4 key features in Salesforce’s Agentforce 2.0

“The only thing we’re going to do in Salesforce is Agentforce.” That’s what Salesforce CEO Marc Benioff said in September introducing AI agents. This week, the company showed what that means by unveiling the vastly improved version of Agentforce 2.0.

Among its new features, four stand out:

• A library of pre-built skills and workflow integrations for quick customization.
• Ability to deploy Agentforce in Slack.
• Improvements to the Atlas Reasoning Engine.
• Agentforce Test Center.

Here’s a look at them and how they can be used.

A library of skills and integrations

This library includes key business applications such as CRM, Slack, and Tableau, and integrations from AppExchange partners. These ready-to-use skills simplify the process of creating custom AI agents. Eliminates complex and time-consuming integration problems. The library has built-in Slack actions like Create Canvas and Message Channel that allow teams to create agents for their Slack workflows.

Here are some examples:

• CRM skills allow you to create agents to automate and improve the customer experience. These agents can do things like lead nurturing, sales coaching, and service planning, among other things. For example, the Sales Development skill can create agents that nurture leads based on pre-defined rules. The Sales Coaching skill enables agents to actively participate in sales calls, provide real-time feedback to reps, and improve their performance.
• MuleSoft integrations enable companies to use Agentforce across their entire business ecosystem. For example, it can connect Agentforce to its ERP system and automate order fulfillment processes. It can also integrate with marketing automation platforms to launch personalized email campaigns based on customer interactions.
• The AppExchange enhances the capabilities of Agentforce by giving users access to specialized skills created by partners.

Agentforce in Slack

This makes Slack a central point for employee interaction with Agentforce. They can access information, run workflows, and manage tasks right within Slack. This means they don’t have to jump between apps.

Agentforce can also automate tasks within Slack. Accenture, for example, uses it to provide employees with quick updates on important accounts. It helps automate document loading and provides recommendations for solving business problems. It also simplifies the creation and visualization of proposals and improves employee collaboration, including providing real-time updates, retrieving documents, offering proactive recommendations and creating proposals.

Dig deeper: SharkNinja Takes the Salesforce AI Journey

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

Enhanced Atlas Reasoning Engine

The Atlas Reasoning Engine has been enhanced with advanced reasoning and augmented data acquisition generation (RAG) so that agents can handle more complex, multi-step questions and provide more precise and accurate answers.

For example, RBC uses Atlas and Data Cloud with Agentforce to help its financial advisors. Data Cloud integrates all client data into a unified system, providing advisors with a comprehensive view of their clients. Atlas can answer clients’ complex questions. It does this using multi-step reasoning. It is also based on RBC data and business logic. This helps to provide a reliable answer.

An old Russian proverb says: Trust, but verify. The enhanced RAG capabilities allow users to do this by embedding citations with agent responses. Citing the exact sources used builds confidence in the AI ​​output. It also helps users to check accuracy.

Agentforce Test Center

The test center allows enterprises to test their AI agents before using them. This ensures that agents follow instructions, stay matter-of-fact and work quickly. This helps mitigate risk and ensures that agents perform consistently and reliably. It also provides tools that make it easy to test, audit, and scale agents.

Exercising and preaching

Salesforce uses the technology internally. It says agents on help.salesforce.com now handle 83% of customer support inquiries independently, with human-to-human escalations down 50% since implementation two weeks ago.

“Suddenly, as a CEO, I’m not just managing human beings, I’m also managing agents,” Benioff said. “Today there is an authentic agent layer around the platform. It’s not some idea of ​​a vision in a future thought, it’s what’s happening right now.”