Skip to main content
Raga AI

Coex (client: Ardonagh) · Insurance and financial services

Multi-Agent KYC Onboarding

Delivery context

Personally delivered by Raga AI founder Usman Bukhari through Usman Bukhari Ltd before establishing RAGA AI LTD.

Sector
Insurance and financial services

Ardonagh Specialty onboarded clients through a manual analyst workflow, gathering KYC evidence by hand from multiple external registers.

Business challenge

Onboarding took days or weeks, data had to be reconciled across sources with conflicting records, and everything had to hold up in a regulated compliance environment.

What was delivered

  • A multi-agent system gathering and reconciling client data across external registers and internal systems into structured risk summaries
  • Resilient integrations with caching, retry and rate-limit handling so a full check completes within a single analyst sitting
  • Orchestration covering inbox monitoring, document extraction and automatic case creation
  • Authentication, audit logging and role-based access throughout, shortening time-to-onboard

Security, governance and operational considerations

  • Built for a regulated compliance environment: audit logging and role-based access applied throughout
  • Conflicting records across sources reconciled explicitly rather than silently overwritten
Technical implementation
  • Multi-agent system on Azure AI Foundry across Companies House, LexisNexis WorldCompliance and internal PAS
  • Azure Logic Apps orchestration with Document Intelligence extraction and case creation in MongoDB
  • React / TypeScript front end with a FastAPI service layer

Technology stack

  • React / TypeScript
  • FastAPI
  • Azure Logic Apps
  • MongoDB

Related service: AI governance consultancy

Facing something similar?

Request a discovery conversation and we will talk through your workflow, the systems involved and whether this approach would work for you.

View all case studies