Case study, Travel & Hospitality

A blocked WhatsApp inbox, turned into a 24/7 AI sales channel

CoNDENSE.tech built ARIA, a production conversational agent on WhatsApp Business API with Claude as its reasoning core, taking Erga Tourism from missed messages to prefilled checkout carts in seconds.

ARIA answering a pre-sales question on WhatsApp about experiences in Villasimius

15: live tools on Erga's booking API: catalog, availability, pricing and orders
~10 sec: median time from customer message to agent reply, live bookings included
~1 in 2: prefilled checkout carts from the agent converting to a paid order
4 / 5: outbound replies written by the AI, freeing staff for cases that need judgment

The challenge

Five out of ten potential customers were already lost

Erga Tourism is a ~20-person incoming DMC selling excursions, car and boat rentals, airport transfers and ticketing across Sicily, Sardinia, Puglia and Umbria. In high season it fields more than 100 contacts a day, split evenly between pre-sales and post-sales.

Phone was the primary channel; WhatsApp existed but was fragmented across different numbers per brand and connected to nothing. An earlier attempt at a manually staffed chat had already been shut down as operationally unsustainable, and product knowledge was scattered across four separate backoffice systems, so even a simple availability check required a human to go and look.

By the team's own estimate, roughly five out of ten potential customers were already being lost for lack of a timely answer.

At a glance

Customer: Erga Tourism (Erga S.r.l.) Incoming DMC, Sicily & Sardinia (est. 2014)
Industry: Travel & Tourism, incoming DMC
Use case: Customer-facing conversational commerce on WhatsApp
Numbers live: Erga Tourism + VOI Concierge
Live since: August 2026
Claude Sonnet 4.6: Production agent runtime
Claude Opus 4.8: Evaluation harness judge

The solution

ARIA: a production agent, not a scripted chatbot

Claude sits at the reasoning core of a WhatsApp Business API agent, wired to Erga's own systems with deterministic tools, so it can actually complete a booking — not just answer questions about one.

Working memory

Claude is the single writer of conversation state, holding the thread across slot-filling, corrections and mid-conversation changes, even across sessions.
Fifteen tools

Live calls to Erga's booking API for catalog, availability and pricing, across an eight-step order flow.
Prefilled cart

A prefilled guest-checkout cart that turns a conversation straight into a ready-to-pay order.
Bilingual knowledge

A hybrid knowledge layer with cross-lingual embeddings answers pre- and post-sales questions in the customer's own language, auto-detected from the first message.

Erga's staff can oversee and manage conversations from a multi-tenant operator console with a WhatsApp-Web-like inbox and seamless bot↔human takeover, backed by a full audit log and analytics.

Continuous evaluation aligned with business metrics

Every iteration of the agent is validated against business-critical outcomes rather than subjective impressions. End-to-end multi-turn purchase simulations and blind head-to-head evaluations on actual production conversations safeguard conversion rates, booking accuracy, and brand consistency at every release.

The roadmap

What's next

Building on the same Claude-powered runtime, Erga is now automating outbound quote generation for sales campaigns: an agent that qualifies leads in real time over WhatsApp, pulls live pricing from Erga's API, and drafts a branded quote for human approval before it ever reaches the customer.

Partners on this project

Select Services Partner

Anthropic

Our Anthropic-certified engineers build Claude agents and workflows grounded in your data and run them in production, on the Claude API or on Amazon Bedrock in the EU.

Claude in production

Advanced Tier Services Partner

AWS

Engineers with the AWS Forward Deployed Engineer Validated credential migrate, modernize and run platforms on AWS, as code, on containers or serverless.

Building on AWS