Securely access and dynamically ground generative AI prompts with type, quality, and scope of relevant data needed to learn and provide the most reliable outputs. Merge fields with Salesforce records securely. Use semantic retrieval to bring in relevant information from support knowledge articles.
Add domain-specific knowledge and customer information to the prompt to give the model the context it needs to respond more accurately. Reduce the chance of hallucinations with added context from CRM data, knowledge articles, service chats, and more. Automatically retrieve and use that data to generate trusted responses.
* Coming soon
Mask the data used in your prompts to add an additional layer of protection. Automatically detect PII and payment data, and redact it from the prompt before it is sent to a Large Language model. Subsequenty de-mask that data after the response is created so that the proper context is shared with internal users.
Secure AI is AI that protects your customer data without compromising the quality of its outputs. Customer and company data are key to enriching and personalising the results of AI models, but it's important to trust how that data is being used.
One of the top safety concerns of AI is data privacy and security, given that many customers don't trust companies with their data. Generative AI specifically also introduces new concerns around accuracy, toxicity, and bias of content that it generates.
Salesforce keeps its customers' data secure using the Einstein Trust Layer, which is built directly into the Platform. The Einstein Trust Layer includes a number of data security guardrails such as data masking, TLS in-flight encryption, and Zero Data Retention with Large Language Models.
Deploying trusted AI will empower you to reap the benefits of AI without compromising on your data security and privacy controls. The Einstein Trust Layer allows you achieve peace of mind when it comes to where your data is going and who has access to it, so that you can focus on achieving the best outcomes with AI.
First, understand how AI can address your business needs and identify your use cases. Next, choose a partner that you can trust with a proven track record of delivering trusted AI solutions. Lastly, determine the regulatory and compliance requirements for your specific industry to inform your approach to your trusted AI journey.