Use cases › Customer service & contact center
Maccabi Healthcare: how the agent works and how to build one like it
Summary: Maccabi Healthcare runs voice and chat agents for information requests, emergency guidance and appointment booking, serving 2M+ users per the source.
Source: https://www.wonderful.ai/case-studies/healthcare?scLang=en source read via search extract
Why this use case works
Healthcare raises the bar on safety: emergency guidance must follow fixed protocols, and the agent has to recognize when to stop and hand over. Combining routine tasks (booking, info) with a strict escalation path is how a large provider gets volume without taking clinical risk. (Our analysis.)
Agent pattern: Voice agent
A voice agent pipeline: telephony, speech-to-text, an LLM with tool access, text-to-speech, and a structured hand-off to a human when needed. Small teams usually start with a hosted voice-agent platform rather than wiring the parts themselves.
How a smaller team could replicate it
A clinic group can start with appointment booking and FAQ over voice or chat, hard-code red-flag phrases that trigger immediate human or emergency routing, and keep clinical advice out of scope at first. (Our analysis, not a claim made by the source.)
Want a rough business case first? Try the AI agent ROI calculator, or ask us to scope it.
Risks and guardrails
Risks: missing an emergency, giving clinical advice outside scope, and privacy obligations on health data. Guardrails: fixed emergency protocols, conservative escalation thresholds, data handling that meets local health-privacy law, and regular clinician review of transcripts. (Our analysis.)
What to measure
Bookings completed without staff, red-flag detection recall, wait time to reach a human, and patient satisfaction.
Related Customer service & contact center deployments
- Travelers: Travelers: a fully autonomous voice claims agent handles auto first-notice-of-loss. 85–90% of users complete their claim through it.
- LendingTree: LendingTree: a multi-agent mortgage assistant (supervisor + workers, LangGraph/MCP). Over 97% of conversations are handled without escalation.
- ENGIE: ENGIE: an Agentforce agent answers billing/EV questions and switches on smart charging through the SAP API.
- Commerzbank "Bene": Commerzbank "Bene": a chatbot that handles 2M+ chats and resolves 70% of them.
- Amdocs: Amdocs: a telco CX agent resolves complex issues end-to-end.
Part of the AgentStack Atlas catalog of 52 sourced agentic AI deployments. Spotted an error? Email agentstackatlas@mail.grokbot.com.