In-house Financial Services United Kingdom Company newsroom

Allianz United Kingdom

Enterprise Knowledge Search

Allianz UK underwriters had to search through as many as 70 lengthy guidance documents during underwriting, spending significant time finding the right rules and answers, which slowed response times, risked missing critical information, and made it harder for junior staff to get timely guidance.

260 Property and Liability Underwriters
800-page guidance document
as many as 70 such documents
nearly 3,000 questions from 190 users

Reported impact

Business outcome

BRIAN helps underwriters find guidance faster, make better-informed decisions with greater confidence, improve speed and accuracy in day-to-day work, support junior underwriter onboarding, and create a scalable foundation for expansion into more documents, business lines, and adjacent functions such as Claims.

  • Productivity Improvement
  • Scalability

Solution

Allianz UK built BRIAN, an in-house generative AI Underwriter Guidance Tool, to help commercial underwriters retrieve policy and risk guidance from internal documentation. The system ingests uploaded underwriting guides, currently covering all Property and Casualty and Specialty line documents, and digests them into a searchable knowledge base. Underwriters ask natural-language questions in BRIAN’s interface, and the tool returns concise answers generated only from the uploaded source documents. To support traceability and compliance, each response also links directly to the exact section of the original guidance used to generate the answer, including very large documents. Allianz says the tool was developed jointly by business, transformation, technology, and datalab teams, is already in full production, and is being scaled across more users, documents, and business lines.

Data flow

Internal underwriting guides for Property and Casualty and Specialty lines are uploaded into BRIAN, which digests the documents into its database. Underwriters submit natural-language questions through the tool, BRIAN scans the relevant guides, generates a concise answer sourced only from those documents, and returns the answer together with a link to the exact section of the original guidance.

Solution architecture

1 components · 1 layer
  1. Uncategorized
    • BRIAN Generative AI underwriter guidance tool that digests internal underwriting guides and returns concise answers with direct links to the source sections used.

Architecture clues

  • Allianz plans to add more guides and materials in 2025 and extend the approach to other business areas such as Claims.
  • BRIAN currently covers all Property and Casualty and Specialty line documents.
  • Each answer includes a direct link to the specific source section used.
  • The source says responses are generated exclusively from uploaded documents to support compliance and reliability.
  • The tool is in full production after a pilot phase.

Evidence from the source

"BRIAN is now in full production and ready to scale. BRIAN digests underwriting guides – currently all Property and Casualty (P&C) and Specialty line documents – and allows underwriters to ask specific questions and receive concise, accurate responses."
"BRIAN was developed as a collaboration between Allianz UK business, transformation and technology teams, together with datalab"
"Crucially, the information is sourced exclusively from the uploaded documents, ensuring compliance and reliability."
"Currently, BRIAN is being used by 260 Property and Liability Underwriters across all Allianz UK commercial offices, with plans to scale to all 600+ underwriters within 12 months"
"Following a successful pilot phase with nearly 3,000 questions from 190 users"
"It provides a concise answer, and it also includes a direct link to the specific section of the 800-page guidance document used to generate the response."
"This inefficiency can result in slower response times, critical information being missed and a less-than-ideal experience for brokers and customers."
"With as many as 70 such documents to refer to, underwriters can spend upwards of two hours a week simply sifting through these resources"
Transparency Evidence & methodology 75/100 reference value · 92% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value75/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence92%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    8 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Allianz United Kingdom

    Allianz United Kingdom customer story

    First-party
    https://www.allianz.com/en/mediacenter/news/articles/250211-aI-at-allianz-how-ai-is-cracking-complexity-for-underwriters.html
    Source type
    Customer-published story
    Published
    Feb 11, 2025
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Feb 11, 2025 · Allianz · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.