Multichannel concierge agent with voice and WhatsApp
A restaurant group in Mexico City. We built a concierge agent that takes reservations by voice and WhatsApp, releases no-show tables and manages a prioritized waitlist.
Restaurant group (client under NDA)
The host kept getting pulled away to answer the phone and WhatsApp with repetitive questions (hours, availability, location), at the expense of guests in the dining room. No-show tables sat empty with no notification, and the waitlist didn't prioritize regulars over first-timers.
Stack and deliverable
A concierge agent integrated with the restaurant's POS: it takes reservations over WhatsApp and by voice (with synthesized voice), confirms with an advance reminder, releases the table if there's no response after the reservation time and manages the waitlist with priority by visit frequency. It reports daily to the operations manager and monthly to leadership.
What changed in the operation
What we learned
What guests notice is whether the experience beats what they had before: an instant answer instead of a busy line. The critical piece is that escalation to the manager is immediate and obvious whenever something doesn't add up.
How it was built
Technology: WhatsApp Business · Voice · POS API
Delivery: Staged delivery through to production
FAQ · this case
How did this Restaurants & F&B 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 Restaurants & F&B case?
WhatsApp Business · Voice · POS API. 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 Restaurants & F&B?
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 Restaurants & F&B?
A Studio diagnostic with an architect. We identify which processes to automate first and estimate the return for your case.
No cost · No commitment