Salesforce Previews Enterprise AI Harness and AI Control Plane
Salesforce previewed Enterprise AI Harness and AI Control Plane to help customers build and manage AI agents with improved reliability and security.
Salesforce Inc. previewed two offerings to help customers build and manage artificial intelligence agents. The company introduced Enterprise AI Harness and AI Control Plane according to SiliconANGLE.
Enterprise AI Harness details
Enterprise AI Harness is a collection of technologies designed to improve the reliability and security of customers' AI agents. Many of the technologies that underpin the offering are already available in its cloud services. The rest will start rolling out early in Salesforce's 2028 fiscal year, which begins next February. The offering will comprise six main feature collections. Half of them focus on the business data that AI agents use to carry out their work. Trusted Context brings together data assets such as customer records and product availability information. Support for real-time signals will also be included. Another set of features will ensure that the data used by AI agents is accurate. Salesforce plans to provide multiple information quality controls including a data lineage tool. Cybersecurity teams will gain the ability to regulate which agent can use what dataset and how. The offering will include an intelligent model routing mechanism to send agent requests to the most suitable LLM based on parameters such as accuracy and cost. Enterprise AI Harness will enable customers to pair their AI agents with deterministic reliability controls. It will also ease the task of connecting agents to external applications.
AI Control Plane features
The AI Control Plane will enable administrators to centrally monitor AI agents' performance and inference costs. The offering will help ensure that agents adhere to cybersecurity policies.
What it means for revenue teams
Revenue teams can use the new data controls and real-time signals to improve the accuracy of AI agents handling sales tasks. Administrators will gain tools to monitor agent performance and costs in one place. These capabilities may help teams apply consistent policies when agents interact with customer data and external systems.
