Engine accelerates AI agent development on the Salesforce Platform

Engine, a $2.1 billion travel platform, leveraged the Salesforce Platform to dramatically accelerate the development and deployment of AI agents. They reduced the time to build their first AI agent, Eva, from months to just 12 days, and significantly improved testing and integration processes for subsequent agents.

Engine · over 1,000 employees.

Traditional development options for AI agents were either limited (low-code) or took months (custom development), relying heavily on a small group of developers. Delivering innovations like their customer self-service agent Eva required multiple tools and long release cycles. Writing tests for new functionalities took days, and building and refining complex integrations typically consumed weeks.

Engine now leverages the Salesforce Platform, including Agentforce, Builder, Apex, and Vibes, within a hybrid development environment. This unified system allows them to design, test, and deploy AI agents rapidly. They can reuse existing actions and Apex code, making the first AI agent, Eva, a foundation for future agents. Testing processes are significantly more efficient, now taking hours instead of days, and AI-assisted tools streamline complex integrations from weeks to a few days.

Engine developed their first AI agent, Eva, in just 12 days, a process that would have previously taken months. Their second agent was delivered in days, not weeks, due to a modular approach. Testing time for changes was reduced from days to a few hours, and complex integrations were accelerated from multi-week efforts to a few days. This has enabled faster releases with fewer risks and resulted in 50% of chat requests being resolved agentically.