05— Module 05

Output formatting.

4 min read

Format isn't neutral. A bulleted list and a paragraph carry the same content but a different relationship with the reader. Format is part of voice.

Why this is the foundation

Format composes with everything else you've been designing. A warm persona giving you a bulleted list still feels distant because the format is doing the wrong work. A blunt persona writing flowing prose feels less blunt because the format softens it. Format and tone aren't separable — they reach the reader together.

A few specific moves that pay off:

Say “no lists” when you mean it. The model defaults to lists for almost anything that could be structured. If you want prose, the easiest fix is one sentence in the system prompt.
Specify length, not just shape.“Short paragraph” is more useful than “short.” “Three sentences” is more useful than “short paragraph.”
Match the format to the channel.A toast notification, a long-form email, and a chat reply have different shapes. The system prompt should know which one it's producing.
Read what comes out, not what you asked for. If the model keeps reaching for headings when you asked for prose, the rule went into the system prompt softly. Make it louder.

The familiar move

You make format choices constantly. Where to break a paragraph, when to use a list, when to drop in a heading, when to push a warning into a callout. Every one of those is a small claim about how the reader should navigate the page.

The same content, restructured, reads as a different document. A long paragraph treats the reader as someone who'll sit with the idea. A four-bullet list treats them as someone who needs to scan. Neither is wrong. Picking the right one is design.

The lesson, stated plainly

Most language models default to a few formats — bulleted lists with bolded prefixes, numbered steps, headings every two paragraphs. They're the safest-looking defaults, which is why models reach for them. They're also wrong a lot of the time. A heartfelt support reply doesn't want bullets. A checklist doesn't want flowing prose.

The fix isn't to scold the model in your system prompt. The fix is to specify the format on purpose: “answer in one short paragraph, no lists.” Format becomes another knob in the system prompt, sitting next to voice and persona. Once you treat it that way, the output starts behaving.

A small example

Bulleted default

Format instruction

(none — model picks)

Output

“Here's what to think about before your interview: - Open with rapport, not the first question - Avoid leading or compound questions - Let silence do work - Take notes by hand if you can”

Read

Scannable, list-shaped. Reads more like a checklist than a conversation. Fine for a doc; cold for a chat.

Prose, on purpose

Format instruction

Reply in one short paragraph. No lists.

Output

“Before you walk in: lead with rapport, not the first question. Keep questions short and one-at-a-time, and let silence do some of the work — most people fill it with the thing they actually wanted to say. Take notes by hand if you can; it changes how you listen.”

Read

Same four points, different relationship with the reader. Sounds like advice from someone, not a checklist.

Same content. Same persona, probably. The format is doing the work of moving the output from “a list of tips” to “something a person said.”

Try it in your own work

This module doesn't pair with a single playground — format shows up everywhere. The fastest way to feel it is in Diff Mode: write the same user message, set Config A to a system prompt that mentions no format, set Config B to one that specifies format on purpose. Read both. You'll see how much of the output you were assigning to “voice” was actually formatting choices.

Then carry that habit into the rest of your work. The next time you're tuning a system prompt, the question to ask isn't just whatthe model should say — it's what shape that answer should take.

Next module

06 Evaluation