AI Automation
Clawleaf: AI Voice Reception
A 24/7 AI phone agent that answers, captures caller details, finds the patient and routes the call.
DisciplinesAI Automation
Our roleDesign, build, release
Technologies
Python
PyTorchVision modelsInference at edge
PythonPyTorchVision modelsInference at edge
Clawleaf
The challenge
What was in the way.
Calls came in around the clock and outside office hours they went unanswered — with no record of who called, which patient they were asking about, or what they needed.
Disciplines in scope
Hardware—
Firmware / IoT—
AI / MLIn scope
Web & mobile—
How we built it.
The agent is scoped deliberately narrowly — identify, locate, route — so it stays reliable on the calls that matter instead of improvising on clinical questions. Patient lookup runs live against the care platform mid-call, and anything ambiguous transfers to a person with the context already attached.
01Technical discovery
02Architecture & prototype
03Build & iterate
04Deploy & hand over
AI Voice Reception Agent — answers calls 24/7, captures caller details, locates the patient in the care system and routes to the right team
Deployed for multiple clients, each with its own greeting, routing map and escalation rules
Every call logged with a transcript, the matched patient record and the routing decision
Hands off to a human line whenever intent is unclear or the caller asks for one
01Shipped
Delivered to production and still maintained by the team that built it.02Tested
One test matrix across hardware, firmware and interface — no gaps between layers.03Documented
Runbooks, monitoring and escalation handed over with the system.04Scaled
Grew with usage without re-architecture or a second rebuild.