Blits.ai
Meet Blits.ai at Singapore FinTech FestivalNovember 18 to 20, 2026 · Singapore · Stand 3-SK-30
Book a 1:1 →

Business function

AI use cases for underwriting

The most documented AI use cases for underwriting are underwriting submission triage, SME cash flow underwriting and underwriting risk assessment copilot, across 55 public deployments by 54 organizations. Assessing and pricing risk before a policy or facility is written.

Use cases
10
Deployments
55
Organizations
54
Outcome disclosed
58%

The 10 most common AI use cases for underwriting

Ranked by the number of organizations with a public deployment, as of 11 November 2026.

  1. 1
    AI for commercial underwriting submission intake and triage

    AI that reads incoming broker submissions for commercial insurance so underwriters open a complete, prioritized file instead of an inbox.

    9 organizations
    about 98% accuracy
    one deployment, organization claim
  2. 2
    AI cash flow underwriting for small business loans

    SME cash flow underwriting is an underwriting engine that assesses a small business's repayment capacity from live bank transactions and payment flows, instead of audited accounts, for lenders.

    8 organizations
  3. 3
    AI copilot for underwriting risk assessment

    An underwriting risk assessment copilot is an AI tool that assembles everything relevant to a risk, such as the submission, loss history and underwriting guidelines, for an insurance underwriter.

    8 organizations
    50% cycle time reduction
    one deployment, vendor claim
  4. 4
    AI credit scoring with alternative data for thin file applicants

    Alternative data credit scoring is a machine learning model that adds consumer permissioned data to credit bureau data, so a lender can assess applicants with thin or no credit files.

    8 organizations
    at least 90% automation rate
    one deployment, organization claim
  5. 5
    AI agent for corporate credit analysis and credit memo drafting

    AI credit underwriting and memo drafting is an AI agent that drafts a committee ready credit memo for a corporate borrower, for the relationship and credit teams to review.

    6 organizations
    96% cycle time reduction
    one deployment, vendor claim
  6. 6
    AI for insurance renewal processing and customer retention

    Renewal and retention AI prepares and runs the insurance renewal cycle, digitizing renewal submissions and changes in risk for underwriters and flagging policies at risk of lapsing or leaving.

    5 organizations
    100% automation rate
    one deployment, vendor claim
  7. 7
    AI aerial imagery risk scoring for property insurance underwriting

    AI property risk scoring reads aerial imagery to rate roof condition, wildfire exposure and other building features at quote, so underwriters inspect fewer homes.

    4 organizations
    at least 95% accuracy
    one deployment, organization claim
  8. 8
    AI mortgage underwriting decision engine

    A mortgage underwriting decision engine is AI that reads a loan file, applies the lender's and investors' guidelines, and returns an approve, refer or open conditions status for each loan.

    4 organizations
    about 50% productivity gain
    one deployment, vendor claim
  9. 9
    AI straight through underwriting for small business cyber insurance

    Straight through cyber underwriting is AI that scans a small business's external footprint, scores its cyber risk and issues a bindable quote without an underwriter touching it.

    4 organizations
    50% cycle time reduction
    one deployment, organization claim
  10. 10
    AI summarization of medical evidence for life and health underwriting

    AI medical evidence summarization reads the medical records behind a life or health insurance application and turns them into a structured, cited summary for the underwriter.

    4 organizations
    about 50% cycle time reduction
    one deployment, organization claim

10 Underwriting use cases

54 organizations in 18 countries run these use cases in public. 58% of those 55 deployments disclose a measurable outcome.

Insurance

AI aerial imagery risk scoring for property insurance underwriting

AI property risk scoring reads aerial imagery to rate roof condition, wildfire exposure and other building features at quote, so underwriters inspect fewer homes. It turns an address into a score and a set of flags that feed the insurer's eligibility, inspection and pricing rules, and the underwriter or the rules engine keeps the decision.

Deployments
4 public, best grade C
Reported accuracy
at least 95%
Florida Peninsula Insurance Company, organization claim
Banking

AI agent for corporate credit analysis and credit memo drafting

AI credit underwriting and memo drafting is an AI agent that drafts a committee ready credit memo for a corporate borrower, for the relationship and credit teams to review. It gathers the borrower's documents and data, spreads the financials into the bank's template, calculates ratios and covenant headroom, pulls bureau and news information, and links every figure to its source for the team to challenge, complete and sign.

Deployments
6 public, best grade B
Reported cycle time reduction
96%
Kuwait Finance House, vendor claim
Banking

AI cash flow underwriting for small business loans

SME cash flow underwriting is an underwriting engine that assesses a small business's repayment capacity from live bank transactions and payment flows, instead of audited accounts, for lenders. It also draws on point of sale data, receivables and accounting data, and returns a decision recommendation with the evidence and reasons behind it.

Deployments
8 public, best grade B
Autonomy
Supervised agent
Insurance

AI copilot for underwriting risk assessment

An underwriting risk assessment copilot is an AI tool that assembles everything relevant to a risk, such as the submission, loss history and underwriting guidelines, for an insurance underwriter. It also gathers third party data and public information, highlights exposures and gaps against the insurer's underwriting guidelines, and drafts the underwriting narrative or referral note, while the underwriter makes and signs every decision.

Deployments
8 public, best grade B
Reported cycle time reduction
50%
Generali Global Corporate & Commercial, vendor claim
BankingPayments and cards

AI credit scoring with alternative data for thin file applicants

Alternative data credit scoring is a machine learning model that adds consumer permissioned data to credit bureau data, so a lender can assess applicants with thin or no credit files. The alternative data includes bank account cash flow, rent, utility and telco payments or data from partner platforms, and the model returns a decision with specific reasons.

Deployments
8 public, best grade B
Reported automation rate
at least 90%
Upstart Holdings, organization claim
Insurance

AI for commercial underwriting submission intake and triage

AI that reads incoming broker submissions for commercial insurance so underwriters open a complete, prioritized file instead of an inbox. It reads emails, applications, schedules of values, loss runs and supplements, extracts the risk data into a structured record, checks clearance and appetite, and enriches and ranks the risk with internal and third party data.

Deployments
9 public, best grade B
Reported accuracy
about 98%
Paragon Insurance Group, organization claim
Insurance

AI for insurance renewal processing and customer retention

Renewal and retention AI prepares and runs the insurance renewal cycle, digitizing renewal submissions and changes in risk for underwriters and flagging policies at risk of lapsing or leaving. It also prepares the renewal conversation and answers customers' renewal questions, while renewal prices stay governed by the insurer's pricing rules and fair value obligations.

Deployments
5 public, best grade B
Reported automation rate
100%
JAGADIRI, vendor claim
BankingReal estate

AI mortgage underwriting decision engine

A mortgage underwriting decision engine is AI that reads a loan file, applies the lender's and investors' guidelines, and returns an approve, refer or open conditions status for each loan. It sits above document and income checks, and underwriters handle the files it refers.

Deployments
4 public, best grade B
Reported productivity gain
about 50%
NEO Home Loans, vendor claim
Insurance

AI straight through underwriting for small business cyber insurance

Straight through cyber underwriting is AI that scans a small business's external footprint, scores its cyber risk and issues a bindable quote without an underwriter touching it. Flagged or large risks are referred to an underwriter, and the corrections underwriters make can be used to retrain the model.

Deployments
4 public, best grade B
Reported cycle time reduction
50%
Coalition, organization claim
Insurance

AI summarization of medical evidence for life and health underwriting

AI medical evidence summarization reads the medical records behind a life or health insurance application and turns them into a structured, cited summary for the underwriter. The records include attending physician statements, electronic health records, lab results and disclosures, and the summary covers conditions, treatments and dates, mapped to the insurer's underwriting manual so the underwriter can decide faster and more consistently.

Deployments
4 public, best grade B
Reported cycle time reduction
about 50%
Aviva, organization claim

What the evidence says

Computed from the 55 public deployments behind these use cases. Numbers update with every checked record.

Benchmarks with at least 3 pooled values

Benchmarks across Underwriting use cases
KPIMedianReported rangeData pointsClaimed by
Cycle time reduction50%
50% to 96%
42 organization, 2 vendor
Industries these use cases also serve
AI patterns used
Deployments by stage
  • Announced
    5
  • Pilot
    1
  • Production
    39
  • Scaled
    10
Public deployments by region
  • North America
    31
  • Asia Pacific
    10
  • Europe
    6
  • Global
    5
  • Middle East
    2
  • Latin America
    1

Organizations with a public deployment

  • AXIS Capital
  • Accelerant Holdings
  • American International Group
  • Arch Capital Group
  • At-Bay
  • Atlanticus
  • Aviva
  • Banesco USA
  • Banestes
  • Better Home & Finance Holding Company
  • Bowhead Specialty
  • CNA Financial
  • CSAA Insurance Group
  • California FAIR Plan Association
  • Chase
  • Citi
  • Coalition
  • Cowbell
  • DBS Bank
  • Florida Peninsula Insurance Company
  • Fora Financial
  • GXS Bank
  • Generali Global Corporate & Commercial
  • Golden 1 Credit Union
  • Hiscox
  • ING
  • JAGADIRI
  • Kapitus
  • Kinsale Capital Group
  • Kuwait Finance House
  • MYbank
  • Manulife
  • Markel
  • NEO Home Loans
  • National Australia Bank
  • Nsure.com
  • OakNorth Bank
  • Paragon Insurance Group
  • Patelco Credit Union
  • PayPal
  • Prudential plc
  • SBLI
  • Shinhan Bank
  • Skyward Specialty Insurance Group
  • State Bank of India
  • Sukoon Insurance
  • Sumitomo Mitsui Banking Corporation
  • TAB Bank
  • United Wholesale Mortgage (UWM)
  • Upstart Holdings
  • Upstart Network
  • Zurich Australia
  • Zurich Insurance Group
  • Zurich North America

Frequently asked questions

What are the most common AI use cases for underwriting?
Counted by organizations with a public deployment, the most common are AI for commercial underwriting submission intake and triage (9 organizations), AI cash flow underwriting for small business loans (8 organizations), AI copilot for underwriting risk assessment (8 organizations), AI credit scoring with alternative data for thin file applicants (8 organizations) and AI agent for corporate credit analysis and credit memo drafting (6 organizations). The library documents 10 AI use cases for underwriting, 10 of them with a public deployment: 55 deployments by 54 organizations in 18 countries.
How many of these AI deployments are live in production?
49 of the 55 public deployments are live: 39 in production and 10 scaled across the organization. 1 are pilots and 5 are announced.
Which AI use cases for underwriting are high risk under the EU AI Act?
3 use cases fall in the high risk tier: AI credit scoring with alternative data for thin file applicants, AI mortgage underwriting decision engine and AI summarization of medical evidence for life and health underwriting. For 5 other use cases the tier depends on design, for example whether the system decides on access to an essential service. Each use case page explains its tier and what it requires. This is not legal advice.
Where do these numbers come from?
From the Blits.ai AI Use Case Library. Every deployment is a public record of a named organization with a cited source, and every number is computed from those records. Data as of 11 November 2026.

Explore the library

All AI use cases

Search and filter the whole library.

State of AI Use Cases

Aggregate findings across every record.

KPI benchmarks

Definitions and reported values per KPI.

Methodology

How every record is verified and graded.