How to Prepare for the Salesforce AI Specialist Cert: Exams Start September 9!

The Salesforce AI Specialist certification was announced in August 2024, and exams start on September 9, 2024!

Are you planning on taking this certification? If so, this article will guide you through the resources available and what areas you need to focus on to successfully tackle this brand-new cert!

About the Salesforce AI Specialist Exam

• The exam consists of 60 multiple-choice/multiple-select questions.
• You will have 105 minutes to complete the exam.
• The passing score is TBD.
• The exam costs $200*, and retakes are $100.
• The exam can be taken online or at a testing center.
• There are no prerequisites to take this exam.

*Following Dreamforce 2024, Salesforce has made the AI Specialist certification free until December 31, 2025.

Resources

In advance of the certification going live on September 9, 2024, Salesforce has released plenty of study material to help you swot up.

• Trailhead Exam Guide: Your first port of call should always be the Salesforce Trailhead Exam Guide. Here, you can find key information about the exam, recommend resources, and a breakdown of the key topics and weightings.
• Drive Productivity with Einstein AI: This is an in-depth Trailmix designed to prepare you for the AI Specialist certification. With almost 30 things to do, from Trailhead modules to videos to Help articles, this mammoth trail comes in at an estimated completion time of 9 hours and 34 minutes! Not to worry, though, I anticipate many of you will already have done some of the tasks, especially if you tackled the AI Associate exam.
• Cert Prep: Salesforce AI Specialist: This module is a great way to refresh yourself on the key concepts and test your knowledge. (Also, side note: how nice is the user interface for the overview?! It is so easy to see at a glance what skills you will gain, what you’ve completed, and key insights about the module.) Cert Prep modules are particularly useful due to their inclusion of practice exam questions and flashcards.

Key Topics

To successfully earn your Salesforce AI Specialist certification, you’ll need to master a range of key topics. Here’s an overview of what you can expect to encounter on the exam…

Einstein Trust Layer: 15%

• Identify the security, privacy, and grounding features of the Einstein Trust Layer.
• Implement and manage the Einstein Trust Layer.

You can expect scenario-based questions in this section to test your knowledge of the components of the Einstein Trust Layer, how to manage it, and processes that protect customer data.

Some of the features of the Einstein Trust Layer are:

• Mask sensitive data, safeguarding personally identifiable information (PII) before the AI model sees it.
• Secure data retrieval of Salesforce data for grounding the prompt based on the permissions of the user executing the prompt.
• Check for toxic output, screening out bias, inappropriate language, and any other form of offensive content.
• Prevent harmful data leaks, as the Einstein Trust Layer has a zero data retention policy.
• Remain in compliance with federal and state regulations for data usage.
• Generate audit trails to easily track and review how user prompts have generated content and provide pre-built reports and dashboards for analysis.

Here are some key terms to familiarize yourself with before the exam:

• Dynamic Grounding
• Secure Data Retrieval
• Prompt Defense
• Hallucinations
• Toxicity Scoring
• Data Masking
• Zero-Data Retention Policy

Generative AI in CRM Applications: 17%

• Given a scenario, identify the correct generative AI feature in Einstein for Sales.
• Given a scenario, identify the correct generative AI feature in Einstein for Service.

This section will test your knowledge of the AI features within Salesforce, including:

• Einstein Lead Scoring
• Einstein Opportunity Scoring
• Einstein Activity Capture
• Einstein Sales Emails
• Einstein Service Replies for Email
• Einstein Call Explorer
• Einstein Call Summaries
• Einstein Case Classification
• Einstein Work Summaries
• Einstein Article Recommendations

Based on a scenario, you will be expected to choose the correct feature to support the requirements.

Prompt Builder: 37%

• Given business requirements, identify when it’s appropriate to use Prompt Builder.
• Identify the right user roles to manage and execute prompt templates.
• Identify the considerations for creating a prompt template.
• Given a scenario, identify the appropriate grounding technique.
• Explain the process for creating, activating, and executing prompt templates.

Prompt Builder allows you to create templated, reusable prompts that can be deployed across your entire org using functionality such as Custom Buttons and Flow.

1. Prompt Template Workspace: Enter your natural language prompt.
2. Resources: Select which resources you want your prompt to include.
3. Resolution: View your prompt with record data selected by the user. The data replaces the placeholders initially created in the prompt, sourced from the chosen merge fields, flows, or Apex code.
4. Response: Preview the response for selected records. Verify the output for accuracy and safety before using the template.
5. Configuration: Select which model type to use for your prompt.

This is the highest-weighted section of the exam, so be sure to spend some time here. You should be able to identify when it is appropriate to use Prompt Builder, the user roles to manage or execute prompts and prompt templates, how prompts are grounded, and how to create prompts.

If you fancy getting hands-on with prompts, the following article will guide you through five sample prompts.

Einstein Copilot: 23%

• Given business requirements, identify when it’s appropriate to use Einstein Copilot.
• Explain how the large language model (LLM) identifies and executes a copilot action.
• Leverage standard copilot actions and create custom copilot actions.
• Manage and monitor Copilot adoption.

Einstein Copilot allows you to customize the user-facing Einstein Copilot chatbot. By utilizing a set of tools, you can integrate Apex, Flow, and MuleSoft APIs, as well as generative AI components, to create custom functionality.

Model Builder: 8%

• Given business requirements, identify when it’s appropriate to use Model Builder.
• Configure standard, custom, and Bring Your Own Large Language Model (BYOLLM) generative models.

Model Builder allows you to choose a Large Language Model (LLM) for a specific use case, as opposed to other solutions such as ChatGPT. Salesforce believes that this will become extremely important in the future, particularly as specific AI models develop and businesses begin to build out their own LLMs.

Different use cases or data residency concerns may require different LLMs. That’s why it is so important that Model Builder lets you choose which LLM to use!

Summary

To ensure success on your first attempt, I strongly recommend getting hands-on practice in an AI playground (available through Trailhead) and testing your knowledge with practice exams. Will you be one of the first to snag the Salesforce AI Specialist certification? You can already sign up for the exam via WebAssessor.

What other study resources have you found helpful? Let us know in the comments!