Salesforce Agentforce: What you need to know

We’ve updated our page on Agentforce with details on new Agentforce pricing options and Agentforce for Public Sector.

Since its launch at the Dreamforce conference in September 2024, Salesforce Agentforce changed the conversation around AI, customer experience and customer service. Shortly after the launch, Salesforce announced it was hiring more than 1,000 employees to meet the demand for Agentforce. 

At the time of the Agentforce announcement, Salesforce CEO Marc Benioff called Agentforce “the third wave of AI — advancing beyond copilots to a new era of highly accurate, low-hallucination intelligent agents that actively drive customer success.”

The platform is so important to Salesforce that Benioff declared at the Agentforce launch, “The only thing we’re going to do at Salesforce is Agentforce.”

Listen to an AI-generated audio Deep Dive of Agentforce based on the contents of this article.

Customize this article for your job role

What is Agentforce?

Agentforce is essentially a platform layer in the Salesforce ecosystem. Agentforce bots are generative AI bots, but unlike popular genAI platforms like ChatGPT and Google Gemini, Salesforce says its Agentforce bots can be trusted to take action on their own.   

Unlike earlier chatbots, AI agents do not follow a prescribed pattern of answers to common queries, but are capable of responding more flexibly to questions or issues because they are trained on internal data and are capable of drawing on the support of a large language model (LLM). Salesforce’s agentic AI, for example, can be trained on data in Salesforce Data Cloud.

Agentforce combines three major Salesforce tools — Agent Builder, Model Builder and Prompt Builder — to deliver out-of-the-box bots that work across industries. The bots are customized using inexpensive, low-code tools.

The initial agents created with Agentforce include:

• Campaign Optimizer, which manages and executes full campaign lifecycles. 
• Service Agent, which replaces chatbots in handling customer service.
• Buyer, which helps B2B customers find products, make purchases and track orders.
• Personal Shopper, which recommends products and helps with search.
• Merchant, which does all the site-related tasks for merchandisers, including promotions, product descriptions and insights.
• Sales Development Representative, which engages with potential leads 24/7.
• Sales Coach, which helps train sales teams and lets sellers practice pitching.

General availability for Agentforce One began on Oct. 25, 2024, with pricing starting at $2 per conversation, with discounts available to large users

Salesforce also announced the Agentforce Partner Network at the launch. It lets other organizations deploy third-party agents or use third-party actions when designing custom agents in Agentforce.

Dig deeper: Customer experience management in the age of agentic AI

How does Agentforce work?

During the initial Agentforce announcement at Dreamforce, Benioff said Agentforce is designed for customers who don’t know much about AI or building bots.

“They are not going to have to be an expert in an LLM, they are not going to have to understand all of these deep capabilities that you would need to know to be a computer scientist,” he said. This is “AI for the rest of us.”

Agentforce is powered by an upgraded version of Salesforce’s Einstein AI called Atlas Reasoning Engine, which is “designed to simulate how humans think and plan.” 

At the announcement, Salesforce drew a comparison to self-driving cars. Agentforce can interpret data to adapt to conditions in real time and can act independently within a company’s guardrails. 

Benioff said Agentforce has the lowest hallucination rate of any generative AI but did not say what that rate is. 

Agentforce integrations with other Salesforce tools

Data Cloud

Data Cloud provides the customer data that grounds Agentforce, making agents more contextually aware, knowledgeable and adaptable to customer needs. Data Cloud connects, unifies and harmonizes customer data and metadata, giving agents access to the exact information they need to deliver precise, contextual responses. It makes structured and unstructured data – including emails, transcripts and PDFs – easily digestible by large language models (LLMs). The RAG functionality allows users to upload files and URLs as data sources for their agent. 

Customer 360

Agentforce is deeply integrated with Salesforce Customer 360, leveraging applications like sales, service, marketing and commerce. A complete view of the customer is critical to seamless hand-offs to human agents with the full conversation history.

Heroku

As part of its Agentforce 3 announcement, Salesforce said Heroku Managed Inference and AppLink will make it fast and easy to deploy, register, maintain and connect custom MCP servers. With Heroku’s secure infrastructure and DevOps automation, developers can bring trusted custom actions to Agentforce.

MuleSoft

MuleSoft is an integration, automation and API management platform. It extends Agentforce capabilities by enabling Salesforce developers and admins to leverage their APIs and bring in third-party data.

As part of the Agentforce 3 announcement and its support for model context protocol (MCP), Salesforce introduced new MCP connectors for MuleSoft that will convert any API and integration into an agent-ready asset, complete with security policies, activity tracing and traffic controls.

Slack

Slack is a central point for employees to interact with Agentforce. They can access information, trigger workflows and manage tasks directly within Slack, which means they don’t have to jump between applications.

Agentforce also uses Slack Enterprise Search to learn from conversations in Slack channels and direct messages. This helps agents provide more relevant responses and actions based on the context of conversations.

Tableau 

Tableau Einstein is an AI-powered visual analytics platform that includes Agentforce. It is designed to intelligently embed data and insights across the flow of work and encourages employees to use data to drive action. 

Dig deeper: 4 key features in Salesforce’s Agentforce 2.0

Agentforce Testing Center

In December 2024, Salesforce announced The Testing Center, which lets businesses test their AI agents before deployment. The Testing Center gives Agentforce users an opportunity to  ensure the agents follow instructions, stay factual and work quickly. This helps mitigate risks and ensures agents perform consistently and reliably. It also provides tools that make it easier to test, audit and scale agents.

Library of skills and integrations

Also announced in December 2024, this library spans key business applications like CRM, Slack and Tableau, and integrations from AppExchange partners. These ready-to-use skills simplify the process of building tailored AI agents. The library has pre-built Slack Actions like Create Canvas and Message Channel, which let teams create agents for their Slack workflows.

Here are some examples:

• The CRM Skills let you create agents to automate and enhance customer experiences. These agents can do things like lead nurturing, sales coaching, and scheduling service engagements among other functions. 
• The Sales Development skill creates agents that nurture leads based on predefined rules. 
• The Sales Coaching skill lets agents actively participate in sales calls, providing real-time feedback to representatives and improving their performance.
• The MuleSoft integrations let companies use Agentforce across their entire business ecosystem. For example, it can connect Agentforce to its ERP system to automate order fulfillment processes. It can also integrate with marketing automation platforms to trigger personalized email campaigns based on customer interactions.
• The AppExchange boosts Agentforce capabilities by letting users access specialized skills created by partners.

Which companies are using Agentforce?

Salesforce itself is using Agentforce internally. It says agents at help.salesforce.com now handle 83% of customer support queries independently, with human escalations dropping by 50% in the two weeks after it was implemented.

RBC uses Atlas and Data Cloud with Agentforce to help its financial advisors. Salesforce Data Cloud integrates all RBC client data into a unified system, giving advisors a comprehensive view of their clients. Atlas can answer complex client questions using multistep reasoning. It also pulls from RBC’s data and business logic to deliver a reliable answer.

Accenture uses Agentforce to give employees quick updates on important accounts. It helps automate document retrieval and makes recommendations for solving business problems. It also streamlines proposal creation and visualization and enhances employee collaboration by providing real-time updates, retrieving documents, offering proactive recommendations and creating proposals. 

Other companies publicly identified by Salesforce as Agentfore customers include:

• 1-800-ACCOUNTANT
• AAA Washington
• The Adecco Group
• AdMed, Inc.
• BACA Systems
• Bouygues Telecom
• Capita
• City of Kyle, Tex.
• Co-operators Group Limited
• Engine
• Finnair
• Goodyear
• Grupo Globo
• Indeed
• L’Oréal
• OpenTable
• PepsiCo
• RBC Wealth Management
• Saks
• SharkNinja
• Wayfair
• Wiley

Dig deeper: SharkNinja embarks on its Salesforce AI journey

Salesforce announces trust and governance capabilities for Agentforce

In mid-May 2025, Salesforce unveiled a set of governance, security and compliance capabilities to help organizations deploy trusted AI agents. 

These capabilities allow customers to govern data across the entire Salesforce platform, whether from inside or outside of Salesforce applications.

Salesforce uses several products to create trust and data governance, including Agentforce, Salesforce Data Cloud, MuleSoft and Trusted Services (including capabilities from the recently acquired Own, Shield, and the Trust Layer).

Salesforce says the capabilities deliver a fully integrated, enterprise-grade foundation for trusted, governed and secure AI, in contrast to fragmented point solutions available elsewhere. Agentforce runs natively on the platform, providing control, visibility and assurance at every stage of agent deployment. 

The capabilities range from Zero Copy data access and built-in policy enforcement to real-time monitoring and AI behavior transparency. They include:

• Salesforce Backup & Recover: Formerly known as Own Recover, this provides 100% protection of Salesforce data and metadata, including automated backups and restoration down to the field level.
• Salesforce Archive: This is for compliance with regulatory requirements and internal data retention policies. It can also optimize performance by only working with relevant data.
• Data Mask and Seed: Protect and seed Sandbox data at scale, making it easier to test and deploy AI agents safely and efficiently.
• Shield 2.0: Provides greater visibility into user activity and behavior, including proactive threat detection and easier compliance reporting.
• Security Center 2.0: Simplify security posture management, including faster data classification and greater visibility into risks, including new automated risk assessments from Own Secure.

There are also capabilities to help developers build and test Agentforce agents before they go into production.

Read more about Salesforce’s trust and governance initiatives for Agentforce.

Agentforce pricing models

Salesforce intially launched Agentforce with a conversational pricing model of $2 per conversation. In May 2025, Salesforce introduced three new pricing models:

1. New Flex Credits to help businesses scale Agentforce

Flex Credits offer customers flexibility with a consumption-based model that Salesforce says aligns cost with business outcomes. Businesses only pay for the exact actions Agentforce performs, which could include  updating customer records, automating complex workflows or resolving cases. Each of these actions consumes 20 Flex Credits ($0.10 per action). Flex Credits are  available in packs of 100,000 credits ($500).

2. New Flex Agreement to shift investment as priorities change

The new Flex Agreement allows organizations to manage both human and digital labor and shift their investments between user licenses or digital labor according to their business priorities. The Flex Agreement converts user licenses into Flex Credits, or Flex Credits into new user licenses, for exploring new, value-generating use cases.

3. New Agentforce user licenses and add-ons with included Agentforce usage

New Agentforce user licenses and add-ons help bring Agentforce capabilities to every employee, offering unlimited employee-facing agent usage in a per-user, per-month (PUPM) pricing model. 

Get more details on the Agentforce pricing models.

Salesforce continues to tweak Agentforce pricing models

In mid-August 2025, Salesforce made more changes to its Agentforce payment options, offering three distinct ways to pay for Agentforce usage. 

• Pay-as-you-go (new as of August 2025): No up-front commitment; pay monthly for Flex Credits used.
• Pre-commit (new as of August 2025): Make an up-front commitment for more favorable pricing, and pay monthly for Flex Credits used. 
• Pre-purchase: Save the most by paying up front, ideal for businesses with predictable, onsistent usage.

Pay-as-you-go Agentforce pricing

Pay-as-you-go pricing became generally available starting in August 2025. It has no up-front commitment, and users pay monthly based on the number of Flex Credits used. Salesforce considers it an ideal option for running pilots, testing new use cases and managing unpredictable workloads. 

Pre-commit Agentforce pricing

Introduced in a limited release in August 2025, pre-commit pricing allows customers to unlock more favorable pricing when they make an up-front commitment. Naturally, the bigger the commitment, the bigger the savings. Salesforce expects pre-commit pricing will be more widely available in late 2025.

Pre-purchase Agentforce pricing

The existing pre-purchase option allows Agenforce customers to pay up front for a set amount of usage over their contract term and draw from that balance as they go. This is how most of Agentforce customers pay for the platform and works well for businesses with predictable workloads and consistent demand. 

Salesforce Marketing Cloud Next includes Agentforce features

In June 2025, Salesforce introduced Marketing Cloud Next, which embeds autonomous AI agents across the entire customer funnel.

Salesforce said the product represents a shift from traditional campaign-based marketing to agentic marketing, where AI agents act independently to execute campaigns, personalize customer interactions and optimize performance.

These AI agents can interpret business goals and carry out tasks across marketing, sales, service and commerce functions. For example, marketers can input a goal — such as raising awareness of a new product among top customers — and the AI will build and launch the campaign, manage customer journeys and personalize outreach across channels like email, SMS and web.

Among the features on Marketing Cloud Next are Agentforce Campaign Creation and Agentforce Web Curation.

What’s new in Salesforce Agentforce 3?

In late June 2025, Salesforce announced Agentforce 3, which focuses on observability and control, in an attempt to solve a problem vexing companies deploying agentic AI: they can’t see what their AI agents are doing.

Central to Agentforce 3 is Agentforce Command Center. Command Center, which is built into Agentforce Studio, is an observability solution that delivers a single pane of glass to monitor agent health, measure performance and optimize outcomes. 

Teams can use Command Center to analyze every AI agent interaction, drill into specific moments, understand trends in usage and see AI-powered recommendations for tagged conversation types, all of which can be used to continuously improve the agent experience. 

MCP support in Agentforce

As part of the Agentforce 3 announcement, Salesforce said Agentforce wouldsoon include a native model context protocol (MCP) client, allowing Agentforce agents to connect to any MCP-compliant server without any custom code. This enables access to enterprise tools, prompts and resources — governed by existing security policies.

Agentforce customers will be able to discover MCP servers from more than 30 partners through AgentExchange. Launch MCP partners include AWS, Box, Cisco, Google Cloud, IBM, Notion, PayPal, Stripe, Teradata and WRITER.

Additional Agentforce 3 enhancements include improvements to the Agentforce architecture to reduce latency, additional support for geographies and additional language support.

Read more details on the Agentforce 3 announcement.

Agentforce for vertical markets

Salesforce i introducing Agentforce platforms designed specifically for vertical markets. These Agentforce products include pre-built agents to speed up deployments and help customers get started with agentic AI faster.

Agentforce for Retail

In January 2025, Salesforce used the National Retail Federation (NRF) conference to announce Agentforce for Retail, which includes a library of pre-built agent skills relevant to retail. It is aimed at facilitating the creation of AI agents by retail brands to supply what Salesforce is calling “digital labor.”

The new skills available in Agentforce for Retail include:

• Order management. Self-service order servicing options allowing customers to conversationally update order information like payment or shipping details.
• Guided shopping. Using natural language, customers get product recommendations from agents and check out conversationally.
• Appointment scheduling. Automated scheduling with real-time availability updates aimed at field services like deliveries, installations and consultations.
• Loyalty promotion creation. Assistance for marketers in creating and optimizing loyalty promotions with conversational prompts.

Salesforce also announced Retail Cloud with Modern POS, a new offering that brings online and offline inventory data together on a single platform. 

Dig deeper: Salesforce launches Agentforce for Retail

Agentforce for Field Service

Salesforce announced in April 2025 it is launching Agentforce for Field Service, its digital labor platform built to augment dispatchers and technicians by eliminating scheduling bottlenecks and tackling routine, time-consuming tasks. 

Accord to research conducted by Salesforce, inefficient scheduling is the No. 1 drain on field service teams. It’s estimated skilled tradespeople and technicians waste nearly an entire workday each week on administrative work — time that should go toward hands-on repairs and customer service.

Agentforce integrates into existing data systems and user interfaces, autonomously scheduling appointments, assisting with filling schedule gaps, troubleshooting in real time and summarizing job reports. It also features audio playback and natural language voice commands, so field technicians can conveniently interact with Agentforce and consume information while on the move — boosting productivity, safety and response times.

Agentforce for HR Service

In early May 2025, Sales announced Agentforce for HR Service, a set of AI-powered capabilities embedded directly into Salesforce’s HR Service platform.

Agentforce for HR Service includes a suite of out-of-the-box topics – broad categories of tasks AI agents perform — and actions-specific steps or tools the AI agent uses to complete those tasks.

Agentforce for HR Service lets employees perform common HR support tasks conversationally — right where they spend most of their time, inside applkcations like Slack or their employee portal — without needing to file tickets, dig through policy documents or move between multiple systems.

The AI agents are grounded in company data, knowledge articles and policies, and integrate with leading Human Resource Information Systems (HRIS) and Human Capital Management (HCM).

Among the capabilities of Agentforce for HR Service:

• Delivering personalized answers to employees.
• Tracking employee programs.
• Managing HR cases.
• Updating employee details.
• Managing time off requests.
• Updating direct deposit details.
• Submitting and track expenses.
• Escalating requests to a human HR rep.

Agentforce for Financial Services

In May 2025, Salesforce introduced Agentforce for Financial Services, a set of pre-built, role-based AI agent templates for financial services teams. The agents can handfe key front-office tasks like preparing for an investment review, replacing a lost credit card, surfacing relevant loan options and other administrative burdens that detract from more valuable customer engagement.

Agentforce is grounded in a firm’s data, workflows and compliance controls so every action conforms with internal policies and regulatory requirements. Agentforce is natively embedded in Salesforce’s Financial Services Cloud, allowing human and digital workers to operate from the same deeply unified platform in a way that feels intuitive and trustworthy.

Agentforce for Financial Services includes pre-built templates for:

• Financial Advisor and Banker agents that help high-touch relationship managers scale their practice by automating meeting preparation and follow-up.
• Banking and Insurance service agents, which handle routine service requests like reversing a fee, canceling a credit card or explaining insurance coverage options.
• A Digital Loan Officer agent that guides borrowers through loan product discovery for auto or personal loans.

Each pre-built template includes Topics, which guide agent behavior, and Actions that give agents the ability to take action specific to financial services jobs. Firms can customize and expand these agents with Agentforce to reflect their specific processes, guardrails, policies and service models using a declarative, no-code environment.

Agentforce for Revenue

In July 2025, Salesforce introduced Agentforce for Revenue, which allows revebnue teams to employ digital labor to handle routine tasks like quoting, follow-ups and data entry.

Agentforce for Revenue is embedded in Salesforce Revenue Cloud, and combines humans and AI agents to streamline the entire quote-to-cash process, from quoting and contracting to ordering and invoicing, with greater speed, accuracy and confidence.

Here’s how Salesforce says the Agentforce for Revenue and Revenue Cloud work together: 

• After a quote is kicked off by Agentforce, sellers use Revenue Cloud’s enhanced Product Configurator to quickly tailor complex offerings, including quotes with more than 1,000 line items. 
• Traditional CPQ tools rely solely on rigid, rule-heavy systems. Salesforce uses a constraint-based logic engine that augments those traditional approaches, giving customers the flexibility to handle more complex demands. 
• Salesforce uses bidirectional rules and point-and-click templates to dramatically reduce rule maintenance and authoring time. Salesforce compares it to GPS for quoting that guides reps to valid configurations in real time, speeding up time-to-quote.

According to Deloitte, 71% of B2B executives struggle with manual, fragmented sales processes — and 13% of deals are lost because of disconnected tools. 

As hybrid monetization models become the norm, reps don’t have time to manually piece together subscriptions, usage-based pricing, and service offerings. 

Salesforce believes Revenue Cloud and Agentforce can eliminate that complexity, unifying all transaction types on a single quote, and carrying the transaction data through to the order and invoice.

Agentforce for Public Sector

In August 2025, Salesforce announced Agentforce for Public Sector, which enables government agencies to build, customize and deploy custom and out-of-the-box agents. 

Agencies can use these AI agents to autonomously handle work like answering common citizen queries and processing license renewals. Agentforce adheres to a number of global compliance requirements, including FedRAMP High, Protected-B and IRAP, to help with trust and security.

Agentforce for Public Sector includes prebuilt actions (tasks an agent can perform) like “find similar complaints” or “check for regulatory code violations” specifically designed for the public sector. These actions can be quickly deployed and adapted for every process.

Some of the actions available today include

• Simplify enforcement and reduce risk: Based on relevant regulations, an AI agent can support compliance officers and inspectors by recommending specific code violations, helping with regulatory fee calculations and creating documentation. From flagging violations to generating follow-up emails, agents with Compliance Management actions help cut down on administrative work.

• Speed up response and spot trends: Agents can summarize and analyze constituent complaints, identify related past issues and recommend next steps based on relevant policies and regulations. 

• Find and hire top talent, faster: Agentforce can help speed up hiring and reduce recruiting administrative burdens with AI-powered resume matching and candidate engagement. It can also recommend a job position to an applicantbased on their skills, experience and goals. 

• Help constituents apply for benefits: Agentforce allows constituents to converse naturally with an agent, in all supported languages, to ask about applicable benefits and eligibility criteria. This helps deliver assistance to constituents in a timely manner, while enabling faster application processing, reduced error rates and increased policy compliance.