ApivomApivom
Get Demo

Salesforce Agent API (Agentforce) Connector

Salesforce Agent API — the Agentforce interface for calling a published agent from outside Salesforce: open a session on an agent, send messages synchronously or as a streamed response, post feedback and close the session — registered in Apivom Atlas as 5 routes on api.salesforce.com.

What you can do

  • Sessions: start a session on a published Agentforce agent by agent id, end it when the conversation is over
  • Messages: send an end-user message and receive the agent's reply synchronously, or stream the response as server-sent events
  • Feedback: post thumbs-up/down and comments on an agent reply for the Agentforce quality loop
  • 5 routes (all write) on api.salesforce.com with your My Domain org as issuer, documented in the AI integration guide (llms.txt)

Use cases

  • Agentforce agent behind your own channel — Open a session and relay messages from a website, kiosk or internal tool so a published agent answers where your users already are.
  • Streamed replies in a custom UI — Use the streaming route to render the agent's answer as it is generated instead of waiting for the full reply.
  • Feedback loop for agent quality — Capture end-user ratings on each reply and send them to Salesforce so the Agentforce team can tune topics and actions.

The Agent API is the programmatic front door to Agentforce: once an agent is built and published in your Salesforce org, any external channel can open a session with it, exchange messages — in one shot or streamed token by token — collect feedback and end the session, with Salesforce handling grounding, actions and guardrails inside the org. Apivom Atlas registers the five v1 routes exactly as Salesforce publishes them, on api.salesforce.com, with a Connected App that has the Agent API scope issuing the token. No Apivom product calls the Agent API today: Apivom's conversational assistants run on Apivom's own stack and are not Agentforce agents, and no workflow hands conversations to Salesforce. The connector exists so a customer who has invested in Agentforce can scope an Apivom channel or workflow that fronts their agent, per customer.

Authentication

A Connected App on your Salesforce org (consumer key + secret) and your My Domain instance URL. The caller runs the OAuth 2.0 flow and sends the access token as Bearer; the instance URL becomes the per-request base URL. Apivom Atlas forwards, logs and stores nothing.

Frequently asked questions

Can I switch this connector on today?

The connector is registered in Apivom Atlas — every route is catalogued, the credential contract is published and the AI integration guide (llms.txt) is live — and your credential can be stored in Apivom Iris. Wiring it into a product workflow (sync, automation, notifications) is done per customer: tell us the use case and we scope it with you.

Are Apivom's conversational assistants built on Agentforce?

No. Apivom's assistants use Apivom's own conversational models and channels. The Agent API connector is registered so a customer's Agentforce agent could be fronted by an Apivom channel if they ask for it — nothing of the sort runs today.

What does the agent need on the Salesforce side?

An Agentforce licence, an agent built and published in Agent Builder, and a Connected App with the Agent API scope that your org's admin authorises. Agentforce consumption is billed by Salesforce on the org that owns the agent.

Does Apivom charge per API call for this connector?

No. Connectors are part of your Apivom tenant and are not metered in the Atlas portal. The vendor's own pricing, quotas and rate limits still apply to the account you connect — Apivom paces its calls to stay inside them and shows every call in your tenant's integration log.

Where are my credentials stored and who can see the traffic?

Apivom Atlas is a stateless gateway: it never stores vendor credentials or tokens. The Apivom product that connects keeps the credential encrypted in your tenant database, and every request and response is logged in your tenant only — your data is never shared across tenants.

More Atlas integrations

AI integration guide (llms.txt)

Machine-readable markdown — feed it to your AI assistant as integration instructions.