Insura
AI assistant for policy terms and conditions.
Help employees identify the terms that apply to a customer enquiry more quickly.
Trusted by leading organisations
Why we built this,
Insurers and insurance intermediaries receive questions every day about whether specific situations are covered. To answer them, staff need to consult policy terms, clauses, exceptions and information about deductibles.
That knowledge is often spread across different documents and product variants. As a result, answering questions takes a lot of time, and staff depend on colleagues with extensive product knowledge. There is also a risk that similar questions will be interpreted differently.
Insura makes policy terms accessible through a single digital assistant. Staff ask a question in everyday language and receive relevant information from the connected policy documents.
What you can expect,
One place for questions about policy terms
Insura searches the connected policy documentation based on an employee’s question. This means they do not have to look up each document or clause separately.
The questions Insura can answer depend on which products, policy terms and additional documentation are available.
Answers based on selected sources
The assistant bases its answers on the sources you make available. Where possible, it shows which information it used so an employee can check the answer.
You decide:
- Which policy documents to connect
- Which products the assistant is used for
- Which employees have access
- When further review is needed
Support when assessing customer queries
Insura can help employees find relevant terms and exceptions. The assistant does not make a final coverage decision when interpretation, additional information or professional judgement is needed.
This keeps human review part of the process, particularly for exceptions and questions with more significant consequences for the customer.
Our approach,
-
Start with a clearly defined insurance product
We start with a clear selection of products, documents and common customer questions. This keeps the first application manageable and lets subject matter experts assess whether the answers are useful.
-
Connect and test policy documents
We make the selected policy terms and additional knowledge sources accessible to Insura. We then test the assistant with questions from day-to-day work. We check whether it finds the right information and whether it is clear when a question cannot be answered using the available sources.
-
Expand in a targeted way
After the first application, Insura can be expanded to cover other insurance products, document types or kinds of customer questions. We also agree on how the sources will be managed. This allows new policy terms and product changes to be incorporated in a controlled way.
Not a general-purpose chatbot, but a focused assistant that helps employees apply policy terms carefully.
This helps Insura with the research, while the final assessment remains with the employee.
What we’ve built before,
Three projects from our work with data and AI.
Further reading
Blogs and in-depth content from our team.
Three lessons from our AI projects
What we learned from dozens of AI projects: start with the decision, treat data quality as an organisational issue and arrange management in advance.
From pilot to production: why most AI projects stall
Most AI projects stall not because of the technology, but because of data, teams and processes. Read what it takes to move from pilot to production.
Responsible AI: from principles to practice
AI is developing rapidly. New models emerge almost every week, and more and more organisations are experimenting with AI.
Get in touch
Stef Stoelwinder
Business DevelopmentE-mail info@datasciencelab.nl
Phone +31 (0)20 3636 724
Frequently asked questions,
Insura can be configured using selected policy terms and additional product documentation. Which sources are suitable depends on the insurance products and the questions you want the assistant to handle. For reliable use, the documents must be up to date, complete and clearly managed.
Insura helps staff find relevant terms, clauses and exclusions. Whether the assistant can also help reach a conclusion depends on the complexity of the question and the information available. When interpretation or further assessment is needed, a member of staff remains responsible for the decision.
New and amended documents must be added to the knowledge sources through a controlled process. That is why we establish who is responsible for managing them and how changes are processed. The assistant can only answer based on the information available at the time.
An assistant with a defined scope works with selected documents and within a clearly specified area of use. This makes it easier to check which information is used and when a question falls outside that area. Validation and human review are still needed.
Make it clear that Insura supports the research process and does not automatically take over every coverage decision. Source references, clear usage rules and escalation when there is doubt help staff assess answers critically. Training and clear responsibilities are just as important as the technology.