部署与运维

service-itsm-teams-employee-agent-configure

forcedotcom/sf-skills

Configure the embedded Agentforce Employee Agent so it replies inside the Microsoft Teams ITSM custom client ('Salesforce Employee Assist' / 'Ask AI Agent'). Use this for: 'set up employee agent in Teams', 'embed Agentforce agent in Teams', 'make the IT Service Employee Agent reply in Teams', 'Teams Ask AI Agent not responding', 'agent joins then leaves without replying', 'configure MIAW deployment for Teams employee agent', 'Teams embedded messaging agent setup'. Builds the whole stack headlessly (zero Setup-UI clicks): the Web messaging channel with User Verification ON, the Enhanced Chat User Verification Key Set (JWKS_URL) it requires, the Teams_AgentForce custom-client deployment, the routing flow to the agent, and the Agent Access permission set that lets the portal user reach the agent. DO NOT TRIGGER for enabling the Teams feature Salesforce Go page toggle (service-itsm-teams-configure) or for configuring notification preferences.

  • 1164 次安装
  • 1100 星标
  • 收录于

安装命令

npx skills add https://github.com/forcedotcom/sf-skills --skill service-itsm-teams-employee-agent-configure

SKILL.md

Configure the Embedded Agentforce Employee Agent in Microsoft Teams

Make the embedded Agentforce agent ("IT Service Employee Agent") actually reply inside the Microsoft Teams ITSM custom client ("Salesforce Employee Assist" → "Ask AI Agent"). The Teams custom client loads a Messaging-in-App-and-Web (MIAW) deployment at runtime by its esDeveloperName, which is hard-wired to Teams_AgentForce in committed Core config (service-cloud-requestor-agent-miaw.configuration.json / the Teams app manifest) — so the Embedded Service Deployment must be named exactly Teams_AgentForce and cannot be renamed per-org.

This is the hardest, most under-documented part of Teams ITSM. The full build-from-scratch recipe — verified live against a real org — lives in:

→ references/teams-embedded-employee-agent.md

Execute one step at a time. These steps make real, state-changing API calls. Run a single operation, show its result, confirm it succeeded, then proceed — do not batch multiple setup calls into one parallel block.