Skip to main content
Use CasesFinancial services & insurancePrivate Sector

Agent assist and call summarisation for member advocates

Gives advocates the member's status, relevant rules and next-best action during calls and writes the summary afterwards

Human approves every decisionValue: Cost
Who we serve
Private Sector
Category
Financial services & insurance
Value
Cost
Human role
Human approves every decision
Maturity

The problem

Without agent assist and call summarisation for member advocates, member advocates carry this work manually, case by case, working through call audio, member records, rules by hand, with the cost, delay and error rate that implies.

How it works

Agent assist and call summarisation for member advocates gives advocates the member's status, relevant rules and next-best action during calls and writes the summary afterwards. The approach relies on real-time retrieval, speech-to-text, summarisation. It draws on call audio, member records, rules and is typically owned by member advocates. The main constraint is accuracy of live guidance; consent for transcription. Where the human comes in: advocates decide what to say; summaries reviewed before saving. It is in production at multiple organisations; examples include Humana Google Cloud Agent Assist for 20,000+ advocates.

Where the human comes in

Human approves every decision

Advocates decide what to say; summaries reviewed before saving

What it needs

Call audio, member records, rules

What to plan for

Accuracy of live guidance; consent for transcription

In the field

Humana Google Cloud Agent Assist for 20,000+ advocates

Public deployments by other organizations, listed for context. Not Sphere projects.

More in Private Sector

See all
  • Acrisure AI operating system for insurance brokerage

    Building an AI operating system for insurance on Ontology, Foundry and AIP

    Human approves every decisionValue: Revenue
  • Aerial and drone asset inspection

    Vision on drone and satellite imagery for lines and vegetation

    Human approves every decisionValue: Risk management
  • AI Investigator for financial crime and compliance

    Agent-driven investigation embedding Lucinity's AI-native capabilities into Oracle's financial-crime platform to support investigator workflows

    Human approves every decisionValue: Risk management