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 (
readvscommerce) per agent.Pair agent actions with the same journeys customers use, so flows stay consistent and audited.
Related
Last updated
Was this helpful?
