Structured Output: JSON and XML

When your prompt feeds into code, you need machine-readable output. JSON mode and XML tags make the AI's response parseable instead of loose prose.

30 min · Reviewed 2026

Why structure matters

If you're using an AI inside an app, you don't want a friendly paragraph — you want data. A list of book titles. A calendar event with a date and duration. A code file and a test file. Structured output is how you get clean, predictable data the rest of your program can use.

JSON output

Analyze this customer review and return ONLY valid JSON matching this schema:

{
  "sentiment": "positive" | "neutral" | "negative",
  "topics": string[],
  "urgent": boolean,
  "summary": string (max 20 words)
}

Do not include any text before or after the JSON.

Review: "Bought this for my grandma. The setup was a nightmare — the instructions are in tiny print and missing page 3. But once my son helped her get it working, she loves it. Still, I'd return it if I could."A typical JSON extraction prompt.

The AI will return a JSON object like {"sentiment": "negative", "topics": ["setup", "instructions", "accessibility"], "urgent": false, "summary": "Setup was frustrating but grandma loves the product."}. Your code can JSON.parse it and move on.

XML tags (Claude-style)

Anthropic's Claude was trained with lots of XML-tagged data, so it responds very well to XML tags for structure. You can both send and request them.

I'll give you a support email. Extract information and wrap your answer in XML tags.

<email>
Subject: Broken laptop
Hi, my laptop won't turn on. I ordered it 3 weeks ago, order #A8823. I'm out of town until Friday. - Mike
</email>

Respond with:
<customer_name>...</customer_name>
<order_id>...</order_id>
<issue>...</issue>
<urgency>low | medium | high</urgency>
<suggested_reply>...</suggested_reply>XML tags separate input from output and make fields easy to parse.

When to pick which

JSON	XML Tags
Best for data going into code.	Best for long content with multiple sections.
Compact, widely supported.	More readable for humans, flexible for mixed content.
Brittle — one stray comma breaks it.	Forgiving — ignores stray text outside tags.
Ideal: extractions, classifications, small objects.	Ideal: essays with sections, multi-step reasoning, document analysis.

You are a calendar assistant. Extract events and return ONLY JSON like:

[
  {
    "title": string,
    "date": "YYYY-MM-DD",
    "start_time": "HH:MM",
    "duration_minutes": number,
    "participants": string[]
  }
]

Text:
"Team sync is Wednesday at 10am, 30 minutes, with Maya and Dev. Then I have yoga Thursday 6pm for an hour."Real extraction task — feeds right into a calendar app.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-prompting-structured-output-builders

What is the core idea behind "Structured Output: JSON and XML"?
1. When your prompt feeds into code, you need machine-readable output. JSON mode and XML tags make the AI's response parseable instead of loose prose.
2. Large style guides, glossaries, or brand-voice references.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which term best describes a foundational idea in "Structured Output: JSON and XML"?
1. XML tags
2. JSON mode
3. structured output
4. schema
A learner studying Structured Output: JSON and XML would need to understand which concept?
1. JSON mode
2. structured output
3. XML tags
4. schema
Which of these is directly relevant to Structured Output: JSON and XML?
1. JSON mode
2. XML tags
3. schema
4. structured output
What is the key insight about "Many APIs have native JSON mode" in the context of Structured Output: JSON and XML?
1. Claude, GPT, and Gemini all have 'JSON mode' or 'response format: json_object' settings that force valid JSON.
2. Large style guides, glossaries, or brand-voice references.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
What is the key insight about "Validate the output" in the context of Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Even with JSON mode, always wrap your parse in try/catch. Real-world AI outputs occasionally break schema.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
What is the recommended tip about "Level up your prompts" in the context of Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Distinguishing between retrieved facts and its own knowledge
3. Add context before your request — role, background, constraints. A prompt like "You are a chemistry teacher.
4. Learn what "level" means and why it's important
Which statement accurately describes an aspect of Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Distinguishing between retrieved facts and its own knowledge
3. Learn what "level" means and why it's important
4. If you're using an AI inside an app, you don't want a friendly paragraph — you want data. A list of book titles.
What does working with Structured Output: JSON and XML typically involve?
1. The AI will return a JSON object like {"sentiment": "negative", "topics": ["setup", "instructions", "accessibility"], "urgent": false, "summ…
2. Large style guides, glossaries, or brand-voice references.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which of the following is true about Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Anthropic's Claude was trained with lots of XML-tagged data, so it responds very well to XML tags for structure.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which best describes the scope of "Structured Output: JSON and XML"?
1. It is unrelated to prompting workflows
2. It applies only to the opposite beginner tier
3. It focuses on When your prompt feeds into code, you need machine-readable output. JSON mode and XML tags make the
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Distinguishing between retrieved facts and its own knowledge
3. Learn what "level" means and why it's important
4. JSON output
Which section heading best belongs in a lesson about Structured Output: JSON and XML?
1. XML tags (Claude-style)
2. Large style guides, glossaries, or brand-voice references.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which section heading best belongs in a lesson about Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. When to pick which
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which of the following is a concept covered in Structured Output: JSON and XML?
1. XML tags
2. structured output
3. JSON mode
4. schema

← Back to interactive lesson

Tendril · Builders · Prompting

Structured Output: JSON and XML

When your prompt feeds into code, you need machine-readable output. JSON mode and XML tags make the AI's response parseable instead of loose prose.

30 min · Reviewed 2026

Why structure matters

JSON output

Analyze this customer review and return ONLY valid JSON matching this schema:

{
  "sentiment": "positive" | "neutral" | "negative",
  "topics": string[],
  "urgent": boolean,
  "summary": string (max 20 words)
}

Do not include any text before or after the JSON.

Review: "Bought this for my grandma. The setup was a nightmare — the instructions are in tiny print and missing page 3. But once my son helped her get it working, she loves it. Still, I'd return it if I could."A typical JSON extraction prompt.

XML tags (Claude-style)

Anthropic's Claude was trained with lots of XML-tagged data, so it responds very well to XML tags for structure. You can both send and request them.

I'll give you a support email. Extract information and wrap your answer in XML tags.

<email>
Subject: Broken laptop
Hi, my laptop won't turn on. I ordered it 3 weeks ago, order #A8823. I'm out of town until Friday. - Mike
</email>

Respond with:
<customer_name>...</customer_name>
<order_id>...</order_id>
<issue>...</issue>
<urgency>low | medium | high</urgency>
<suggested_reply>...</suggested_reply>XML tags separate input from output and make fields easy to parse.

When to pick which

JSON	XML Tags
Best for data going into code.	Best for long content with multiple sections.
Compact, widely supported.	More readable for humans, flexible for mixed content.
Brittle — one stray comma breaks it.	Forgiving — ignores stray text outside tags.
Ideal: extractions, classifications, small objects.	Ideal: essays with sections, multi-step reasoning, document analysis.

You are a calendar assistant. Extract events and return ONLY JSON like:

[
  {
    "title": string,
    "date": "YYYY-MM-DD",
    "start_time": "HH:MM",
    "duration_minutes": number,
    "participants": string[]
  }
]

Text:
"Team sync is Wednesday at 10am, 30 minutes, with Maya and Dev. Then I have yoga Thursday 6pm for an hour."Real extraction task — feeds right into a calendar app.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-prompting-structured-output-builders

What is the core idea behind "Structured Output: JSON and XML"?
1. When your prompt feeds into code, you need machine-readable output. JSON mode and XML tags make the AI's response parseable instead of loose prose.
2. Large style guides, glossaries, or brand-voice references.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which term best describes a foundational idea in "Structured Output: JSON and XML"?
1. XML tags
2. JSON mode
3. structured output
4. schema
A learner studying Structured Output: JSON and XML would need to understand which concept?
1. JSON mode
2. structured output
3. XML tags
4. schema
Which of these is directly relevant to Structured Output: JSON and XML?
1. JSON mode
2. XML tags
3. schema
4. structured output
What is the key insight about "Many APIs have native JSON mode" in the context of Structured Output: JSON and XML?
1. Claude, GPT, and Gemini all have 'JSON mode' or 'response format: json_object' settings that force valid JSON.
2. Large style guides, glossaries, or brand-voice references.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
What is the key insight about "Validate the output" in the context of Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Even with JSON mode, always wrap your parse in try/catch. Real-world AI outputs occasionally break schema.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
What is the recommended tip about "Level up your prompts" in the context of Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Distinguishing between retrieved facts and its own knowledge
3. Add context before your request — role, background, constraints. A prompt like "You are a chemistry teacher.
4. Learn what "level" means and why it's important
Which statement accurately describes an aspect of Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Distinguishing between retrieved facts and its own knowledge
3. Learn what "level" means and why it's important
4. If you're using an AI inside an app, you don't want a friendly paragraph — you want data. A list of book titles.
What does working with Structured Output: JSON and XML typically involve?
1. The AI will return a JSON object like {"sentiment": "negative", "topics": ["setup", "instructions", "accessibility"], "urgent": false, "summ…
2. Large style guides, glossaries, or brand-voice references.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which of the following is true about Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Anthropic's Claude was trained with lots of XML-tagged data, so it responds very well to XML tags for structure.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which best describes the scope of "Structured Output: JSON and XML"?
1. It is unrelated to prompting workflows
2. It applies only to the opposite beginner tier
3. It focuses on When your prompt feeds into code, you need machine-readable output. JSON mode and XML tags make the
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. Distinguishing between retrieved facts and its own knowledge
3. Learn what "level" means and why it's important
4. JSON output
Which section heading best belongs in a lesson about Structured Output: JSON and XML?
1. XML tags (Claude-style)
2. Large style guides, glossaries, or brand-voice references.
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which section heading best belongs in a lesson about Structured Output: JSON and XML?
1. Large style guides, glossaries, or brand-voice references.
2. When to pick which
3. Distinguishing between retrieved facts and its own knowledge
4. Learn what "level" means and why it's important
Which of the following is a concept covered in Structured Output: JSON and XML?
1. XML tags
2. structured output
3. JSON mode
4. schema

← Back to interactive lesson