Extraction · beginner

Structured JSON extractor from email

Pull sender, subject, intent, urgency, and action items from a raw email body.

You're indexing inbound email into a CRM and want a consistent JSON schema regardless of how the email is written.

The prompt

Copy this verbatim. Replace the {{ … }} placeholders with your values.

<instructions>
Extract structured data from the email below. Return one JSON object matching <format>.
Output the JSON inside <result> tags. No prose, no markdown fences.
If a field is missing from the email, use null.
</instructions>

<format>
{
  "sender_name": "string or null",
  "sender_email": "string or null",
  "subject": "string",
  "intent": "question | request | complaint | other",
  "urgency": "low | medium | high",
  "action_items": ["string"]
}
</format>

<email>{{ email_body }}</email>

Return inside <result> tags.

Sample input

From: Jane Lee <[email protected]>
Subject: Need invoice copy
Hi — could you resend the May invoice? Our AP needs it by Friday. Thanks, Jane

Expected output

<result>
{
  "sender_name": "Jane Lee",
  "sender_email": "[email protected]",
  "subject": "Need invoice copy",
  "intent": "request",
  "urgency": "medium",
  "action_items": ["Resend May invoice to [email protected] by Friday"]
}
</result>

Notes & tuning tips

Inline `null` and `|` enums in the schema — Claude respects them.
`return only inside tags` is the single most reliable way to dodge markdown fences.
For batch jobs, parallelize at the request level — don't ask for a JSON array of multiple emails in one call.