Unlock growth through agentic solutions

Get started with Agentforce.

Agentforce and beyond

AI agents that speak your industry's language.

Take advantage of a fast-tracked activation of Agentforce to create optimal time-to-value outcomes and greater operational efficiency.

Autonomy with purpose
Agentforce enables agents to take multi-step actions such as resolving a customer case, qualifying leads or orchestrating a campaign. All without waiting for humans to micromanage each step.
Speed and scale
Companies leveraging Agentforce are unlocking the potential of their teams with more efficient workflows, better adherence to ideal processes, faster response times, more consistent execution and the flexibility to scale up when demand surges.
Built for trust
Agentforce Command Center gives you a single, real-time view into security, data privacy, compliance and model accuracy. The Session Tracing data model exposes that same data raw, allowing the creation of custom agent analytics in Salesforce or your favorite BI platform.

What is Agentforce?

Agentforce is Salesforce's platform for building autonomous AI agents that streamline tasks and support employees and customers. Businesses create agents using natural language to handle support, marketing and lead qualification, all grounded in Data Cloud and secured by the Einstein Trust Layer.

76%
Of customer inquiries resolved without a human
52%
Increase in self-service quality improvement after deploying AI-powered service
80%
Faster support request resolution, freeing humans for higher value work

Frequently asked questions

Agents: An AI system that can understand a request, reason through it and take action without human intervention, whether that's resolving a case, qualifying a lead or updating a record. Agents are created using Agentforce's agent builder and rely on machine learning and natural language processing (NLP) to handle tasks across sales, service, marketing and commerce.
Role: An agent’s purpose. This defines the job to be done and the broader goals the agent should achieve on your team.
Knowledge: The data an agent needs to be successful. This could include company knowledge articles, CRM data, external data via Data Cloud, public websites and so on.
Subagent (formerly Topics): An Agentforce subagent is a defined "job to be done" that guides an AI agent on a specific set of tasks, instructions and actions. It categorizes the agent's responsibilities, such as order management or customer support and provides the rules and tools (actions) the agent uses to handle a customer's request within that specific area.
Actions: The goals an agent can fulfill. This is the predefined task an agent can execute to do its job based on a trigger or instruction. For example, it could run a flow, prompt template or Apex.
Guardrails: The guidelines an agent can operate under. These can be natural-language instructions telling the agent what it can and can’t do, when to escalate to a human or could come from built-in security features in the Einstein Trust Layer.
Channels: The applications where an agent gets work done. This can be your website, CRM, mobile app, Slack and more.
Yes, Agentforce is designed to integrate with existing systems and applications through various methods, including APIs, MuleSoft connectors and Salesforce's own automation tools. It can connect to both internal Salesforce data and external systems like ERPs and other cloud services, allowing AI agents to access and process data from across your entire enterprise. This integration enables autonomous workflows that can operate across different platforms and applications.