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 SFR Model, secure, custom AI model from Salesforce, along with Pro, a premium model tier that includes leading LLMs. 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

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: Code with ease with intelligent Agentforce right beside you. Get started with agentic development workflows and Salesforce automation by chatting with Agentforce in natural language. Agentforce 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.

  • 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.

  • Test Case Generation: Use Agentforce to easily create unit test cases for your Apex methods and LWC components, using natural language prompts. Quickly get to required Apex test coverage and get your code ready for deployment.

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 solutions are designed, developed, and delivered to be compliant with our five principles for trusted generative AI.

Accuracy: We prioritize accuracy, precision, and recall in our models, and we back our model outputs up with explanations and sources whenever possible. We recommend that a human check model output before sharing with end users.

Safety: We work to mitigate bias, toxicity, and harmful outputs in our models using industry-leading techniques. We protect the privacy of personally identifiable information (PII) in our data by adding guardrails around this data.

Honesty: We ensure that the data we use in our models respects data provenance and that we have consent to use the data.

Empowerment: Whenever possible, we design models to include human involvement as part of the workflow.

Sustainability: We strive to build right-sized models that prioritize accuracy and to reduce our carbon footprint.

Learn more at Salesforce AI Research: Trusted AI.

Agentforce Vibes is powered by customized 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 SFR model is well-equipped to handle tasks that require deeper code understanding and more complex reasoning. It's been fine-tuned to specifically handle code-related tasks and support interactive features such as chat.

Our inline autocompletion currently uses the SFR model. For Agentforce, users have access to other 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 falls back to Salesforce-hosted models. 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 (SFR) model. The limit resets 24 hours after the first Pro model request.

Model behavior depends on your Einstein toggle and model provider configuration in Einstein Setup:

  • 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 our Pro model in Configure Model Providers, you'll see a message and will be reverted to the Core model.

We choose the model automatically depending on the feature:

FeatureModel Used
AgentforcePro. Fallback: SFR model.
Inline AutocompleteSFR model.

Agentforce Developer Guide

Manage Model Provider Access