Email lead extraction

This workflow reads an email body and pulls out who wrote it, what they want and how urgent it is. The API takes files only, so the email body goes up as a .txt file; the Python SDK does that for you when you pass text=.

The email

→

What comes back

sender_name99%

company_name99%

inquiry_type98%

urgency99%

topics

NodesParse → ExtractCredits60 per pageYou get

The graph

{
  "name": "Email lead extractor",
  "nodes": [
    { "id": "parse_1", "type": "parse" },
    {
      "id": "extract_1",
      "type": "extract",
      "extraction_schema": {
        "fields": [
          { "name": "sender_name",  "description": "Full name of the person who sent the email", "data_type": "string" },
          { "name": "sender_email", "description": "Email address of the sender", "data_type": "string" },
          { "name": "company_name", "description": "Company or organization the sender represents", "data_type": "string" },
          {
            "name": "inquiry_type",
            "description": "The primary category of this inquiry",
            "data_type": "enum",
            "enum_options": [
              { "name": "pricing",      "description": "Pricing or cost inquiry" },
              { "name": "demo_request", "description": "Request for a product demo" },
              { "name": "support",      "description": "Technical support or help request" },
              { "name": "partnership",  "description": "Partnership or integration inquiry" },
              { "name": "other",        "description": "Other inquiry type" }
            ]
          },
          {
            "name": "urgency",
            "description": "How urgent this request appears based on language and deadlines mentioned",
            "data_type": "enum",
            "enum_options": [
              { "name": "low",    "description": "No urgency signals" },
              { "name": "medium", "description": "Moderate urgency or soft deadline" },
              { "name": "high",   "description": "Explicit deadline or urgent language" }
            ]
          },
          {
            "name": "topics",
            "description": "Products or areas of interest mentioned in the email",
            "data_type": "multi_select",
            "enum_options": [
              { "name": "enterprise",  "description": "Enterprise plan or features" },
              { "name": "integration", "description": "Integration or API capabilities" },
              { "name": "pricing",     "description": "Pricing or billing" },
              { "name": "security",    "description": "Security or compliance" }
            ]
          },
          { "name": "summary", "description": "A one-sentence summary of what the sender is asking for", "data_type": "string" }
        ]
      }
    }
  ],
  "edges": [{ "source": "parse_1", "target": "extract_1" }]
}

import os
from anyformat.sdk import Client
from anyformat.workflow import Schema

client = Client(api_key=os.environ["ANYFORMAT_API_KEY"])

workflow = (
    client.workflow("Email lead extractor")
    .parse()
    .extract([
        Schema.string("sender_name",  "Full name of the person who sent the email"),
        Schema.string("sender_email", "Email address of the sender"),
        Schema.string("company_name", "Company or organization the sender represents"),
        Schema.enum("inquiry_type", "The primary category of this inquiry", options=[
            Schema.option("pricing",      "Pricing or cost inquiry"),
            Schema.option("demo_request", "Request for a product demo"),
            Schema.option("support",      "Technical support or help request"),
            Schema.option("partnership",  "Partnership or integration inquiry"),
            Schema.option("other",        "Other inquiry type"),
        ]),
        Schema.enum("urgency", "How urgent this request appears based on language and deadlines mentioned", options=[
            Schema.option("low",    "No urgency signals"),
            Schema.option("medium", "Moderate urgency or soft deadline"),
            Schema.option("high",   "Explicit deadline or urgent language"),
        ]),
        Schema.multi_select("topics", "Products or areas of interest mentioned in the email", options=[
            Schema.option("enterprise",  "Enterprise plan or features"),
            Schema.option("integration", "Integration or API capabilities"),
            Schema.option("pricing",     "Pricing or billing"),
            Schema.option("security",    "Security or compliance"),
        ]),
        Schema.string("summary", "A one-sentence summary of what the sender is asking for"),
    ])
    .create()
)

import { Anyformat, Schema } from "@anyformat/sdk";

const af = new Anyformat({ apiKey: process.env.ANYFORMAT_API_KEY! });

const workflow = await af
  .workflow("Email lead extractor")
  .parse()
  .extract([
    Schema.string("sender_name",  "Full name of the person who sent the email"),
    Schema.string("sender_email", "Email address of the sender"),
    Schema.string("company_name", "Company or organization the sender represents"),
    Schema.enum("inquiry_type", "The primary category of this inquiry", [
      Schema.option("pricing",      "Pricing or cost inquiry"),
      Schema.option("demo_request", "Request for a product demo"),
      Schema.option("support",      "Technical support or help request"),
      Schema.option("partnership",  "Partnership or integration inquiry"),
      Schema.option("other",        "Other inquiry type"),
    ]),
    Schema.enum("urgency", "How urgent this request appears based on language and deadlines mentioned", [
      Schema.option("low",    "No urgency signals"),
      Schema.option("medium", "Moderate urgency or soft deadline"),
      Schema.option("high",   "Explicit deadline or urgent language"),
    ]),
    Schema.multiSelect("topics", "Products or areas of interest mentioned in the email", [
      Schema.option("enterprise",  "Enterprise plan or features"),
      Schema.option("integration", "Integration or API capabilities"),
      Schema.option("pricing",     "Pricing or billing"),
      Schema.option("security",    "Security or compliance"),
    ]),
    Schema.string("summary", "A one-sentence summary of what the sender is asking for"),
  ])
  .create();

Run and read

Send the email body as a text file. Any .txt works; a saved .eml works too and keeps the headers.

# The body of the email, saved as a file
curl -X POST "https://api.anyformat.ai/v3/workflows/$WORKFLOW_ID/upload/run/" \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  -F 'files=@lead-email.txt;type=text/plain'
# -> 202 {"run_id": "...", "status": "queued"}

# Read the run. Repeat until "status" is "processed".
curl "https://api.anyformat.ai/v3/runs/$RUN_ID/" \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY"

email_text = """From: Maria Lopez <maria.lopez@acmecorp.example>
Subject: Enterprise pricing for Q2 rollout

Hi, I am the VP of Engineering at Acme Corp. We process about 40,000 supplier
invoices a month ... Our board meets on June 12 and I need a quote and a
security overview before then. ..."""

# text= uploads the string as a .txt file for you
result = workflow.run(text=email_text).wait()

lead = {name: field.value for name, field in result.fields.items()}
if lead["urgency"] == "high":
    print(f"HIGH PRIORITY: {lead['sender_name']} from {lead['company_name']}")

import type { ExtractedField } from "@anyformat/sdk";

const emailText = `From: Maria Lopez <maria.lopez@acmecorp.example>
Subject: Enterprise pricing for Q2 rollout

Hi, I am the VP of Engineering at Acme Corp. ...`;

const file = new File([emailText], "lead-email.txt", { type: "text/plain" });
const run = await workflow.run(file);
const result = await run.wait();

// field() can return a scalar or rows; every field here is a scalar
const field = (name: string) => result.field(name) as ExtractedField<string> | undefined;
if (field("urgency")?.value === "high") {
  console.log(`HIGH PRIORITY: ${field("sender_name")?.value} from ${field("company_name")?.value}`);
}

What comes back

The run above, trimmed. It took 10 seconds.

Response

{
  "results": {
    "extractions": [{ "fields": {
      "sender_name":  { "value": "Maria Lopez", "confidence": 99.0, "evidence": [{ "text": "From: Maria Lopez <maria.lopez@acmecorp.example>", "page_number": 1 }] },
      "company_name": { "value": "Acme Corp", "confidence": 99.0, "evidence": [{ "text": "I am the VP of Engineering at Acme Corp.", "page_number": 1 }] },
      "inquiry_type": { "value": "pricing", "confidence": 98.0, "evidence": [{ "text": "1. What does the enterprise plan cost at our volume?", "page_number": 1 }] },
      "urgency":      { "value": "high", "confidence": 99.0, "evidence": [{ "text": "Our board meets on June 12 and I need a quote and a security overview before then.", "page_number": 1 }] },
      "topics":       { "value": "enterprise, pricing, security, integration", "confidence": 98.0, "evidence": ["…"] },
      "summary":      { "value": "Maria Lopez is requesting an enterprise-volume quote, a security overview and ERP API integration information before June 12.", "confidence": 4.0, "evidence": ["…"] }
    } }]
  }
}

Every field also carries verification_status and value_override. Runs and results has the full envelope, section by section.

When it goes wrong

Your topics field looks like a single topic. A multi_select value arrives as one comma-separated string: "enterprise, pricing, security, integration". Split on ", " to get the list back. A good lead is rejected on a low confidence. The summary above scored 4%. A generated sentence is not quoted from the email, so it has no source phrase to score against, and it scores low even when it is right. Gate on the extracted fields, and never on the summary. Two inquiry types keep swapping. pricing and demo_request read alike to a model given only their names. The enum_options descriptions are what separate them, so write the description that names the close case: “Pricing or cost inquiry” against “Request for a product demo”. parse.blocks is empty and parse_confidence is null. A .txt upload has no layout to ground, so there are no blocks and no parse score. That is expected for text input. Gate a text pipeline on the extracted fields instead. A mailbox backs up. Create the workflow once and call upload and run per email. The submission limit is 60 requests per minute, so pace the queue rather than firing the whole inbox at once.

Next steps

Extract node

Field types, modes and smart lookup

Upload and run

Multipart fields, conflicts and idempotency

Classify node

Route each email type to its own Extract node

Field types

Every data type a field can take

Examples

Read the page

Messy piles

Money and compliance

At scale

Email lead extraction

The graph

Run and read

What comes back

When it goes wrong

Next steps

Extract node

Upload and run

Classify node

Field types

​The graph

​Run and read

​What comes back

​When it goes wrong

​Next steps

Extract node

Upload and run

Classify node

Field types

The graph

Run and read

What comes back

When it goes wrong

Next steps