Dec 8th, 2023

ARAG is a leading provider of legal expenses insurance and assistance products for intermediaries, insurers and solicitors. It has won several industry awards, achieved record profits and celebrated its 10th anniversary in 2016.

As the Generative AI SME on the AI-Driven Claims Handling project, we are currently set to shorten the average claim handling time from 9 hours to 3 hours using GenAI.

Background & Objectives


In recent years, the insurance industry has undergone significant transformation. Driven by tech innovation, companies recognise the potential of AI to help improve their operations and enhance their ability to serve customers.

ARAG is on a journey to leverage these new technologies, and the opportunity to continuously improve on their services. The first of which is their core service in claims-handling.


ARAG’s goal is simple to state, yet ambitious to achieve:
Shorten the average claim handling time from 9 hours to 3 hours.

To help achieve the goal, the key project objectives outlined were:

  • Faster claims handling by automating document processing
  • Improved customer experience through reduced administrative burden
  • Cost savings by automating routine tasks


As the AI Principal and Generative AI SME the project, my responsibilities were:


Architect enterprise platform solutions in line with the governance framework to achieve the 6 key deliverables detailed by ARAG utilising Azure and OpenAI

Stakeholder Management

Work with internal stakeholders across the management team to agree on project requirements, build the enterprise architecture, delivery plan, governance framework and technical approach


As an SME, responsible for the strategic direction of the AI tools, solutions and governance to dictate the best approach to achieving business outcomes

Security & Privacy Governance

Discussion and ideation of integrating existing architecture and security governance framework in line with company policy

Commercials & SOW

Validation and approval of the delivery tech team, size shape and structure; including requirements and scope.


ARai: AI co-pilot PoC

A tested and working POC solution across data and backend, with a minimal Frontend solution to prove initial assumptions and technical feasibility of the AI solution.

Governance and Ethics Framework

A detailed Generative AI Governance framework that covers the Responsible, Ethical, Secure, Accountable and Transparent use of AI in claims handling.

Future Product Roadmap

A high level delivery plan including skills & roles required to take the POC into production.

Future Tech and Team Design

A high level roadmap that captures technical tasks and priority features for taking the solution into the the next phase.

Tools & Technologies

This project branched into many varying aspects of engineering and technologies, and a few tools were used.

  • Architecture
  • Jira
  • Confluence
  • SSH
  • Python
  • AI
  • Data
  • Azure
  • Gradio
  • LangChain
  • Pinecone
  • LanceDB
  • OpenAI
  • ChatGPT
  • GPT-4
  • CodeLlama
  • Github Copilot
  • VS Code
  • Microsoft Office Suite