Agentforce uses ReAct prompting to help agents reason through problems and can lead to fully autonomous agents that offer personalized support based on a user's specific inquiry. Salesforce also provides a tool called Agentbuilder for clients to create and deploy custom Agentforce agents. The company measures the success of its software by the success of its clients and aims to see a broad adoption of AI agents designed with Agentbuilder within their CRM systems and in Slack.
Key takeaways:
- Salesforce has expanded its AI tools with Agentforce, a platform that helps Salesforce clients build and deploy agents to automate tasks such as generating written reports from sales data and creating summaries of conversations in Slack.
- Agentforce's core technology, the Atlas Reasoning Engine, was developed by Salesforce's engineering team and can access AI models from third-party technology partners including OpenAI, Anthropic, Amazon, and Google.
- The Atlas Reasoning Engine uses what's known as ReAct prompting to help agents reason through problems and can lead to fully autonomous agents that offer personalized support based on a user's specific inquiry.
- Salesforce's clients can also use a tool called Agentbuilder to create and deploy custom Agentforce agents that can act on triggers, such as receiving an email or making a sale, without a direct prompt from a company's employees.