Touchpoints
A touchpoint is a configured entry point through which users interact with an AI agent—for example, a chat assistant for a specific product or customer-care flow. Each touchpoint binds together a channel, a model and system prompt, the knowledge sources it can draw on and the tools it can call. Use this section to create touchpoints and tailor each one to a specific use case.
Available on any plan
Anyone with can edit access can create and manage touchpoints
Browse touchpoints
The Touchpoints page lists every touchpoint as a card on the left. Each card shows its name, a toggle to enable or disable it, the channel it uses (for example, Rational AI Chat) and the number of tools it has enabled. Use the search box to filter by name, and click a card to open its details on the right.
Create a touchpoint
Click New in the top-right corner. A new touchpoint is created and opened for editing so you can configure it through the tabs described below. Remember to Save your changes.
Configure a touchpoint
The details panel is organised into four tabs:
Settings
- Touchpoint ID – The unique identifier of the touchpoint (use the copy icon to copy it, for example when integrating an external client).
- Channel – The channel the touchpoint is exposed through.
Models
- System prompt – The instructions that define the agent's role and behaviour for this touchpoint.
- Default model – The model that powers the touchpoint's responses, overriding the platform default from Conversations settings.
Sources
Choose which knowledge sources the touchpoint can draw on when answering, so the agent only uses the relevant data for its use case.
Tools
Enable the tools the agent is allowed to call during a conversation.
Manage a touchpoint
Use the toggle on each card to enable or disable a touchpoint, or open the options menu (the three vertical dots) in the details panel to:
| Action | Description |
|---|---|
| Disable | Take the touchpoint out of service without deleting it. |
| Delete | Permanently remove the touchpoint. |