Claude ChatLesson 10

Formatting & Response Style

Claude formats its replies using Markdown — headings, lists, tables, and code blocks render cleanly in the chat. You control the style by asking for shorter or longer answers and specifying the output format you need.

Markdown rendering

Claude writes responses in Markdown, and the chat interface renders it automatically. You see formatted text, not raw symbols — though you can copy the underlying Markdown if needed.

H
Headers

# H1, ## H2, ### H3 — structure long answers

## Section title
•
Bullets & numbers

Unordered and ordered lists for steps and items

- Item one - Item two
⊞
Tables

Rows and columns for comparisons and data

| Col A | Col B |
</>
Code blocks

Syntax-highlighted code with a copy button

```python\nprint('hi')\n```
claude.ai — rendered response
C
Project Setup Guide
Prerequisites
  • Node.js 18 or later
  • A code editor (VS Code recommended)
  • Git installed
Quick comparison
ToolSpeedBest for
npmFastMost projects
yarnFastMonorepos
Install command
npm create next-app@latest my-app
Claude renders Markdown automatically — headers, bullets, tables, and code blocks display formatted
Tip: Ask Claude to "use headers and bullet points" when you want a scannable answer, or "put this in a table" when comparing multiple items side by side.

Asking for shorter or longer responses

Claude defaults to a balanced length — enough detail to be useful without being overwhelming. You can shift that in either direction with a few words in your prompt, or refine after the first reply.

Phrases that control length

GoalExample phrase
Shorter"Keep it under 100 words." / "Give me a one-paragraph summary."
Brief"Answer in 2–3 bullet points." / "TL;DR only."
Standard"Explain this clearly." (no length constraint)
Longer"Go into detail." / "Explain step by step with examples."
Long form"Cover each major section in detail."
Adjust after"Make that shorter." / "Expand on the second point."
Prompt: "Explain DNS in 2 sentences."
DNS (Domain Name System) translates human-readable domain names like google.com into IP addresses computers use to connect. When you type a URL, your browser asks a DNS server for the matching IP address before loading the page.
Prompt: "Explain DNS in detail with examples."
What DNS does
DNS maps domain names to IP addresses…

How a lookup works
1. Browser checks local cache
2. Queries recursive resolver
3. Walks the DNS hierarchy…

+ examples, record types, troubleshooting
Specify length in your prompt — Claude adjusts depth and word count to match

Requesting specific formats

Tell Claude exactly how you want the output structured. The right format depends on what you plan to do with the answer — paste into code, scan quickly, or read as a document.

JSON
API responses, config files, structured data for code
"Return only valid JSON, no explanation."
Bullet list
Action items, short lists, quick scanning
"List the top 5 risks as bullet points."
Numbered steps
Tutorials, procedures, ordered instructions
"Give me numbered steps to deploy."
Table
Comparisons, feature matrices, side-by-side data
"Compare these in a table with columns for price, speed, and ease."
Prose
Essays, emails, narratives, reports
"Write this as a professional paragraph, not a list."
Code only
When you just want the snippet, no commentary
"Return only the Python code, no explanation."
JSON
"Return the data as JSON."
{
  "name": "Acme Corp",
  "employees": 120,
  "founded": 2018
}
Bullet list
"Give me 4 bullet points."
  • Use HTTPS for all production traffic
  • Store secrets in environment variables
  • Enable two-factor authentication
  • Review access permissions quarterly
Prose
"Write this as a flowing paragraph."

A well-designed API should prioritize consistency and predictability. Endpoints should follow a clear naming convention, return standard HTTP status codes, and document every field so consumers can integrate without guesswork.

Request the format you need — JSON for code, bullets for scanning, prose for reading

Combining format and length

You can combine constraints in a single prompt. The more specific you are, the less follow-up messages you need.

Strong combined prompt
"Summarize this article in exactly 5 bullet points. Each bullet should be one sentence. Use plain language for a non-technical audience."
✗ Vague
"Tell me about APIs."
✓ Specific
"Explain REST APIs in 3 bullet points for a beginner. Keep it under 80 words."
Summary:
  • Claude renders Markdown — headers, bullets, tables, and code blocks display formatted.
  • Control length with phrases like "under 100 words" or "go into detail."
  • Request specific formats: JSON, lists, tables, prose, or code only.
  • State format, length, and audience in one prompt to cut down on follow-ups.

What's Next

Claude Chat vs. Other Products — when to use Chat, Code, Cowork, Skills, or Plugins.