Salesforce Introduces Agentforce Testing Centre.
Learn moreAgentforce
A
Humans with agents drive customer success together. Build and customise autonomous AI agents to support your employees and customers 24/7.
These companies are seeing value from their Agentforce
Wiley sees 213% return on investment with Salesforce.
Learn how the publisher implemented Agentforce to cut costs and boost productivity.
OpenTable boosts customer service with Agentforce.
See how the company boosts productivity for service reps with AI agents and Service Cloud.
Saks elevates luxury shopping with unified data and AI Service Agents.
See how Agentforce will boost service agent productivity to deliver luxury shopping experiences.
Agentforce will transform ezCater’s customer experience.
Discover how Agentforce will automate customer service to simplify ordering food for the workplace.
What is an Agentforce agent?
An Agentforce agent is a proactive, autonomous application that provides specialised, always-on support to employees or customers. They're equipped with the necessary business knowledge to execute tasks according to their specific role.
What is an agent’s role?
The role is the agent's purpose. It defines the job to be done and the broader goals the agent should achieve on your team.
What is an agent’s trusted data?
Trusted data is the information the agent needs to carry out its role. This could include company knowledge articles, CRM data, external data via Data Cloud, public websites and so on.
What are an agent’s actions?
Actions are the predefined tasks 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.
What are an agent’s guardrails?
Guardrails define what the agent can and cannot do. These can be natural-language instructions to escalate to a human or could come from built-in security features in the Einstein Trust Layer.
What are an agent’s channels?
Channels are the applications where agents can do work. This can be your website, CRM, mobile app, Slack and more.
Discover pre-built Agentforce agents for your business needs
Service
Resolve customer enquiries 24/7
Agentforce Service agents engage customers autonomously across channels 24/7 in natural language. They resolve cases swiftly and accurately because every answer is grounded in trusted data. Set your Service agent up in minutes using prebuilt templates or customise fast with low-code. Define clear security guardrails and when to seamlessly escalate to human employees.
Sales Development Representative (SDR)
Engage with prospects 24/7
Agentforce SDRs autonomously answer product questions, handle objects and book meetings for sales reps. They act and respond accurately, with responses grounded in your business data. You decide how often, which channels and when your agent will engage before briefing sellers for handoff. It can meet leads on their preferred channels, like SMS or WhatsApp, in any language.
Sales Coach
Provide personalised sales role-plays
With a Sales Coach agent, you can practise pitching, handling objections and negotiation with realistic role-plays tailored to each deal. Get consistent feedback on seller strengths, areas for improvement and actionable steps to advance deals, all grounded in CRM data. Then, easily assess ROI by analysing win/loss rates of deals, with or without coaching.
Personal Shopper
Offer personalised product recommendations
Engage shoppers with a personal assistant. Power personalised conversations directly on your commerce site or in a preferred messaging app, like WhatsApp. Help shoppers find products and make purchases faster by guiding search queries and personalising product recommendations.
Campaign
Create and optimise campaigns end-to-end
Build better campaigns faster. With Agentforce Campaigns, marketers can save time with a trusted agent to help generate a campaign brief, target audience segment, content and even build a customer journey in Flow. And because an agent never sleeps, it will continually analyse performance against KPIs and proactively recommend improvements.
Which agent will you build?
Scale your workforce. Handle any business use case. With Agentforce, you can quickly configure any agent from scratch with existing Salesforce tools like prompts, flows, Apex and APIs.
Healthcare Agent
Banking Agent
Retail Agent
Operations Agent
CX Agent
Analytics Agent
IT Agent
Finance Agent
Customise your agents on the Salesforce Platform
Tailor pre-built agents to do whatever your business calls for with low-code. Here's how.
Agent Builder is the low-code builder for Agentforce. Users can tap into existing tools like Flows, prompt templates, Apex and APIs to configure their agent. Set-up is simple: Create a job to be done by the agent by defining topics, giving natural language instructions for that topic and creating a library of actions for it to choose from. Easily monitor an agent’s plan of action and test its responses right in Agent Builder.
The Atlas Reasoning Engine is the brain of Agentforce agents. Users can equip agents to respond naturally and adapt to situations so they're faster, more multi-turn and more capable. Increase their accuracy with topics, which classify requests into a specific category with a defined scope and rules, including which actions an agent can and cannot take.
With Agentforce, teams can use natural language topics and instructions to create guardrails for an agent, including when to escalate or hand off a task to a human. The Einstein Trust Layer enables Agentforce to use any LLM safely by ensuring that no Salesforce data is viewed or retained by 3rd-party model providers.
Only Agentforce brings together Humans + AI + Data + Actions
The most effective use of AI agents is as partners to humans in the customer experience. Assistive agents can help employees in the flow of work by taking on time-consuming jobs so people can focus on high value tasks. Autonomous agents perform certain tasks proactively and escalate to humans when necessary. For example: Agents can provide every new AE their own, personal sales coach that gives them feedback, offers guidance and helps them be their best on the job.
Agents need the right data to work. With Data Cloud, you can create the most intelligent agents possible, because they have access to the right data for any employee or customer experience. Use any data in your organisation with Agentforce, across all systems and sources. It’s scalable, secure and enterprise-grade thanks to Data Cloud. Without sacrificing security, your agents can be dynamic and knowledgeable about your business process and customers — and act accordingly.
An AI agent that can’t take meaningful action is just another bot. Agentforce agents take action across any system so you can complete work faster. They connect data to action by exposing metadata about defined workflows and AI automations. This is what makes them capable of high-value tasks. These may be actions taken on the employee's behalf. For example, these AI agents can help a sales rep draught an email to a customer, create a close plan and kick off a 1:1 nurture cadence for the customer that includes all their upcoming marketing activities.
Connect with partners to deploy Agentforce for your business.
Certified partner experts are ready to help you create a strategy, connect data, and customise and implement Agents tailored to your business needs.
Agentforce Testing Centre
Testing autonomous AI agents requires an approach that works for non-deterministic systems. With Testing Centre, teams can use AI to generate hundreds of synthetic interactions, then run those tests automatically in parallel to see what topics and actions Agentforce chooses. From here, teams can iterate by adjusting instructions as needed — saving time that would have been lost on manually testing many different variations of a conversation.
Calculate your ROI with Agentforce.
Find out how much time and money you can save with a team of AI-powered agents working side by side with your employees and workforce. Just answer four simple questions to see what's possible with Agentforce.
Join the Agentblazer community.
Connect with Agentblazers from around the world to skill up on AI, discover use cases, hear from product experts and more. Grow your AI expertise — and your career.
Ready to take the next step with Agentforce?
Build agents fast.
Take a closer look at how agent building works in our library.
Get expert support.
Work with Professional Services experts to quickly build agents and see value.
Talk to a rep.
Tell us about your business needs and we’ll help you to find answers.
Agentforce Frequently Asked Questions
AI Agents are autonomous, proactive applications designed to execute specialised tasks to help employees and customers. Agents use large language models (LLMs) to analyse and understand the full context of customer interactions or an automated trigger, then reason through decisions on the next steps autonomously.
These agents generate responses that are consistent with your company’s brand voice and guidelines using trusted business data, including Salesforce CRM data, external data from Data Cloud and more. These agents are capable of operating 24/7 across various platforms like self-service portals and messaging channels, handling tasks proactively within set guardrails. When faced with complex issues beyond their scope, they can escalate the matter to human agents, ensuring that queries are resolved efficiently and accurately.
Businesses can build agents with Agent Builder using existing Salesforce Platform tools to create standard and customised topics and actions. You can use prompts grounded in trusted enterprise data. You can use Flows to create automations across any system. You can use MuleSoft API connectors to connect Agents to any system. And last, you can use your Apex & Javascript to create the customised code and business logic for your Agent.
Businesses can create an agent for any role, any industry and to solve any use case. With Agentforce, it's ready to spin up out-of-the-box agents across service, sales, marketing, commerce and more.
- Service Agent replaces traditional chatbots with AI that can handle a wide range of service issues without preprogrammed scenarios, improving customer service efficiency.
- Sales Development Representative (SDR) engages with prospects 24/7, answering questions, managing objections and scheduling meetings based on CRM and external data, allowing your sellers to focus on building deeper customer relationships.
- Sales Coach provides personalised role-play sessions for your sales team, using Salesforce data and generative AI to help sellers practice pitches and objections tailored to specific deals.
- Merchandiser assists your ecommerce merchandisers with site set-up, goal setting, personalised promotions, product descriptions and data-driven insights, simplifying daily tasks.
- Buyer Agent enhances the B2B buying experience, helping your buyers find products, make purchases and track orders via chat or within sales portals. Personal Shopper acts as a digital concierge on your ecommerce sites or messaging apps, offering personalised product recommendations and assisting with search queries.
- Campaign Optimizer automates the full campaign lifecycle, using AI to analyse, generate, personalise and optimise marketing campaigns based on business goals.
- Agentforce (formerly Einstein Copilot) supports employees in the flow of their work with specific tasks by searching for data, creating action plans and executing them to increase workplace efficiency.
Einstein is natively embedded into the Salesforce Platform and leverages data from CRM and external applications to provide insights, predictions and generated content directly in the flow of work.
An ai agent builder is a platform for building and customising AI agents. With Agentforce, our low-code Agent Builder that makes it easy to customise out-of-the-box agents or build new agents for any role, any industry or any use case using existing tools like Flows, Prompts, Apex and MuleSoft APIs to configure their agents. Using Agent Builder, businesses can create a job to be done for their agent by defining topics, writing natural language instructions within that topic and creating a library of actions for it to choose from. Users can also easily observe an agent’s plan of action and test their responses in Agent Builder.