All videos
0:00 / 0:00
ai

Salesforce Headless 360 Demo: Build AI Agents That Work Anywhere

Salesforce Product Center5 August 2026Watch on YouTube

Part of series

Ep. 10 · Agentforce Coworker Build

View the series

Description

See Salesforce Headless 360 in action, the agentic platform that lets you deploy AI agents and Salesforce capabilities onto any surface, from Slack to React apps to mobile. This demo shows how developers can build with coding agents using MCP tools, APIs, and CLI commands, while keeping data, metadata, business logic, and governance on the trusted Salesforce core. Salesforce Headless 360 gives builders the tools they need to create multi-surface agentic experiences without rebuilding your logic for every channel. Whether you're exploring headless architecture for the first time or looking to scale AI agents across your enterprise, this demo walks through the full developer workflow. In this video, you'll learn how to: Use Agentforce Vibes and MCP tools to build AI agents with Salesforce org context Inspect metadata, data models, and Salesforce capabilities directly from a coding agent Create, test, and deploy an Agentforce Service agent with topic routing, guardrails, and escalation behavior Define UI components once with the Agentforce experience layer and render them across Slack, React, mobile, and more Move from prompt to working interface quickly using Salesforce-specific development guidance TIMESTAMPS 0:00 – Introduction to Salesforce Headless 360 0:20 – Demo overview: Connected Executive Education on Salesforce 0:40 – Slack integration: Agentforce response in the flow of work 1:05 – Behind the scenes: Agentforce Vibes and the builder environment 1:30 – Choosing your AI agent framework (OpenAI vs. Anthropic harnesses) 1:55 – MCP tools: Salesforce capabilities available directly to coding agents 2:20 – Skills and Salesforce-specific guidance for agent development 2:50 – Retrieving org metadata with parallel agents 3:15 – Metadata visualizer: understanding the learning management model 3:45 – Creating the CE service agent with a prompt 4:20 – Testing and tracing agent behavior before release 5:00 – Deploying the agent back to the Salesforce org 5:30 – Agentforce experience layer: define UI once, render everywhere 6:00 – Multi-surface preview: Slack, ChatGPT-style, and default card 6:30 – React app integration for program operations 7:05 – Live preview and production app demo 7:35 – Mobile experience with the learner card 7:55 – Conclusion: Headless 360 and the trusted Salesforce core RESOURCES & LINKS Explore Salesforce Headless 360: salesforce.com/headless Learn more about Agentforce for Developers: salesforce.com/agentforce/developers/vibe-coding Read the guide on Agentic AI: salesforce.com/agentforce/what-is-agentic-ai Subscribe to Salesforce: bit.ly/SalesforceSubscribe #SalesforceHeadless360 #Agentforce #AIAgents #AgenticAI --------- Subscribe to Salesforce’s YouTube Channel: http://bit.ly/SalesforceSubscribe Learn more about Salesforce: https://www.salesforce.com Facebook: https://www.facebook.com/salesforce Twitter: https://www.twitter.com/salesforce Instagram: https://www.instagram.com/salesforce LinkedIn: https://www.linkedin.com/company/salesforce About Salesforce: Improve customer relationships with Salesforce, the #1 AI CRM where humans with agents drive customer success together. Our integrated platform pairs your unified customer data with trusted agents that can assist, take action autonomously, and hand off seamlessly to your employees in sales, service, marketing, commerce, and more. Disclaimer: This video is for demonstration purposes only. All account data depicted is fictional and does not contain personally identifiable information (PII). This content is intended solely to illustrate product functionality in a simulated environment.

What you'll learn

  • Salesforce Headless 360 enables developers to deploy AI agents across multiple surfaces like Slack, React apps, and mobile without rebuilding logic for each channel
  • MCP tools and Agentforce Vibes give agents direct access to Salesforce capabilities, metadata, and org context while being managed as code
  • The Agentforce Experience Layer defines UI components once and automatically renders them across different channels, accelerating quick deployment
  • Developers can test and trace agent behavior before deploying to the Salesforce org, with built-in guardrails and escalation behavior
  • Governance, data, and business logic remain centralized in the trusted Salesforce core while agents act autonomously on external surfaces

Frequently asked questions

What are MCP tools in the context of Salesforce Headless 360?
MCP tools give coding agents direct access to Salesforce capabilities, data models, and organization metadata. They function as interfaces that allow agents to inspect and interact with Salesforce org context while being managed as code.
How does the Agentforce Experience Layer work for multi-surface deployment?
The Experience Layer lets you define UI components once and automatically render them across multiple channels like Slack, ChatGPT-style, React apps, and mobile, eliminating the need to rebuild logic for each channel.
Which AI frameworks can developers choose in Headless 360?
Developers can choose between OpenAI and Anthropic harnesses for their AI agents, providing flexibility in selecting the AI framework that best fits their needs.
How is governance protected in Salesforce Headless 360?
Governance, data, metadata, and business logic remain centralized in the trusted Salesforce core while agents act autonomously on external surfaces. This ensures critical business policies are maintained despite distributed agent activities.

Topics