Explore how Salesforce brought personalization into Agentforce by using AI to transform free-form conversations into structured user intent, and much more.

The Salesforce Engineering Blog offers a deep dive into Salesforce technologies, providing technical insights, best practices, and real-world examples. Developers can explore topics such as Salesforce development, architecture, and integrations, gaining  knowledge to build innovative solutions on the Salesforce platform. With contributions from Salesforce engineers and industry experts, the blog serves as a resource for the Salesforce community.

Salesforce Engineering

Salesforce's Data 360 Personalization team built intent-based recommendations for Agentforce by transforming free-form conversations into structured user intent using LLMs. The system addresses cold-start scenarios through semantic catalog modeling with vector embeddings, and integrates real-time conversational intent with historical behavioral signals in a hybrid ML architecture. Key innovations include the "Understand User Intent" Agentforce action for extracting structured intent from conversations, sub-second data ingestion via Data 360, and AI-assisted validation using synthetic scenarios and LLM-as-a-judge frameworks. The architecture balances immediate conversational context against long-term user behavior while maintaining low latency across Salesforce's multi-system ecosystem.

Agentforce: Enabling Conversational Recommendations with AI-Driven Intent