Prepare a funding lead when the completed application lands
For Funding brokers and sales operations teams
Capture the business and contact information your intake team needs from a completed application. Use the structured result as input to your own CRM mapping and review process.
25 free credits/month · No card needed
See the workflow and review checks{
"legal_business_name": "Example Harbor Services LLC — synthetic",
"trading_name": "Example Harbor Repair",
"contact_name": "Example Contact",
"contact_email": "applicant@example.com",
"requested_amount": 75000,
"stated_monthly_revenue": 42000,
"business_activity": "Commercial equipment maintenance"
}Synthetic data, not a live extraction. Real responses also include confidence, validation, and result status.
When this work lands on your desk
A prospect returns a completed PDF application, and sales operations needs to prepare an accurate lead record for the funding team.
Handwritten additions, trading names and differently formatted contact details make copy-and-paste intake inconsistent. A business name alone may already exist in the CRM under another spelling. A defined extraction schema gives the reviewer the applicant’s stated facts without claiming that they have been verified or matched.
Start with the documents you already collect
- Completed business funding applications
- Broker application PDFs
- Scanned application forms
PDF, JPEG, PNG, TIFF, or WEBP. Send one file per extraction call; create separate schemas when the document types need different fields.
Define the fields
Open the starter schema. Edit field descriptions, mark the values your process requires, and save it in your account.
Extract at intake
Send the document and saved schema slug to
POST /api/v1/extract, or collect the file through a branded upload site.Hand off reviewed data
Your CRM integration validates required fields, resolves existing businesses and maps the approved result. If industry classification is needed, run it as a separate reviewable step using appropriate business evidence.
A schema shaped around the next step.
Start with these fields, then adjust them to match your documents and destination system. The example above shows the data object you are asking Dokyumi to extract.
Download editable starter schemaStarter fields are optional until you choose which are required. Nested line items need a defined structure if you want validation of their individual values.
| Field | Type | What to capture |
|---|---|---|
legal_business_name | string | Applicant’s stated legal entity name. |
trading_name | string | Doing-business-as name if supplied. |
contact_name | string | Named application contact. |
contact_email | string | Email exactly as stated, for separate validation. |
requested_amount | currency | Requested funding amount, not an approved offer. |
stated_monthly_revenue | currency | Self-reported monthly revenue from the application. |
business_activity | string | Applicant’s business description; not a verified classification. |
Give exceptions a clear path to review.
Dokyumi returns a model-reported confidence map, validation details, and a completed or review status for produced results. Check required fields and your business rules before passing data onward.
A completed extraction describes the extraction result. Your application and reviewers own matching, approvals, routing, and updates to other systems.
Read the response contractChecks for this process
- Legal entity and trading name swapped
- Requested amount entered as a range
- Handwritten contact details that need confirmation
- Revenue frequency omitted or inconsistent with the schema
Prove the fit on a representative batch.
Use several application templates and include handwritten amendments. Check field mapping in a CRM sandbox and confirm that duplicates and incomplete applications reach a review queue.
Compare extracted values with a reviewer’s reference set. Record corrections, unresolved fields, review time, and credits used before connecting downstream actions.
The free plan’s credit limits apply. Assisted pilots are scoped with Dokyumi before work begins.
Expand when the next process is ready
Use paid capacity as application intake becomes continuous. Add schemas or portals for distinct broker channels and extend the process to supporting statements.
For a tailored implementation
Discuss custom volume and schema configuration for partner networks with many application variants.
Talk through document mix and volumeStart small. Add capacity as intake grows.
All self-service plans include the REST API, upload-site webhooks, custom confidence thresholds, and schema inference. Choose by volume, schema count, and upload sites.
Each document uses one credit per 5 pages, rounded up. An 8-page file uses 2 credits. Self-service files can be up to 50 pages; larger files, custom-built schemas, and additional volume are quoted through Enterprise. Full pricing details
Questions about funding application crm intake
Does Dokyumi create the CRM record?
The extraction API returns structured data. Your application or integration performs the CRM write after your own validation and duplicate checks.
Is self-reported revenue verified?
No. Keep application claims distinct from supporting evidence. Your team reconciles stated revenue with the documents it requires.
Can I use one schema for every broker?
Use a shared schema when the required meanings align. Evaluate broker-specific labels and add separate schemas where the requested information differs.
How do I test this workflow on my own documents?
Start free with 25 credits per month, 2 schemas, and 1 branded upload site. The starter schema opens in the schema builder after sign-up. Edit the fields, save it, and upload a representative file through your account or the extraction API. Account documents are stored according to Dokyumi’s privacy policy; contact hello@dokyumi.com for deletion requests and retention requirements.