Loading
Agentforce and Einstein Generative AI
Table of Contents
Filter by (0)Add
Select Filters

          No results
          No results
          Here are some search tips

          Check the spelling of your keywords.
          Use more general search terms.
          Select fewer filters to broaden your search.

            Search all of Salesforce Help
            Search all of Salesforce Help
            Prepare for Model Deprecation and Rerouting

            You are here:

            1. Salesforce Help
            2. Docs
            3. Quickstart Your Einstein Generative AI Solution

            Prepare for Model Deprecation and Rerouting

            This document provides guidance on retesting Salesforce AI implementations during model deprecation and rerouting. Deprecation and rerouting are considered temporary. If your model is in one of these states, consider switching to a new model.

            Term Glossary
            Deprecation In the context of AI development, “deprecation” describes a model that is no longer recommended for use. Model providers, such as Open AI, typically deprecate old models when new, improved models are available. Deprecation is a formal process that indicates to users to transition to a different model. During the deprecation phase, a deprecated model still works as designed.
            Rerouting Model rerouting is a process of redirecting requests from an older model to an available alternative. Rerouting can occur when the model provider deprecates or retires the model. Salesforce reroutes requests to ensure the continuity of service. 

            Deprecation and Rerouting Information

            Model deprecation and rerouting notices are published in the Einstein Platform release notes. A list of deprecated and rerouted models are also listed on the Large Language Model Support page.

            When a model provider retires a model, Salesforce may route requests to the latest version of that model family to ensure continuity of service. For example, OpenAI GPT 3.5 Turbo 16k requests route to OpenAI GPT 3.5 Turbo.

            Define Success for Your Implementation

            1. Define what success looks like for your end users. Different use cases require unique testing methods.
            2. Save testing results from the initial implementation phase. If you have examples of expected responses, use them to compare with the result. Use the same tests for the new model to ensure there aren’t significant variations.

            Guidance When Changing Models

            1. Note
              Note Review the model configuration in Model Builder. See, Create a Model Configuration.
              When configuring a model in AI Models (formerly Einstein Studio) Model Playground, deprecated and rerouted models can't be selected. Instead, you can select a new foundation model to continue using your configurations. 
            2. In AI Models, create a new configured model that matches the rerouted model (if applicable). Set the configuration with the same hyperparameters as the previous model.
            3. After saving the configuration, open Prompt Builder. 
            4. Retest prompt templates using the new model. Testing prompts and responses in Prompt Builder can be done directly in the Model Playground in AI Models. Adjust the prompt template so that it aligns with your goals.
            5. If your implementation includes agents, open the agent in Agentforce Builder. In Agentforce Builder, you can test subagents, actions, and knowledge to configure an agent. Adjust the agent behavior so that it aligns with the predetermined definition of success.
            6. After setting the configured model, prompt template, and agent individually, test your entire AI implementation end to end. It is important to continually get user feedback for improvements. 
             
            Loading
            Salesforce Help | Article