Enrichment Fields
Detailed reference for all fields in the enrichment block of a completed scan.
Overview
The enrichment block contains structured business intelligence extracted from public sources: the company's website, news coverage, regulatory filings, and other publicly accessible information. This data is gathered fresh at scan time by a research agent.
Fields
industry_sector
Type: string
The broad industry classification of the company.
Possible values: Technology · Financial Services · Healthcare · Retail & E-commerce · Manufacturing · Legal & Professional Services · Media & Entertainment · Education · Real Estate · Transportation & Logistics · Energy & Utilities · Government & Public Sector
revenue_band
Type: string
The estimated annual revenue range based on publicly available signals (funding rounds, employee count, pricing, press releases).
Possible values: < $1M · $1M–$10M · $10M–$50M · $50M–$200M · $200M–$1B · > $1B
This is an estimate. If the company has not disclosed revenue, the band is inferred from comparable indicators. Where insufficient data exists to make a reliable estimate, the field may be null.
revenue_model
Type: string
A short description of how the company generates revenue. Examples: "SaaS: annual subscription per insurer client", "Usage-based API pricing", "Marketplace: commission on transactions".
business_operations
Type: string
A 2–4 sentence summary of what the company does, who its customers are, and how it operates. Written for an underwriter audience: focuses on the operational facts relevant to risk assessment.
product_category
Type: string
A specific product classification within the sector. More granular than industry_sector. Examples: "Insurance Technology (Insurtech)", "Medical Imaging AI", "Autonomous Vehicle Software".
product_details
Type: string
A 2–3 sentence description of the core product's mechanics and functionality. Focuses on what the product does technically: how it works, what inputs it takes, and what outputs it produces.
ai_in_product
Type: string
A description of how AI is integrated into the product. Specifically addresses:
- What AI or ML models are used
- What decisions or outputs those models produce
- The degree to which AI operates autonomously vs. with human oversight
This field is the primary input to the ai_intensity and autonomy risk dimensions.
number_of_users
Type: integer | null
The estimated number of end users or customers who interact with the product. This is the primary input to the blast_radius risk dimension. null if insufficient data is available.
Optional field: field_citations
When the scan is created with "include_field_citations": true, the enrichment block includes a field_citations map showing the source URLs used to generate each field:
Fields with no identified sources will not appear in the field_citations map. This feature is intended for audit and compliance use cases where you need to trace every data point to its origin.
Data quality and confidence
Enrichment quality depends on how much public information exists about the company. Companies with:
- A detailed public website
- Press coverage or funding announcements
- Published documentation or case studies
...will yield high-confidence enrichment with all fields populated. Very new companies, stealth startups, or companies with minimal web presence may have null values in some fields, particularly revenue_band and number_of_users.
When questionnaire data is provided at scan creation, it supplements public research and typically improves the completeness and accuracy of all fields: especially ai_in_product and product_details.