.
Imagine giving a new chef the instruction 'cook good food'. They cannot tell what good means, so they guess based on their training. Now imagine telling them 'use fresh ingredients, cook to medium-rare, and serve in under fifteen minutes'. They know exactly what to do and you can check whether they did it. The prompt here is the first version, three times. Every adjective sounds caring but tells the model nothing it can act on.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.
Ultra-short throwaway prompts for one-off exploration If you are sketching a quick test and not shipping the prompt, the discipline is overhead; for anything that will run more than once, operationalize.
Prompts where the user provides their own detailed instructions in-message If the user is supplying the operational directives, the system prompt can stay light without being vague.
Bare model evaluation with no system prompt Sometimes you want to measure the model's defaults; adding directives changes what you are measuring.
Quick scan · 2–4 min
Everything important, quickly.
2 min: three anti-patterns in one prompt + the two operational shapes + how each rewrite maps to an eval assertion.
Real-world examples
Real products, models, and research that use this idea.
1OpenAI's prompt engineering guide for GPT-5.5 leads with 'be specific' precisely because vague adjectives like 'helpful' and 'accurate' degrade compliance reliably.
2Anthropic's Claude Opus 4.7 docs explicitly recommend naming concrete behaviors over asking for quality in the abstract.
3Promptfoo and Braintrust assertion suites can only check operational directives; a prompt full of vague adjectives produces zero meaningful assertions.
Interviewer follow-ups
What an interviewer would ask next. Try answering before peeking at the approach.
QHow would you write the eval suite for the rewritten prompt?
Sign in or go Pro to see the approach for this follow-up.
QWhat if the user wants an open-ended creative answer?
Sign in or go Pro to see the approach for this follow-up.
QHow does this generalize to system prompts that span many tasks?
Sign in or go Pro to see the approach for this follow-up.
Don't say this
Red flags and common mistakes that signal junior thinking. Click to expand.
Most common mistake
Reading this prompt and thinking it is just thin; the real failure is that every directive is unfalsifiable, so neither the model nor your eval suite can act on it.