How Hawksmoor turned missed restaurant calls into bookings with a PolyAI agent
UK restaurant group Hawksmoor deployed a PolyAI voice agent that answers calls and books tables across its 14 sites. PolyAI reports high call volumes handled and better conversion than in-restaurant calls.
The problem
Floor staff couldn't answer phones during busy service, and after-hours calls went to voicemail. The group missed around 42,000 calls a year, 20% of total call volume, and didn't know why.
How they did it
- Connected the agent directly to Hawksmoor's table availability, so callers see the same inventory as other channels.
- Rolled it out site by site to protect quality.
- Tuned the agent's voice to match the brand's tone.
- Used Agent Studio so the team can update menus and handle last-minute closures themselves.
Results
- PolyAI reports 20k calls answered every month and 80,000 covers booked since July 2025.
- The 20% missed call rate was reduced to zero, with a 90% guest satisfaction score.
- Conversion through the agent is 11–12%, compared with 8–9% when calls were handled in the restaurant.
As reported by the source (PolyAI customer story); AgentGid did not measure these figures.
This suits multi-site hospitality groups with a booking system that exposes live availability, plus someone who can own integration and rollout. PolyAI bills per minute with no published rate, so cost has to be quoted through a demo, and the call, booking and conversion figures are vendor-reported. A smaller team could test Rasa (Free), though it is a build-it-yourself framework and its free license caps usage at one bot and 1,000 external conversations a month.
The agent used here
Similar use cases
Triage support tickets with an n8n AI Agent and confidence-based routing
An n8n workflow cleans and validates incoming tickets with plain code nodes, uses an AI Agent only to classify urgency and type, and routes each ticket based on how confident the …
The suggested routing: above 0.85 processes autonomously, 0.6-0.85 is processed but flagged for review, and below 0.6 goes to a human.
How Sun & Ski Sports used a Sierra agent for service and product advice
Texas outdoor retailer Sun & Ski Sports launched a Sierra agent called 'Sunny'. It started with returns and order status and grew into giving product advice on product pages. Sier…
Sierra reports a 3x increase in product page conversion for customers who engage with the agent.
How OBI handled peak-season service calls with Parloa voice agents
European home-improvement retailer OBI deployed Parloa voice agents in several countries to answer routine calls and route complex ones. Parloa reports high monthly volume, solid …
Parloa reports 45,000 monthly inquiries handled by AI agents and 89% customer satisfaction (CSAT).