
Argent for Salesforce Agentforce
Models you register through Salesforce's LLM Open Connector can run through Argent. Here is where Argent fits, how it connects and what your team sets.
What Argent does with Salesforce Agentforce
The models you register through Salesforce's LLM Open Connector call your Argent route, so Argent checks and records each of those calls. A small adapter that you build or reuse sits in front of the route; Prompt Builder templates and custom actions can then use the registered model.
- A named agent with a human owner. The connection uses its own Argent agent key, tied to an accountable person. Identity tethering
- Only the models you allow. The route reaches only the models your policy names. Model control
- Sensitive data handled before it leaves. Prompts and replies are scanned and redacted or blocked as your policy says. Sensitive data redaction
- Spend priced and capped, every call signed. Each request is metered against budgets and written to the signed audit ledger. AI spend caps
How Salesforce Agentforce connects
Salesforce Agentforce reaches Argent in one way.
- Gateway base URL. The adapter you build or reuse (in Salesforce's Open Connector format) points the registered model at your Argent route and uses an Argent agent key in place of the provider key. Argent adds the real provider credential from your vault on the way out.
The same steps are in the Argent console under Integrations > AI Clients, and each agent's Connect tab gives the copy-paste values for your tenant.
What you configure
What your team sets in Salesforce Agentforce. These are the settings the Argent console shows for this tool. Values in angle brackets come from your tenant.
- Build or reuse an Open Connector adapter. Implement the LLM Open Connector API (Salesforce einstein-platform repo) in front of the Argent gateway route (adapter translates Salesforce's chat-completions-style request to the route and adds an Argent agent key).
- Register the model in Model Builder. Setup > Einstein Studio > Model Builder > Add Model > LLM Open Connector > endpoint = the adapter's HTTPS URL on port 443.
- Use it where allowed. Prompt Builder templates and custom actions can select the registered model.
Keep registered models on Argent
Keep registered models on Argent. These controls are documented by the platform each one belongs to (linked); pair them with the Argent settings above.
- Salesforce Einstein Trust Layer / admin. Admin chooses which models and where; Open Connector models are registered by admins only. Vendor docs
Want to see which AI tools people already run before you push anything? Start with Shadow AI discovery in watch mode. Watch before you enforce
Check that it works
Send one request and look for the signed row. Prompt Builder test run shows a signed LLM row in the Argent console live stream under the connector's agent key.
Every request also appears on the live stream with the agent's name and owner, and in the session view. Session replay
Where to go next
Keep going. Pages that cover the same ground from another angle.
- Use case: Governing customer-facing AI assistants
- Use case: Controlling agent tool access: MCP and agent-to-agent
- Goals: See all AI in your company, Data loss prevention, Budget and token spend, Model control and routing, Agent identity and ownership
- Capabilities: Keyless agents, Prompt injection defense, Response screening, One-click audit evidence
- Related integrations: ServiceNow Now Assist, OpenAI SDKs, Anthropic SDKs, Amazon Bedrock SDKs
- All integrations: Browse every AI client, provider, vault and identity source
Want this running on your own use cases?
Book a demo