Operations

Extract Fields From Emails with AI

Sender, company, request, deadline — out of emails with quoted replies and signature blocks, using guidance that knows how email is actually read.

Open in Extraction Prompt Generator

Overview

Email is hostile to extraction: the signal sits on top of quoted history, signatures repeat in every reply, and the actual request hides in politeness. This setup extracts sender_name, sender_email, company, subject, request, and deadline with email-specific reading guidance — prefer the newest message over quoted history, mine the signature for sender details — and a faithfulness rule on the request field: the sender's ask in at most two sentences, no interpretation added. Null discipline keeps the record machine-friendly for triage flows.

How to use this resource

Paste the whole thread

The reading guidance handles quoted history — you don't need to trim the email first.
Watch the request field

Faithful to the sender's wording, two sentences max, no interpretation — the field your routing logic can trust.
Let null mark silence

No deadline stated means deadline: null — never "probably end of week".

Why This Works

Newest-message-first guidance defeats the quoted-history trap
Signature mining gets sender details email bodies rarely state outright
The faithfulness rule keeps the request field evidence, not summary

Best for

Shared inboxes where every mail needs the same triage fields
Threads with deep quoted history and repeated signatures
Routing flows that act on the request field downstream

Not for

Deciding the email's category or priority bucket — that's classification
Drafting the reply — extraction feeds that step, it isn't that step

Use cases

Triaging a shared inbox into structured request records
Pulling sender details from signatures without grabbing quoted history
Capturing deadlines as ISO dates for follow-up automation

FAQ

How do I extract sender details from an email with quoted replies

The SOURCE reading guidance tells the model to prefer values from the newest message over quoted history and to mine the signature for sender details, so sender_name and sender_email come from the live message, not the buried thread. Extraction Prompt Generator outputs this prompt; you run it in your own assistant and validate the JSON it returns.

Will the request field summarize or reword what the sender asked

It stays faithful. The EXTRACTION RULES require the request field to keep the source wording with no added interpretation, in at most two sentences, so downstream routing acts on the sender's actual ask rather than a paraphrase. The AMBIGUITY POLICY also limits any inference to one short step from the text, never a chain of assumptions.

What happens when an email states no deadline

It is set to null, not guessed. MISSING DATA requires an unfound field to be null while keeping the key present, and forbids inventing a value, so a silent email yields a null deadline rather than "probably end of week." When a date is present, the rule formats it as ISO YYYY-MM-DD where it can be determined, keeping the record machine-friendly.

Customize This Resource

Opens this setup in Extraction Prompt Generator. Generate to get the full extraction prompt — then adjust the fields, missing-data behavior, and ambiguity policy.

Open in Extraction Prompt Generator

Prompt Template

Copy it as-is, or use Open in Extraction Prompt Generator to load it pre-filled and customize it with your own context.

TASK
Extract the sender's details and request from the email in the input.

SOURCE
The input is an email message, possibly with quoted replies and a signature block.
Reading guidance: Prefer values from the newest message over quoted history; signatures often carry the sender's details.

FIELDS TO EXTRACT
- sender_name (required): Name of the person who wrote the email
- sender_email (required): Sender's email address
- company (optional): Sender's organization, often in the signature
- subject (optional): Topic of the email
- request (required): What the sender is asking for
- deadline (optional): Any date by which they need it

EXTRACTION RULES
- sender_name: The person's full name as written — do not expand initials or invent missing parts.
- sender_email: A valid email address only — not the surrounding text.
- company: The organization's name as written, without surrounding commentary.
- subject: Exactly as written in the source.
- request: Faithful to the source wording, no added interpretation — at most two sentences.
- deadline: Use ISO format (YYYY-MM-DD) when the date can be determined; otherwise extract it as written.
- Extract values from the source text only — do not use outside knowledge to fill fields.
- Do not summarize or interpret the document — return only the fields listed above.

MISSING DATA
- If a field is not found in the source, set it to null — do not omit the key.
- Never invent or guess a value for a missing field.

AMBIGUITY POLICY
- Prefer explicitly stated information; infer a value only when the text strongly implies it.
- Keep any inference minimal — one short step from the text, never a chain of assumptions.

OUTPUT FORMAT
Return the extracted data as a single valid JSON object using the field names below.

EXAMPLE OF A VALID EXTRACTION
{
  "sender_name": "Jane Smith",
  "sender_email": "user@example.com",
  "company": "Acme Corp",
  "subject": "Renewal pricing question",
  "request": "Short description taken from the source",
  "deadline": "2026-06-10"
}

OUTPUT RULES
- Return only the JSON object — no text before or after it.
- Do not wrap the output in markdown code fences.
- Use the field names exactly as defined — no renaming, no extra fields.

More resources from Extraction Prompt Generator

Resource

Extract Data From Text with AI

Free text in, named fields out. The extraction prompt pattern that turns any unstructured text into consistent, parseable records.

Prompt Engineering

Resource

Extract Invoice Data with AI

Invoice number, vendor, dates, total, currency — extracted into clean fields with strict no-inference rules, ready for accounts payable.

Operations

Resource

Missing Data in AI Extraction — Null, Unknown, or Skip

The most consequential setting in any extraction prompt: what the model does when the field isn't in the text. Four behaviors, and when each is right.

Prompt Engineering

Resources that pair well

Resource

Force JSON Output from AI

Stop getting 'Sure, here is the JSON…' — the output-contract pattern that forces models to return only parseable JSON: schema, example, and a strict rule block.

Prompt Engineering

Resource

Classify Support Tickets with AI

Billing, Technical, Account, How-To, Feature Request — ticket triage with definitions that decide the borderline cases for the model.

Support

Resource

Fix Invalid JSON from AI

The JSON won't parse and you can't see why. Deterministic cause-sniffing — trailing commas, single quotes, unclosed brackets — and the repair prompt that fixes it.

Engineering

Related tools

Tool

Extraction Prompt Generator

Build prompts that extract defined fields from unstructured text — emails, invoices, tickets, résumés.

Structured Output

Tip: Save time by exploring related resources and tools that integrate with this resource.