> For the complete documentation index, see [llms.txt](https://docs.peakcommerce.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.peakcommerce.com/integrations/crm-and-revops/salesforce-integration/agentforce.md).

# Agentforce

**Salesforce Agentforce** is Salesforce's platform for building and running autonomous AI agents — assistants that reason over your data and take actions on a customer's behalf. Agents are only as useful as the systems they can act in. For subscription commerce, that means an agent needs a governed way to price plans, build carts, and place or change orders — not just read records. PeakCommerce gives Agentforce agents exactly that surface, and the integration is supported today and rapidly deepening toward fully native.

## What you can do with it

* **Agent-driven commerce** — Agentforce agents browse the catalog, resolve live pricing, preview totals, build carts, and place or change orders through PeakCommerce.
* **Governed by the same guardrails as every channel** — agents act within the same profiles, policies, offer eligibility, and discount ceilings as the journey UI. The agent proposes; PeakCommerce binds the price.
* **Conversational journeys** — an agent runs, or hands off to, a PeakCommerce journey to complete a purchase, plan change, retention save, or cancellation.

## How it fits

PeakCommerce exposes its commerce operations through the **Agent API** (`/api/v1`) — an action-oriented, discoverable surface where every response carries a `nextActions` array so an agent always knows the next legal move. Operations are protected by scoped API keys (`read`, `commerce`, `admin`), idempotency keys, and the platform's policy, offers, and pricing engines. Agentforce agents call these operations to sell and service subscriptions exactly as the buyer-facing UI does; pricing and discount authority stay server-side and are never delegated to the model.

## Who and when

Best for teams already standardizing on Agentforce that want their agents to transact real subscription commerce — not just summarize records — while keeping finance and revenue policy in control.

## Gotchas

* Discount and pricing authority resolve from your tenant policies at request time; an agent cannot exceed them, by design.
* Scope API keys to least privilege (`read` vs `commerce`) per agent.
* Pair agent actions with the same journeys customers use, so flows stay consistent and audited.

## Related

* [Salesforce Sales Cloud Integration](/integrations/crm-and-revops/salesforce-integration/salesforce-sales-cloud-integration.md)
* [Salesforce Revenue Cloud](/integrations/crm-and-revops/salesforce-integration/revenue-cloud.md)
* [What Salesforce apps does PeakCommerce natively integrate with?](/integrations/crm-and-revops/salesforce-integration/what-salesforce-apps-does-peakcommerce-natively-integrate-with.md)
* [CRM & RevOps](/integrations/crm-and-revops/crm-and-revops.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.peakcommerce.com/integrations/crm-and-revops/salesforce-integration/agentforce.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.