Dialog Settings
The Dialog page controls how the agent manages conversations — what language it uses, whether it draws answers from your documents, how it formats responses, and what suggested replies appear after each message.
Navigate to Persona → Dialog in the left sidebar.
Changes to these settings affect token consumption and therefore the cost of running the agent. The page header includes a reminder of this.
Reference Settings
These settings control whether the agent draws on your Resources when forming answers. Resources — the documents, videos, and websites you add to your agent — are processed into searchable chunks that become the references the agent retrieves and cites in its responses.
Enable Reference
When enabled, the agent searches references derived from your uploaded Resources — documents, videos, and websites — before responding. This allows it to give accurate, context-specific answers grounded in your own content rather than relying solely on the base AI model's knowledge.
Disable this if your agent is intended for general-purpose conversation with no proprietary knowledge base.
How Resources become references: Every document, video, and website you add through the Resources menu is parsed and broken into text chunks. These chunks are what the agent actually searches — they are the references. Uploading to Resources is a prerequisite for reference-based answers to work.
Restrict Answer
Only available when Enable Reference is turned on.
When enabled, the agent will only answer questions that can be answered using the knowledge base. If no relevant content is found, it declines to answer rather than guessing or using general knowledge.
Use this when accuracy and traceability to your documents is critical (e.g., legal, compliance, or technical support agents).
Formatting Settings
These settings control the structure and visual format of the agent's responses.
Enforce Markdown Response
Forces all responses to use markdown syntax — headers, bold text, bullet lists, code blocks, and so on. Enable this when your chat interface renders markdown and you want consistently structured answers.
Disable this for voice interfaces or plain-text channels where markdown symbols would appear as raw characters.
Enable Charts in Response
Allows the agent to generate and embed charts or data visualizations inside responses when the data warrants it. Useful for analytics or reporting assistants.
Show Table in Presentation Panel
When enabled, tables generated in a response are rendered in the presentation panel (the right-side panel in presentation mode) rather than inline in the chat thread. This keeps the chat readable while detailed tabular data appears in a dedicated area.
Dialog Settings
Dialog Language
Sets the language the agent uses when composing responses. Select from the dropdown or type a custom value.
If you select Auto, the agent will match the language the user writes in. For example, if a user sends a message in French, the agent will respond in French. This is useful for multilingual audiences where you want each user to receive answers in their own language.
Setting a specific language (e.g., English, Indonesian) overrides Auto — the agent will always respond in that language regardless of what language the user writes in.
Enable User to Change AI Model
Allows end users to switch between different AI models during their conversation. When enabled, a model picker appears in the chat interface.
Allowed Conversation AI Models
Visible only when Enable User to Change AI Model is on. Select which models users are allowed to choose from. Users cannot pick a model outside this list.
The first model in the list becomes the default — it is the model the agent uses at the start of every conversation before the user makes a selection.
Enable Copy to Clipboard Button
Shows a copy button on each agent response, allowing users to copy the text to their clipboard with one click.
Display Feedback Buttons
Shows thumbs-up and thumbs-down buttons below each agent response. Users can use these to provide feedback, which is recorded for review in the monitoring dashboard.
Show Conversation History
When enabled, a My Chats panel appears in the chat sidebar. This panel lists the user's past conversations with the agent, showing a preview of the first message, the date it was started, and the total number of messages exchanged.
Users can click any conversation in the list to resume it — the full message history is reloaded and the conversation continues from where it left off.
This feature only activates for signed-in users. Even if the setting is enabled, anonymous or guest users will not see the My Chats panel and cannot resume previous conversations. If a guest later signs in, their previous anonymous session becomes associated with their account and will appear in the history.
When disabled, the My Chats panel is hidden entirely and each session starts fresh. Past conversation data is still retained on the backend — it simply is not surfaced in the interface.
Document Upload Restrictions
A free-text field where you define rules for blocking certain types of document uploads from users.
Example restriction:
Prevent upload of documents containing personal identifiable information such as national ID numbers, passport numbers, or documents with photographs of individuals. Block files with sensitive financial data such as credit card numbers or bank account details.
Leave this field blank if you want to allow all document types.
Response Suggestions
After each agent response, the system can display a set of follow-up prompts for the user to click. Clicking a suggestion inserts its text directly into the chat input, making it easy for users to continue the conversation without typing.
Suggested Response Type
Controls whether suggestions appear and how they are sourced.
| Type | Behaviour |
|---|---|
| None | No suggestions are shown after any response. |
| Fixed | A set of suggestions you define in advance is shown after every response. Each suggestion has a label (the text shown on the button) and a message (the text inserted into the chat input when clicked). These are the same for every response. |
| Dynamic | After each response, the AI automatically generates three follow-up questions based on the conversation context and appends them as suggestion buttons. The questions change with every response. |
Suggestion Content (Fixed mode only)
When Fixed is selected, a list editor appears below the type selector. Use it to define the suggestions that will appear after every agent response. Each entry requires:
- Label — the text displayed on the suggestion button
- Message — the text that gets inserted into the chat input when the user clicks the button
The label and message can differ. For example, a button labelled "Tell me more" can insert a longer, more specific question as the message.
Saving Changes
Click Save after adjusting any setting. Publish your agent to propagate the changes to end users.