Managing AI Assistants
Managing AI Assistants
The AI Assistants screen is where administrators configure the native end-user assistant — its persona, which model it uses, who is allowed to chat with it, and which platform tools it may call. Assistants run on your company's configured AI provider (see AI Provider Keys); no external workflow tool is required.
Creating or editing an assistant
Click New assistant, or Edit an existing one. The key settings:
| Setting | What it controls |
|---|---|
| Name | How the assistant is labeled in the chat picker. |
| Model | Which model it runs on. Leave as Provider default to use your configured provider's default; the list reflects your company's active AI key. |
| System message | The persona and standing instructions — who the assistant is and how it should behave. |
| User-message template | Optional. Wraps each user turn. Use it to inject
context variables such as {{.message}} (the user's text),
{{.screen_context_json}} (the live Plex screen as readable JSON), and
{{.url}}. Leave blank to send the message unchanged. |
| Autonomy | Supervised asks before write actions; other modes change how much it may do on its own. |
| Enabled | Turns the assistant on or off. |
| Who can use this assistant | Restrict to users who hold a specific role, or leave as Everyone. |
{{.screen_context_json}}). A blank template means the model never receives the
screen context, even when the extension is sending it.Tool families (what the assistant may call)
Under Tool families, check only the capabilities this assistant should have — the model is offered exactly the checked ones. Options include Scripts, SQL/ODBC, Plex ERP, Lookup tables, Local databases, Dashboards, Applications, Automations, Schedules, Email templates, Document templates, Credentials (names only — never secret values), Allowed domains, and Documentation. You can additionally expose specific script tools so the assistant can run named scripts.