Why do six short, specific instructions usually beat one long paragraph of guidance?

Flashcard·Easy·4.0 · 0·~30s·Asked atAnduril Cursor Netflix

Attempt it

A bulleted list is dense: each line is one rule the model can follow or violate, and verification is local. A paragraph buries rules inside connective tissue, makes priorities ambiguous, and lets the model pattern-match to the tone instead of the rules. The token cost of a bulleted version is usually smaller too, the connective words are gone. The bigger reason is testability: with bullets you can write evals that probe each rule independently. With a paragraph, you can only test the gestalt, which makes regressions hard to localise.

Your answer

A bulleted list works better than a paragraph for system-prompt rules for three concrete reasons. **Bullets are locally verifiable.** Each line is one rule. The model can satisfy or violate it independently of the other lines. With a paragraph, the rules are tangled in connective sentences and the model often pattern-matches to the overall tone instead of extracting individual rules. **Bullets are token-cheaper.** The connective tissue,"and", "meanwhile", "in addition", "furthermore", is gone. Six short bullets typically use fewer tokens than a paragraph saying the same thing. **Bullets are testable.** You can write an eval for each rule: does the output respect this one constraint? With a paragraph, you can only test the gestalt: does the output feel right? Gestalt tests catch the big regressions but miss the subtle ones, and they cannot localize which rule was violated when something fails. The one case where a paragraph genuinely helps is when the guidance is a single coherent narrative (a persona description, an explanation of context) rather than a list of rules. There the connective tissue is the content, not overhead.

**Six short, specific instructions beat one long paragraph because they are denser, more testable, and easier for the model to extract as discrete constraints.** A system prompt is read by a model that processes tokens through attention rather than by a human reader who scans for structure. Bullets exploit two facts about how this reading happens. First, each bullet is a local rule. The model can recognise it, weight it, and check the output against it independently of the other bullets. A paragraph buries the same rules inside narrative flow; the model is more likely to pattern-match to the tone of the paragraph than to extract the individual constraints. Production teams routinely see this empirically: converting a paragraph to bullets without changing the content improves rule adherence on the eval set. Second, bullets are testable. With six bullets you can write six independent evals (one per rule) and localize failures. With a paragraph you can only test whether the output "feels right" and the failure modes are diffuse. Diffuse failures are the worst kind because you cannot regression-test them. There is also a token-cost argument. The connective tissue in a paragraph ("and", "meanwhile", "in addition", "that said") costs tokens and contributes nothing to the rule set. Six bullets typically run shorter than the paragraph that says the same things. The one exception is when the system prompt is a narrative rather than a rule set, a persona description, a context explanation, a tone-setting passage. There the connective tissue is the content and bullets would be a worse fit.

TL;DR

Bulleted instructions are dense, testable, and cheaper in tokens; paragraphs hide rules inside connective tissue and reduce evals to gestalt checks.

Memory aid

Easy to grasp

Picture a kitchen with two sets of recipe instructions on the wall. One is a paragraph in flowing prose with the steps embedded inside connective sentences. The other is six short bullet points. New cooks doing the same dish under time pressure mess up the paragraph version more often, not because they cannot read English but because each step is hard to find inside the prose. The bullet version has one rule per line. You can point at the one that got missed. You can train someone by walking through each line. You can put a checkmark next to each one. The model running your system prompt is in the same situation as the cook under time pressure.

Key concepts

Context engineering Prompt engineering LLM evaluation

Concept explanation~2 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

System prompts get written by humans who naturally produce flowing English because that is how humans write well. The model on the other side processes tokens through attention, and the structure that helps human writing often hurts model adherence. Bullets and paragraphs are not just two styles; they are two different surfaces the model treats differently and that the production team can test differently.

This card walks through why the bullet form usually wins for rule sets, where prose is still the right tool, and how to lay out a system prompt that plays each surface to its strength.

What the model sees in each format

A bulleted list is structurally explicit: each bullet is a separate line, often starting with a dash or number, and the model has seen millions of training examples where this format encodes discrete rules or items. Attention can localize to a single bullet and process it as a unit. Output adherence to a single bullet does not depend on the model correctly parsing the bullet next to it.

A paragraph buries rules inside narrative flow. The same rules are present, but they are connected by tokens like "and", "meanwhile", "in addition", "that said". The model reads the paragraph as a coherent passage and is more likely to extract the tone of the paragraph ("this is a careful, formal context") than the rules the paragraph contains.

Empirical signature

Production teams that have done the conversion (paragraph to bullets, no other changes) consistently report improved rule adherence on the same eval set. The lift is not huge on simple tasks but it is real on rule-heavy ones. Anthropic and OpenAI both surface this in their official prompt-engineering guides.

The testability argument

The token-cost and maintenance arguments

When prose is the right tool

How to convert a paragraph prompt to bullets

Situations where this technique stops working.

2–4 min · Everything important, quickly.

Real products, models, and research that use this idea.

Anthropic's published system-prompt patterns for Claude Opus 4.7 use a short persona paragraph followed by a numbered rule list followed by output-format hints.
OpenAI's 2026 prompt-engineering guide for GPT-5.5 explicitly recommends bullet-list rule sections over flowing prose for instructions.

What an interviewer would ask next. Try answering before peeking at the approach.

QWhat does a good per-rule eval look like in practice?

One judge-LLM eval per rule with a pass-fail prompt: 'Does this output respect [rule N]? Answer yes or no.' Run across a labeled set; track pass rate per rule across versions.

2 more follow-ups an interviewer would ask next. Sign in to reveal them.

Red flags & common mistakes

The phrases that signal junior thinking. Click to expand.

Most common mistake

Writing system prompts as flowing English because it reads well to humans. The model is not the audience that benefits from connective tissue; bullets are denser, more testable, and usually cheaper per call.

60 second bullets to scan on the way to the call.

Why a model treats bullets and prose differently during attention
Why bullets are cheaper in tokens than equivalent prose

Primary sources. Browse if you want the original framing.