Appointment confirmation agent + insurer authorizations + prioritized waitlist
A private hospital with multiple specialties. We built an agent that confirms outpatient appointments ahead of time, handles insurer authorizations, frees up no-show slots and reschedules the waitlist by clinical priority — not first come, first served.
Mid-sized private hospital (client under NDA)
Outpatient clinics had a high no-show rate, in line with what's typical for private care in Mexico. The call center confirmed appointments by hand during business hours, but morning appointments — where no-shows clustered — were confirmed too late or not at all. Insurer authorizations (GNP, AXA, MetLife, Atlas, Banorte) were handled by email and phone with no traceability, leading to billing rejections that cost weeks of collections work.
Stack and deliverable
Four components: staggered automatic confirmation via WhatsApp and a bilingual IVR; smart rescheduling when someone cancels, where the agent finds the highest-priority patient on the waitlist by clinical urgency and offers them the slot; insurer authorization pre-validation, which checks whether the patient has an active policy and a covered service, generates the authorization letter pre-filled in the payer's format and sends it for processing before the appointment; and a complete audit trail compliant with Mexico's electronic health record standard, with identity, decision, timestamp and cryptographic signature.
What changed in the operation
What we learned
Rescheduling by clinical priority was what moved the operation most. The reminder on its own helps, but the fundamental change came from the agent offering a cancelled slot to a priority patient on the waitlist instead of 'whoever's next on the list.' The agentic intelligence is in the clinical prioritization, not the reminder.
How it was built
Technology: WhatsApp Business · Voice IVR · Insurer APIs · Hospital PMS · Audit log
Delivery: Staged delivery through to production
FAQ · this case
How did this Private healthcare · Hospital project make it to production?
Staged delivery through to production: design, build, testing with real data and launch. By the end, the client's team was running the agent in production, with observability dashboards and guardrails already configured. Stabilization is part of the delivery.
What tech stack was used in this Private healthcare · Hospital case?
WhatsApp Business · Voice IVR · Insurer APIs · Hospital PMS · Audit log. Each piece was chosen to fit the client's existing systems — no forced migrations, integrating through official APIs wherever they were available.
How are results tracked?
Before the project starts, we agree on an operational baseline with the client, and during stabilization it's reviewed on the operations dashboard. Because of the NDA, we don't publish this client's figures. In the diagnostic we define what to measure in your case.
Can this be replicated at another company in Private healthcare · Hospital?
The pattern is replicable; the specific implementation depends on the current stack, operating volume and internal rules. The Studio diagnostic identifies which pieces apply to your context and estimates the return for your case.
Who runs the agent after the project?
The client's team. Studio hands over the agent running and trains the team on monitoring, prompt adjustments and exception handling. Stabilization support is included for the first few months; after that, an optional monthly retainer is available.
What happens if the AI model changes or gets more expensive?
We don't depend on a single provider. If a model changes or gets more expensive, we move the agent to another one without rebuilding it.
Facing similar challenges in Private healthcare · Hospital?
A Studio diagnostic with an architect. We identify which processes to automate first and estimate the return for your case.
No cost · No commitment