Prompts are the new UX. Learn how to craft CX-aware prompts that reflect tone, intent, and journey stage, so Salesforce AI agents feel intuitive, not scripted, and don’t just respond, but resonate.
Dreamforce passes are going fast. Don’t miss the most valuable event in business. Register now.
Register to join Dreamforce in San Francisco, or stream it free on Salesforce+.
Dreamforce is almost here and passes are going fast. Don’t miss your last chance to save $400 by September 26.
Sessions
Explore Dreamforce 2025 sessions.
Browse 1,600+ sessions from 2025 by role, topic, or industry and get inspired for the innovation coming to Dreamforce 2026.
Prompting with Purpose: CX-First AI on Salesforce
Required equipment: Salesforce Events Mobile App required. Please bring your headphones and use Live Session Audio to hear audio and view captions.
, Salesforce CTA, Chief Architect & CX Architect Director, Capgemini
Role: Administrator, Architect, Designer
Industry: Technology
Product: Agentforce
Topic: Agentic AI
Session Level: Intermediate
Session Type: Theater
Session Summary: This session focused on the importance of designing intelligent, context-aware AI agents using Salesforce tools to enhance customer interactions and improve satisfaction. The speaker emphasized the critical role of data quality, tone alignment, and contextual understanding in creating effective agents, illustrating this with examples of customer service scenarios where agents failed to resonate with customers due to lack of personalization. Key innovations such as the Einstein Intent API were highlighted, showcasing how it can dynamically assess customer intent and improve responses while integrating data from Salesforce's Data Cloud. The session underscored the need for governance, continuous testing, and feedback loops to ensure AI agents deliver consistent and scalable results, ultimately enabling human agents to focus on higher-value tasks and escalations.
Key Takeaways:
• The Einstein Intent API can dynamically assess customer intent and context, enabling AI agents to provide more accurate and relevant responses during interactions.
• Effective AI agents rely on properly aligned tone, contextual understanding, and high-quality data orchestration, ensuring they resonate with customers and enhance their experience.
• Governance, continuous testing, and feedback mechanisms are essential to scaling AI agents and maintaining their effectiveness in real-world scenarios over time.
Session Summary Feedback: Report a Concern
