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’re wondering, “What LLM does Agentforce use?” the answer isn’t just one model it’s a mix of Salesforce’s own custom-built large language models (LLMs) and support for popular third-party options. This setup gives users flexibility while keeping things secure and efficient. In this guide, we’ll break it down in simple terms, based on the latest info as of August 2025.

What Is Agentforce?

Before diving into the LLMs, let’s quickly explain Agentforce. It’s part of Salesforce’s Einstein AI suite, launched to let companies create “agents” smart AI helpers that can handle complex jobs like answering questions, processing data, or even writing code. These agents use LLMs to understand language, reason, and act. Agentforce stands out because it works seamlessly with Salesforce tools like CRM data, making it great for sales, service, and development teams.

Proprietary LLMs Powering Agentforce

Salesforce doesn’t rely only on outside models; they have their own LLMs built by the Salesforce AI Research team. These are designed specifically for tasks like 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 isn’t limited to Salesforce’s models. It supports a wide range of managed LLMs from partners like OpenAI, Anthropic, and Google. These are ready-to-use and geo-aware (meaning they follow local data rules). Here’s a simple table of key ones:

Older models like GPT-3.5 Turbo are rerouted to newer versions for better results. This variety lets you pick based on speed, cost, or features for example, Claude models shine in detailed reasoning, while GPT ones 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’s perfect for companies with specific needs, like extra privacy or specialized training. Just set it up via the Models API, and your agents can tap into these 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 doesn’t rely on a single model. The answer to “What LLM does Agentforce use” is a multi-model approach: Salesforce’s proprietary LLMs like CodeGen2.5 and xGen-Code handle coding and business-specific workflows, while third-party options such as GPT, Claude, and Gemini cover 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