Building MCP Before MCP Existed: Inside Despegar's Sofia Agent

Why It Matters

Sofia’s modular AI approach lets Despegar scale personalized travel assistance while cutting support costs, positioning the OTA as a pioneer in AI‑first customer journeys.

Key Takeaways

• Sofia’s modular flow lets any team build custom travel agents.
• 30% of users now interact with Sofia across booking journey.
• WhatsApp AI toggle drives real‑time offers and higher conversion.
• Sofia handles simple after‑sales queries, freeing agents for complex issues.
• Future roadmap targets end‑to‑end trip planning and claim automation.

Summary

Despegar’s new AI concierge, Sofia, is a home‑grown travel assistant that predates the industry‑wide MCP standard. The company built a multi‑agent platform where a core "brain" called Chappie powers category‑specific flows—flights, hotels, cars, activities—allowing any squad to create and customize its own conversational experience under central supervision. The rollout emphasizes decentralization: product, engineering, and UX teams own their flows, while a shared foundation ensures consistency. Sofia now handles basic after‑sales questions—flight numbers, vouchers, invoices—via chat and voice, routing complex issues to human agents. KPI tracking shows 30% of customers engage with Sofia, and its first‑booking impact is measured through WhatsApp AI toggles that deliver real‑time offers, bypassing cached results. Examples illustrate Sofia’s evolving scope: users ask simple check‑in queries, while the team envisions full‑task automation like filing delayed‑flight compensation claims. A recent hackathon produced a WhatsApp group‑chat bot that helps friends coordinate trips, showcasing the platform’s potential to move beyond transactional booking into the "dreaming" phase of travel planning. By democratizing AI development across squads and integrating conversational search into core channels, Despegar aims to boost conversion, reduce support costs, and set a new standard for OTA personalization. The strategy signals a broader industry shift toward AI‑driven, end‑to‑end travel experiences.

Original Description

Nicolas Alejandro Bogliolo is the AI PM at Despegar, the largest online travel agency in Latin America, and the engineer-product-hybrid behind Sofia, the GenAI travel concierge that beat most of the OTA world to a working multi-agent system.

Before MCP was a standard and before LangChain was widely adopted, his team had already shipped their own orchestration layer and tool protocol in production. This conversation is a rare look at what it takes to build an agentic system that actually books trips, runs on WhatsApp, and keeps adding capabilities without falling over.

Building MCP Before MCP Existed: Inside Despegar's Sofia Agent // MLOps Podcast #375 with Nicolas Alejandro Bogliolo, AI PM at Despegar

What we cover:

- Chappi, the brain of Sofia: how Despegar built an internal orchestration layer when there was nothing off the shelf- Building "MCP before MCP": the custom tool-calling protocol that predated the Anthropic standard- Multi-agent architecture by vertical: flights, hotels, activities, and cars each own their own flow

- Decentralized agent ownership: how any squad in the company can build a flow with central supervision

- Sofia on WhatsApp: making messaging the consumer control center, the way Slack became it for the enterprise

- The five-phase travel arc Sofia covers: dreaming, planning, anticipation, in-trip, and post-trip

- KPI evolution: why "in-scope conversation rate" topped out near 96 percent and what they measure now

- The flight-delay-claim use case and why filing claims through a chatbot is a perfect agent task

- Group trip planning in WhatsApp groups: the next frontier for travel agents

- Sofia as channel of choice: the WeChat-style vision for an agent that handles your entire trip

- Why Despegar held off on giving Sofia the ability to bargain with customers, for now.

Whether you are building production agents, running an OTA, or just curious about how an AI travel concierge actually works under the hood, this episode is full of grounded, in-production lessons from a team that had to invent the patterns the rest of us are now adopting.

Links and Resources:

Despegar: ⁠https://www.despegar.com⁠

Sofia announcement: ⁠https://investor.despegar.com/news-presentations/news-releases/news-details/2024/Despegar-revolutionizes-the-tourism-industry-introducing-the-regions-first-Generative-AI-Travel-Assistant⁠

Sofia coverage on PhocusWire: ⁠https://www.phocuswire.com/despegar-debuts-genai-travel-assistant-remembers-previous-interactions⁠

MLOps Community: ⁠https://mlops.community⁠

Subscribe for more agent and AI infra deep dives

Timestamps

[00:00] Sophia Travel Concierge AI

[00:38] Sophia Multi-Agent System

[06:00] AI Limitations in Practice

[13:52] Travel Planning Exploration

[18:03] Group Travel Decision Making

[21:32] Agent Ecosystem Design

[30:14] Sofia's Travel Assistant Vision

[33:35] Orchestration and MCP Design

[40:13] Sophia Negotiation Concerns

[40:47] Wrap up