What LLM does Agentforce use?

Agentforce is Salesforce’s powerful platform for building and deploying AI agents that help businesses automate tasks, make decisions, and improve customer service. If you are wondering, “What LLM does Agentforce use?” the answer is not just one model; it is a combination of Salesforce’s own custom-built large language models (LLMs) and support for popular third-party options. This setup provides users with flexibility while maintaining security and efficiency. In this guide, we will explain it in simple terms, based on the latest information.

What Is Agentforce?

Before discussing LLMs, let us briefly explain Agentforce. It is part of Salesforce’s Einstein AI suite, launched to enable companies to create “agents,” which are intelligent AI helpers capable of handling complex tasks such as answering questions, processing data, or writing code. These agents use LLMs to understand language, reason, and act. Agentforce stands out because it integrates seamlessly with Salesforce tools like CRM data, making it valuable for sales, service, and development teams.

Proprietary LLMs Powering Agentforce

Salesforce does not rely solely on external models; they have their own large language models developed by the Salesforce AI Research team. These models are specifically designed for tasks such as coding and business workflows, ensuring high performance and security within the Salesforce ecosystem.

CodeGen2.5

• What it is: A compact, fast model released in 2023, focused on low-delay tasks like code completion.
• How it’s used in Agentforce: It helps developers by auto-filling code, creating unit tests, and fixing bugs quickly. It’s trained on many programming languages, including Salesforce’s own Apex language.
• Why it’s great: Keeps everything secure your data stays inside Salesforce, and it learns from expert feedback to get better over time.
• Fun fact: Developers using this save about 125 minutes a week on average!

xGen-Code

• What it is: The newest proprietary model, built for both text and code tasks.
• How it’s used in Agentforce: Powers interactive features like chat-based coding help (e.g., Dev Assistant). It handles conversations, understands complex requests, and generates accurate responses.
• Why it’s great: It beats many other models in accuracy for Salesforce-specific jobs, and it’s efficient to run, which is good for the environment.

These homegrown models are the core of Agentforce for Developers (formerly Einstein for Developers), making coding and AI tasks smoother and more reliable.

Supported Third-Party LLMs in Agentforce

Agentforce is not limited to Salesforce’s models. It supports a wide range of managed LLMs from partners such as OpenAI, Anthropic, and Google. These models are ready to use and geo-aware, meaning they comply with local data regulations. Here is a simple table of key options:

Older models like GPT-3.5 Turbo are rerouted to newer versions for better results. This variety lets you choose based on speed, cost, or features. For example, Claude models excel in detailed reasoning, while GPT models are versatile for everyday use.

Bring Your Own LLM (BYOLLM) Feature

Want even more control? Agentforce lets you bring your own LLM through integrations with:

• Amazon Bedrock
• Azure OpenAI
• OpenAI
• Vertex AI (Google)

This means you can connect custom or preferred models while still using Agentforce’s tools. It is ideal for companies with specific needs, such as enhanced privacy or specialized training. Simply set it up through the Models API, and your agents can use these models for prompts and actions.

How to Choose the Right LLM for Agentforce?

Picking an LLM depends on your goals:

1. For coding and dev work: Stick with proprietary ones like CodeGen2.5 or xGen-Code for speed and accuracy.
2. For general agents: Try GPT-4o Mini for quick, cost-effective chats, or Claude for secure, thoughtful responses.
3. Custom needs: Use BYOLLM if you have a fine-tuned model.

Test a few Salesforce doesn’t pick one “best” for everything, so experiment based on your use case. Always check performance metrics like response time and accuracy.

Conclusion

Agentforce does not rely on a single model. The answer to “What LLM does Agentforce use?” is a multi-model approach: Salesforce’s proprietary LLMs, such as CodeGen2.5 and xGen-Code, handle coding and business-specific workflows, while third-party options like GPT, Claude, and Gemini support general reasoning, conversations, and creativity. With the Bring Your Own LLM (BYOLLM) feature, businesses can also integrate their own fine-tuned or hosted models. This flexibility ensures that Agentforce can adapt to any workflow while maintaining Salesforce’s high standards for security, trust, and scalability.

FAQs