customer_support · healthcare · workflow
Doctolib builds Alfred, an agentic AI system for healthcare support with human-in-the-loop action execution
As Doctolib's platform grew, support request volume increased and linearly scaling the support team was unsustainable, while conventional chatbots frustrated users with rigid decision trees and free-text fields that delivered nothing actionable.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits support request
A health professional sends Alfred a support request describing what they need.
Tools used
LangGraphLiteral.aiLLMRAGKeycloak
Outcome
Doctolib built Alfred as a proof-of-concept agentic AI system handling calendar access management, with a human-in-the-loop design ensuring the LLM never directly executes sensitive actions, and plans to expand to additional support scenarios.
Results
Time saved~1,700
Volume~17,000
Grounding & classification
Source type: technical build writeup
24 fields verified against source quotes.
agentic workflowai agentconversational aimulti agent workflowragknowledge basebuilder submittedfailure mode describedhuman review describednamed customertools describedworkflow describedhealthcarecost reductionemployee productivitytechnical build writeupcustomer supportagentic task executionai draft human approval