Salesforce Launches Agentforce 3

Salesforce today released Agentforce 3, a major upgrade to its digital labor platform that gives companies greater visibility and control to scale AI agents.

Agentforce 3 comes with a new Command Center for complete observability, built-in support for Model Context Protocol (MCP) for plug-and-play interoperability, and more than 100 prebuilt industry actions.

"With Agentforce, we've unified agents, data, apps, and metadata to create a digital labor platform, helping thousands of companies realize the promise of agentic AI today," said Adam Evans, executive vice president and general manager of Salesforce AI, in a statement. "Over the past several months, we've listened deeply to our customers and continued our rapid pace of technology innovation. The result is Agentforce 3, a major leap forward for our platform that brings greater intelligence, higher performance, and more trust and accountability to every Agentforce deployment. Agentforce 3 will redefine how humans and AI agents work together, driving breakthrough levels of productivity, efficiency, and business transformation."

Agentforce Command Center is a complete observability solution that gives leaders a unified pane of glass to monitor agent health, measure performance, and optimize outcomes. Built into Agentforce Studio, it completes the agent lifecycle with tools to understand and refine agents at scale. With it, users can do the following:

• Analyze every AI agent interaction, drill into specific moments, understand trends in usage, and see AI-powered recommendations for tagged conversation types.
• Get live, detailed analytics for latency, escalation frequency, and error rates, plus real-time alerts when the unexpected happens and act fast to keep agents running smoothly.
• Understand what's working, and where to improve with detailed dashboards that track agent adoption, feedback, success rates, cost, and topic performance.
• Capture all agent activity in a native, extensible session-tracing data model in Data Cloud, powering analytics, monitoring, and real-time alerting. Built on the OpenTelemetry standard, these agent signals integrate seamlessly with Datadog, Splunk, Wayfound, and other monitoring partners.
• Monitor AI agents alongside human teammates. Starting with Service Cloud, agent activity will surface in real-time wallboards so contact center supervisors can track performance and escalate fast. And over time, every department will have a Command Center purpose-built for optimizing agents.
• Build and test agents with AI-assisted development tools: In Agentforce Studio, use natural language to generate topics, instructions, and test cases. Agentforce Testing Center simulates behavior at scale with state injection and AI-driven evaluations to pressure-test agents before going live.

Agentforce 3 also comes with MCP and A2A support, pairing open connectivity with enterprise-grade trust giving agents native access to the tools they need, without compromising on control.

Agentforce will include a native MCP client, enabling Agentforce agents to connect to any MCP-compliant server for access to enterprise tools, prompts, and resources governed by existing security policies.

Users can turn APIs into MCP servers instantly with MuleSoft complete with security policies, activity tracing, and traffic controls, to orchestrate and govern multi-agent workflows. Heroku Managed Inference and AppLink help deploy, register, maintain, and connect custom MCP servers. With Heroku’s secure infrastructure and DevOps automation, developers can bring trusted custom actions to Agentforce.

Salesforce is also expanding the AgentExchange, its AI agent ecosystem. Now, customers will be able to discover MCP servers from more than 30 partners that provide trusted access to new third-party tools and resources and seamlessly connect them to Agentforce through a secure AI agent gateway. Launch MCP partners include AWS, Box, Cisco, Google Cloud, IBM, Notion, PayPal, Stripe, Teradata, WRITER and more.

Underpinning every new capability in Agentforce 3 is an enhanced Atlas architecture, providing a foundation through lower latency, greater accuracy, global availability, and additional options for control through new large language models hosted on Salesforce infrastructure.

Agentforce can now use Anthropic's Claude Sonnet model hosted via Amazon Bedrock within the Salesforce trust boundary to meet the needs of customers in high-compliance industries. As part of this expanded relationship, Anthropic will work with Salesforce to empower customers in regulated industries to scale Agentforce adoption with Claude. Later this year, Salesforce will also allow customers to use Google's Gemini in Agentforce.

Other upgrades in Agentforce 3 include the following:

• 50 percent lower latency.
• Response streaming so users can see answers appear in real time.
• Greater accuracy through web search, inline citations with trusted, expanded grounding through the addition of web search as a data source, allowing agents to go beyond internal data to answer requests as well as inline citations that provide references to the grounding sources used in responses.
• An expanded global footprint, deploying to Canada, the United Kingdom, India, Japan, and Brazil.
• Support for French, Italian, German, Spanish, Japanese, and Portuguese, with more than 30 additional languages rolling out in the coming months.
• Automatic model failover, dynamically shifting traffic between model providers in case of performance degradation or outages.

Agentforce is now authorized and generally available in Government Cloud Plus, which enables public-sector customers.

Agentforce 3 also includes more than 200 pre-built industry actions, from patient scheduling, to advertising proposal generation, to vehicle servicing, and more. Agentforce 3 also introduces simplified, flexible pricing with new Agentforce for Sales, Service, and Industry Cloud SKUs with per-user pricing and unlimited usage of actions for employee-facing agents.

Related Articles

Salesforce Launches Agentforce 2dx

New Salesforce Agentforce 2dx offers capabilities to embed proactive agentic AI into any workflow, create multimodal experiences, and extend digital labor

Salesforce Unveils Agentforce

With Salesforce's Agentforce, organizations can build, customize, and deploy their own AI agents with low-code tools.