Salesforce, the world’s #1 AI CRM, has announced Agentforce 3: a major upgrade to its digital labour platform that gives companies the visibility and control to scale AI agents without compromise.
As enterprise adoption accelerates, the real blocker has become clear: teams can’t see what agents are doing — or evolve them fast enough. Agentforce 3 changes that. Built on learnings from thousands of Agentforce deployments since its initial launch in October 2024, Agentforce has helped customers deliver undeniable value. Agentforce 3 equips leaders to monitor, improve, and scale their AI workforce with confidence.
With a new Command Centre for complete observability, built-in support for Model Context Protocol (MCP) for plug-and-play interoperability, and over 100 new prebuilt industry actions to speed time to value, Agentforce 3 helps companies scale what works, fix what doesn’t, and unlock the full potential of agentic AI — with clarity, control, and speed.
Why it Matters: AI agent adoption is surging. According to a soon to be released Slack Workflow Index, AI agent usage is up 233% in six months, and over that same period, 8,000 customers have signed up to deploy Agentforce. But until now, agent platforms have lacked the tooling, governance, and observability needed to scale enterprise-wide. Agentforce 3 closes this gap — delivering the complete visibility, secure tool integration, and enterprise-grade controls organisations need to make agent velocity their competitive advantage.
“With Agentforce, we’ve unified agents, data, apps, and metadata to create a digital labour platform, helping thousands of companies realise the promise of agentic AI today”, said Adam Evans, EVP & GM of Salesforce AI. “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 Centre — Monitor, Measure, and Optimise Your AI Agents: As AI agents take on routine tasks and begin collaborating more closely with human teammates, teams need a new observability layer built for the era of digital labour. Agentforce Command Centre is that layer: a complete observability solution that gives leaders a unified pane of glass to monitor agent health, measure performance, and optimise outcomes. Built into Agentforce Studio, it completes the agent lifecycle with powerful tools to understand and refine agents at scale.
- Uncover patterns across interactions to optimize your agents: Command Centre empowers teams to analyse every AI agent interaction, drill into specific moments, understand trends in usage, and see AI-powered recommendations for tagged conversation types to continuously improve your Agentforce.
- Track agent health and intervene in real time: Get live, detailed analytics for latency, escalation frequency, and error rates, plus real-time alerts when the unexpected happens, so teams can act fast and keep agents running smoothly.
- Understand what’s working, and where to improve: Command Centre offers detailed dashboards that track agent adoption, feedback, success rates, cost, and topic performance — so teams can see what’s gaining traction and where to improve.
- See what your agents are doing — in the tools your teams already use: Agentforce captures 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 tools your teams already use, including Datadog, Splunk, Wayfound, and other monitoring partners for end-to-end visibility across your existing stack.
- Deliver a configurable Command Centre for every team: Monitor AI agents alongside human teammates — right in the flow of work. Starting with Service Cloud, agent activity will surface in real-time wallboards so contact centre supervisors can track performance and escalate fast. And over time, every department will have a Command Centre purpose-built for optimizing their agents.
- Build and test agents fast with AI-assisted development tools: In Agentforce Studio, use natural language to generate topics, instructions, and test cases. Testing Centre simulates behaviour at scale with state injection and AI-driven evals — so you can pressure-test your agents before going live.
Enabling Secure Enterprise Connectivity with MCP and A2A Support: AI agents can’t drive impact if they can’t take action using the tools your business relies on. As open standards like Model Context Protocol (MCP) gain traction, they bring new opportunities for interoperability, but also challenges around governance, identity, and control. Agentforce 3 solves this by pairing open connectivity with enterprise-grade trust — giving agents native access to the tools they need, without compromising on control.
- MCP support built natively into Agentforce: Agentforce will include a native MCP client, enabling Agentforce agents to connect to any MCP-compliant server — no custom code required. Like a “USB-C for AI,” this enables access to enterprise tools, prompts, and resources — governed by your existing security policies.
- Turn APIs into MCP servers instantly with MuleSoft: Leveraging new MCP connectors, MuleSoft converts any API and integration into an agent-ready asset, complete with security policies, activity tracing, and traffic controls — empowering teams to orchestrate and govern multi-agent workflows.
- Easily host and manage custom MCP servers with Heroku: Heroku Managed Inference and AppLink make it fast and easy to deploy, register, maintain, and connect your custom MCP servers. With Heroku’s secure infrastructure and DevOps automation, developers can bring trusted custom actions to Agentforce with less friction.
Expanding the AgentExchange — a Leading AI Agent Ecosystem — to Make Agent-First Tools Easy to Discover and Use: As organisations embed AI agents across their teams, AgentExchange already makes it easy to equip them with the trusted tools they need to drive value fast with partner-built agent actions and templates. Now, customers will be able to discover MCP servers from 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.
- Customers will be able to leverage MCP Servers through AgentExchange from leading partners, including:
- AWS: Agentforce will enable agents to unlock critical insights from vast repositories of unstructured data stored on AWS, leveraging a suite of MCP servers such as the Amazon Bedrock Data Automation MCP Server and Amazon Nova Canvas MCP Server. This will allow Agentforce to intelligently process and summarise documents, extract key information from images, transcribe and analyze audio recordings, identify crucial moments in video files, query enterprise knowledge bases, perform semantic code repository searches, and interact with databases through natural language interfaces via Aurora PostgreSQL/MySQL MCP Servers — all enhancing customer service, compliance checks, and operational reporting.
- Box: Agentforce can help retrieve the latest signed NDA from a Box MCP service, including a summary of key terms. Agentforce can then post a Slack update to the relevant teams that includes the AI summarization, the contract in PDF form, and recommended next steps.
- Google Cloud: Customers can unlock new Agentforce use cases by connecting to key Google and Google Cloud services via MCP. For example, developers will be able to seamlessly connect Agentforce to the Google Maps Platform and generative AI models like Veo, Chirp, Imagen, and Lyria, while also enabling agentic interactions with Google Cloud Databases. This can enable Agenforce actions that span location-based services, creative AI, and transactional data.
- PayPal: Customers can now power a full range of agentic commerce capabilities by connecting Agentforce to PayPal’s MCP server. They can list products, place orders, process payments, dispute claims, track shipping, manage subscriptions, issue refunds, and more with PayPal, making integrations simple and easy.
- Stripe: Agentforce enables AI agents to directly handle a wide range of Stripe functionalities via its MCP server, including real-time product lookups, quick payment link generation, subscription setup, and faster dispute management.
- WRITER: Through a secure connection to WRITER’s MCP server, Agentforce can call WRITER’s enterprise-grade AI agents to automate content generation, knowledge retrieval, and compliance checks all within Salesforce workflows.
Enhancing the Agentforce Architecture for Unmatched Enterprise Readiness: Underpinning every new capability in Agentforce 3 is an enhanced Atlas architecture, providing an enterprise-ready foundation through lower latency, greater accuracy, global availability, and additional options for control through new LLMs hosted on Salesforce infrastructure.
- Expanded LLM choice with hosted Anthropic: 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, solidifying Agentforce’s position as the leader in trusted, flexible AI agents.
- Faster performance and response streaming: Experience a more responsive Agentforce with 50% lower latency since January 2025. Response streaming is also generally available in this release, so users can see answers appear in real time.
- Greater accuracy through web search, inline citations: Agentforce 3 features 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.
- More languages, more geographies: Agentforce 3 features an expanded global footprint, deploying to Canada, the U.K., India, Japan, and Brazil to serve AI agent traffic within those regions. This release also adds GA support for six new languages, including French, Italian, German, Spanish, Japanese, and Portuguese — with more than 30 additional languages rolling out in the coming months.
- Enhanced resiliency with automatic model failover: To ensure agents are always on, Agentforce now enables automatic, latency-based failover — dynamically shifting traffic between model providers in case of performance degradation or outages.
- Bringing Agentforce to Public Sector customers with FedRAMP High Authorisation: Agentforce is now authorised and generally available in Government Cloud Plus, which enables public sector customers to bring Agentforce to their missions with the highest standards of trust, security, and compliance.
Unmatched Industry Readiness Out-of-the-Box Delivers the Fastest Path to Value from AI Agents: Agentforce customers in every industry can deliver value from AI agents fast through more than 200 pre-built industry actions — half of them new this summer — 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 to help teams get started fast and scale boldly.
Deploy and Scale Agentforce with Confidence Through Trusted Experts: The Salesforce partner ecosystem, including Accenture, Deloitte Digital, NeuraFlash, PwC, and more, has aided customers across thousands of Agentforce deployments, providing 272,000 certified specialists to deliver strategic guidance and facilitate the successful activation of AI agents that help drive business impact while maintaining governance.
Image Credit: Salesforce
