Overview
The Agentforce Vibes extension is an AI-powered developer tool that's available as an easy-to-install Visual Studio Code extension built using secure AI models. The extension is available in the VS Code and Open VSX marketplaces as a part of the Salesforce Extension Pack, and Salesforce Extension Pack (Expanded) in the VS Code desktop application, and in Code Builder.
It is important to note that Salesforce does not use customer data to train our LLMs.
Agentforce Vibes assists you throughout the Salesforce development process with expertise learned from anonymized code patterns. Our suite of AI-powered developer tools increases productivity and provides helpful assistance for complex coding tasks. We enforce development best practices with code generation and our suite of recommended static analysis and security scanning tools. With boilerplate code generation as its foundation, AI-assisted tooling also makes it easier for new developers to onboard to the Salesforce Platform.
Agentforce Vibes generates Apex code from natural language prompts and automatically suggests code completions for you as you type. When enabled along with IntelliSense, this feature makes Salesforce development in Visual Studio Code even richer. Familiarity with Visual Studio Code is assumed.
-
Agentforce Chat: Code with ease with intelligent chat right beside you. Get started with agentic development workflows and Salesforce automation by chatting in natural language. Agentforce Vibes takes action to execute tasks like analyzing unfamiliar code, improving documentation, and completing complex development workflows.
-
Customization Rules and Context: Create persistent rules and provide context for more accurate, action-oriented responses from Agentforce Vibes.
- Inline Code Completions: As you type, Agentforce Vibes can suggest code completions, without any interruptions to your workflow. Easily pick the suggestion that works for you. Use this feature in Apex and LWC (JavaScript, CSS, and HTML) files.
The Agentforce Vibes extension uses generative AI, which can produce inaccurate or harmful responses. The output generated by AI is often nondeterministic. Before using the generated output, review it for accuracy and safety. You assume responsibility for how the outcomes are applied to your organization.
Agentforce Vibes is powered by Large Language Models (LLMs) developed by Salesforce, along with Pro, our premium model tier. Pro requests are limited to 50 per day per org, or up to 1,000,000 tokens per day per org, whichever limit is reached first.
Salesforce’s Core model powers interactive experiences like chat and serves as the free-tier option. It also acts as the fallback when you reach the token limit on the Pro model.
Our inline autocompletion currently uses the GPT-4.1 model. For chat, users have access to Salesforce-hosted models, while a premium model tier (Pro) is available up to specified token or request limits. When these limits are reached, the system automatically uses our fallback model. All third-party models are operated within the Salesforce Trust Boundary, or by Salesforce partners inside a shared trust zone.
Each Salesforce org is limited to 50 requests per day on the Pro model. The 24-hour window starts with your first Pro model request. Once the limit is reached, additional requests fall back to the Core model, which also has a limit of 15M tokens per month per org, and 1500 requests per month per org. The limit resets 24 hours after the first Pro model request.
For inline autocompletion, the limit is 1500 requests and 15k tokens per day per org. When the limit is reached, no new completions will be available until the limit resets.
Model behavior depends on your Einstein toggle and model provider configuration in Einstein Setup, if available:
-
If the Einstein toggle is
OFF, model choice doesn't affect model availability. You can continue using Pro without issues. -
If the Einstein toggle is
ON, and you haven't picked ourPromodel inConfigure Model Providers, you see a message and are reverted to the Core model.
Our Pro model is used if either model provider configuration or Einstein isn't available in your org.
We choose the model automatically depending on the feature:
| Feature | Model Used |
|---|---|
| Agentforce Vibes Chat | Pro. Fallback: Core model. |
| Inline Autocomplete | GPT-4.1 model. |