Chatbot
The chatbot is the conversational interface where users interact with AI-powered agents in VIDIZMO. It provides a messaging experience that allows users to ask questions, receive responses, and engage with organizational knowledge and automated workflows through natural language.
What Is The Chatbot
The chatbot serves as the front-end layer of VIDIZMO Intelligence Hub. While agents define behavior and workflows handle processing logic, the chatbot provides the visual interface where conversations happen.
Users interact with the chatbot by typing messages. The chatbot sends these messages to the configured agent, which processes them through its connected workflow and returns responses. This interaction happens in real time, with responses streaming as they are generated.
How The Chatbot Works
When a user sends a message through the chatbot interface, the following process occurs:
-
Message Submission: The user types a question or request in the chat input field and submits it.
-
Agent Routing: The chatbot forwards the message to the active agent. The agent applies its system prompts and determines how to process the request.
-
Workflow Execution: The agent passes the request to its connected workflow. The workflow executes nodes in sequence, retrieving data, processing information, and generating a response.
-
Response Streaming: As the workflow produces output, the chatbot displays the response progressively. Users see text appear in real time rather than waiting for the complete response.
-
Conversation Continuity: The chatbot maintains conversation history within a session, allowing follow-up questions and contextual interactions.
Chatbot and Sessions
Each conversation in the chatbot occurs within a session. Sessions group related messages together and maintain context across multiple exchanges.
Key session behaviors:
- Session Creation: A new session starts when a user begins a conversation
- Message History: All messages within a session are preserved and accessible
- Context Retention: The agent can reference earlier messages in the session to provide relevant responses
- Session Management: Users can start new sessions or return to previous conversations
Chatbot Capabilities
The chatbot interface supports several interaction patterns:
- Text Messaging: Send natural language questions and receive AI-generated responses
- Suggested Prompts: Select from predefined prompts configured in the agent to start conversations quickly
- Content Selection: Browse and attach portal content to messages using inline commands or the content browser
- Extended Search: Toggle comprehensive data fetching for more thorough search results
- Reasoning Control: Enable or disable AI reasoning per message and cancel in-progress operations
- Citations: View source references when the agent includes citations in responses
- Streaming Responses: Watch responses generate in real time as the workflow executes
- Approval Requests: Respond to human-in-the-loop approval prompts when workflows require user confirmation
Selecting Content in Chat
Attach portal content to a chat message to make queries more precise. Content can be selected using inline commands typed in the chat input field or through the content browser accessed via the Browse button.
Inline Content Selection
Type commands directly in the chat input field to search and select content.
/— Open a dropdown listing content in the current folder./?term— Search across all folders for content matching the term./.foldername/or/foldername/— Navigate into a folder by name.- Type
/after a folder link — Open that folder's contents and replace the folder link. /..— Navigate up one folder level.
After selecting an item, it appears as a link in the message. Select the link to open the content in a new tab.
Multiple items can be attached by repeating this process. Inline links are recognized by the chatbot and passed to workflows for processing.
Content Browser
Select the Browse button next to the chat input field to open the content browser. The browser provides a visual interface for navigating and selecting content.
- Search bar — Enter a search term to filter content.
- Globe toggle — Switch between searching the current folder and searching all folders.
- Breadcrumb navigation — Select any level in the breadcrumb path to jump to that folder.
- Folder chevron (→) — Enter a folder without selecting it as an attachment.
Select an item from the list to attach it to the message.
Keyboard Shortcuts
The following keyboard shortcuts are available when the content dropdown is open:
| Shortcut | Action |
|---|---|
| Arrow keys | Navigate through dropdown items |
| Enter | Select the highlighted item as an attachment |
| Tab | Enter the selected folder |
| Shift+Tab | Navigate up one folder level |
| Ctrl+G | Toggle between current folder and global search |
| Escape | Dismiss the dropdown |
| Backspace | Remove an attached content link (when the cursor is directly after the link) |
How Content Selection Works
When a message includes selected content:
- The chatbot extracts content identifiers from attached links.
- Identifiers are sent to the connected agent as part of the query.
- Workflows incorporate this context when processing the request.
- Search operations can be scoped to the selected content.
This enables queries such as:
"Summarize this document" "Which topics are covered in these videos?"
where the referenced content is explicitly attached to the message.
Content Display in the Selector
The content selector displays the following information for each item:
- Content title — The name of the item.
- Parent folder — The organizational context of the item.
- Content type icon — Indicates video, document, image, or other format.
- Selection filter — Items already attached are removed from the list.
The selector supports infinite scrolling and real-time filtering as search terms are entered.
Controlling AI Reasoning
VIDIZMO supports extended reasoning for certain AI models, allowing deeper analysis before generating responses. The reasoning toggle in the chat input area controls reasoning per message. Ongoing operations can also be canceled, giving fine-grained control over response depth, speed, and resource usage.
Enabling or Disabling Reasoning
Select the reasoning toggle in the chat input area to control reasoning for the next message.
- Enabled: The AI performs multi-step reasoning to produce analytical and comprehensive answers.
- Disabled: The AI uses standard processing for faster responses and lower computational cost.
Note: The reasoning toggle applies to the current message only. When reasoning is disabled by the user, this overrides any reasoning configuration set at the workflow node level. When enabled by the user, the node-level configuration applies.
Canceling Ongoing Operations
Select the cancel button during workflow execution to stop the current operation.
- Partial responses generated before cancellation remain visible.
- The system handles the interruption without data loss.
Cancellation is useful when:
- Responses take longer than expected.
- The query needs modification mid-process.
- Resource-intensive operations need to be stopped.
When to Use Reasoning Control
Disable reasoning for:
- Simple queries that do not require multi-step analysis.
- High-volume interactions where speed is critical.
- Cost-sensitive scenarios with limited computational resources.
Enable reasoning for:
- Complex tasks that require multi-step logic.
- Analytical queries requiring thorough context understanding.
- Situations where accuracy and completeness are prioritized over speed.
Extended Search Mode
Extended search enables comprehensive data fetching across the portal content library. When enabled, search operations retrieve more thorough results by expanding the scope and depth of content queries. When disabled, standard search provides faster results with default filtering.
Enabling or Disabling Extended Search
Select the extended search toggle in the chat input area to control search behavior for the next message.
- Enabled: Search operations fetch data comprehensively, returning more detailed and broader results.
- Disabled: Search operations use standard parameters for faster response times.
Note: The extended search toggle applies to the current message only. This setting overrides the default value configured in the Search Mashup node or tool within the workflow.
When to Use Extended Search
Enable extended search for:
- Queries that require results from across multiple folders or content types.
- Research tasks where completeness is critical.
- Situations where initial results may not surface relevant content.
Disable extended search for:
- Quick lookups where speed is preferred.
- Queries targeting specific, known content.
- High-frequency interactions where response time matters.
Where The Chatbot Appears
The chatbot is available in multiple contexts depending on configuration:
Portal Chatbot
Within the VIDIZMO portal, users access the chatbot through the interface. The portal chatbot connects to the portal's configured agents, with the default agent active unless users select an alternative.
Embedded Chatbot
Organizations can embed the chatbot on external websites using an agent's embed code. The embedded chatbot provides the same functionality as the portal version while appearing within external applications. Branding settings configured in the agent apply to the embedded interface.
Chatbot and Agents
The chatbot displays content and behavior defined by the active agent. This includes:
- Welcome Message: The initial greeting shown when users open the chatbot
- Suggested Prompts: Quick-start options that appear before the first message
- Response Style: The tone and format defined by the agent's system prompts
- Fallback Messages: The response shown when the agent cannot process a request
- Visual Branding: Colors, fonts, and logos configured in the agent's branding settings
Switching agents changes these elements without modifying the underlying chatbot interface.
Summary
The chatbot is the conversational interface that connects users to VIDIZMO Intelligence Hub capabilities. It handles message input, displays streaming responses, and maintains conversation sessions. Users can attach portal content to messages through inline commands or the content browser, control AI reasoning depth per message, and toggle extended search for comprehensive data fetching. While agents define behavior and workflows process requests, the chatbot provides the user experience layer where all interactions occur.