Extract Key Findings from a scan PDF | termina

Downloads the scan PDF attached to the deal, locates the Key Findings page, runs structured LLM extraction over that page, and overrides the LLM’s score_level with a deterministic color-flag signal read directly from the flag squares (and ⚠ glyphs) in the PDF’s scorecard table.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Path parameters

group_idintegerRequired

deal_idintegerRequired

file_idintegerRequired

Response

Successful Response

company_namestring

Company name from the page

overall_assessmentstring

Left-panel narrative assessment text

scan_typestring

Type of scan (e.g., ‘Quality of Growth Scan’)

findingslist of objects

Ordered list of scorecard findings

what_could_go_rightstringDefaults to

Upside scenario text from the bottom of the scorecard table, if present

page_numberintegerDefaults to 0

1-indexed page number where Key Findings was found (set by server)

Errors

422

Unprocessable Entity Error

1	{
2	"company_name": "string",
3	"overall_assessment": "string",
4	"scan_type": "string",
5	"findings": [
6	{
7	"topic": "string",
8	"score_level": "significant_positive",
9	"tldr": "string",
10	"description": "string"
11	}
12	],
13	"what_could_go_right": "",
14	"page_number": 0
15	}