VIDIZMO integration brief · Salesforce · vidizmo.ai/integrations/catalog/salesforce

Integrations / Salesforce

Salesforce

Put an agent to work on accounts, cases and opportunities. Visit website

Salesforce is the system of record for accounts, cases, opportunities and service history.

Through its official MCP server and REST API an agent reads that record and acts on it: summarising an account before a renewal, drafting a case response from how similar ones were resolved, checking an opportunity against the evidence in call recordings, and writing the outcome back to the right object. Where a step writes back or sends something, a human-in-the-loop node puts a person in front of it first.

Player and library views embed into Salesforce pages, so the person working a case sees the relevant recording without leaving it, and the embed resolves against their identity.

Every Case Beside the Recording That Explains It

Open as a two-page brief

Salesforce is the system of record for accounts, cases, opportunities and service history. Connect it and AI Intelligence Hub reads that record beside the recorded calls, statements and training video that Nexus holds, answers questions across both, and drafts the next step with a person approving before anything is written back. A player embeds into the Salesforce page, so the person working a case sees the recording without leaving it. Salesforce stays the system of record.

How it connects

Salesforce publishes an official MCP server, and AI Intelligence Hub connects to it as an MCP client. The server is configured once with a name, URL, transport and the headers that carry its credential; its tools are discovered when the connection is bound. In a workflow, an MCP node runs one named tool with arguments fixed at design time. For an agent, an MCP tool hands over the server's tool list, and the agent chooses a tool and fills the arguments as it works. The connection carries the credential it is configured with, so what an agent can read in Salesforce is bounded by what that credential is granted there. Retrieval from the library alongside it still runs under the asking user's own identity.

Where a step needs something the MCP server does not expose, the HTTP Request node calls Salesforce's REST API. In the other direction, the platform's REST API and a workflow's HTTP trigger are the inbound paths, so automation on the Salesforce side can start a workflow.

The JavaScript widget places player and library views inside Salesforce pages, restricted to approved domains, and the embed resolves against the viewer's own identity, so the platform's access control still applies. Account, case and opportunity records stay in Salesforce.

What you can do together

  • Ask AI Intelligence Hub to summarize an account before a renewal, drawing on the Salesforce record and the recorded calls in the library, each source cited.
  • Draft a case response from how similar cases were resolved, approved by the agent before it is written back to Salesforce.
  • Check an opportunity against what was actually said in the recorded call, so the forecast rests on the conversation rather than on a one-line note.
  • Show the relevant recording inside the Salesforce case page from Nexus, with access resolving against the viewer's own identity.

A scenario

  1. 09:10An adjuster opens a case. The claimant's recorded statement, held in Nexus, plays inside the Salesforce page through the embedded player, and the adjuster sees only what their own identity allows.
  2. 09:20The adjuster asks the assistant what the claimant said about when the incident happened and whether it matches the case notes. AI Intelligence Hub reads the case through Salesforce's MCP server, finds the statement in the library, and cites the moment in the transcript beside the case field it compared.
  3. 09:35The adjuster asks for a response drafted from how similar cases were resolved. The assistant reads those cases through the same connection, drafts it, shows an editable preview and waits. The adjuster approves, and the response is written back to the case.
  4. 14:00The claims manager asks for a summary of the account before a renewal conversation and gets the Salesforce history and the recorded calls in one answer, each point cited.
  5. Next morningA workflow reads the cases opened overnight, drafts a first response for each from the resolved cases most like it, and pauses at an approval node until an adjuster signs off.

What stays where

Salesforce remains the system of record

Accounts, cases and opportunities stay in Salesforce, and its own permissions decide what a query returns. AI Intelligence Hub reads through the MCP server and the REST API, and writes back only after a person has approved.

The recordings stay in the library

Calls, statements and training video sit in Nexus under role-based access, audit logs and retention. Retrieval runs under the asking user's identity, so an answer cannot draw on material that user could not open.

Nothing is replaced

Salesforce pages keep their layout, the player is an embedded view inside them, and the platform's own reporting continues alongside.

Processing runs where you deploy the platform

Shared or dedicated SaaS, your own cloud, or on premises. Reaching Salesforce's hosted MCP server needs a network path to it.

Products and solutions

Next step

See it on your own Salesforce instance. We will show the connection made, the data moving and the output, then size it for your deployment.

Request a demonstration  or write to sales@vidizmo.ai

sales@vidizmo.ai  ·  vidizmo.ai/integrations/catalog/salesforce

Not what you need?

We build it

Send us your API documentation and we build, test and maintain the connector, at no development cost to you.

Request this integration

Bring an MCP server

If the system publishes a Model Context Protocol server, AI Intelligence Hub connects to it as a client with configuration alone.

Define a REST endpoint

Describe your endpoint and it becomes a node in an agent workflow, without waiting on our roadmap.