Manage projects
Projects are the core organizational unit in Biel.ai where you configure your chatbot's behavior, data sources, and security settings.
View all projects
The Projects dashboard displays a list of all your projects.

Project detail page
From the Projects dashboard, click on a project name to open its detail page.

Here you can:
Project information
- View the project ID
- Access the code snippet to embed the chatbot widget
- Access the project details using the Settings button
Testing and monitoring
- Test your chatbot widget using the New chat button
- Recrawl sources to update indexed content
- View crawl logs to troubleshoot indexing issues
- Access detailed project analytics
Chat management
- View all chat entries and conversation history
- Filter conversations by sentiment
- Click on any chat entry to view its details
Project actions
- Delete the project
Chat detail view
From the project detail page, click on any chat entry in the conversation list to view its full details.

This view shows detailed information about that specific conversation:
User information
- Email address (if provided)
- Country and IP address
- Sentiment analysis of the conversation
Conversation metadata
- URL where the chat originated
- Date and time of the conversation
- Full conversation history
Actions
- Download: Export the chat in PDF, Excel, or CSV format
- Delete: Remove the chat entry
Bulk actions
Select multiple chat entries using the checkboxes and access the Select action dropdown to perform bulk operations:
- Archive chat entries: Archive conversation history to keep your project organized while preserving data.
- Export chat entries: Download conversation data in bulk for analysis or record-keeping. Available formats include CSV, PDF, and Excel.
- Delete chat entries: Permanently remove selected conversations from your project.
Project settings
From the project detail page, click the Settings button (top right) to open the project settings. The settings layout has a left sidebar with seven groups; each group has its own page with one or more sections.

Only Administrator or Maintainer roles can manage project settings. See Manage roles.
The header on every settings page has two top-right actions:
- Refresh sources: Re-crawl all configured sources. After clicking, you're sent to the project's chat-list page where the loading status is visible.
- Delete project: Permanently delete the project and all its data.
Each section card has its own Save button — saving one card never validates the others.
General
Basic project information:
- Name: Display name for the project.
- Demo page: Enable or disable the public demo page used for testing.
Sources
Configure the data sources your chatbot can answer from. Pick a source type from the chip selector at the top of the page; each chip reveals its own form.
- URLs: Index specific web pages.
- Sitemaps: Index entire websites using XML sitemaps. The Sitemaps tab also exposes URL-filter regex patterns to control which sitemap URLs get crawled.
- GitHub: Index GitHub repositories directly.
- OpenAPI: Import API specifications.
- Confluence: Connect a Confluence workspace.
- Files: Upload documents (PDF, CSV, Excel, Word, TXT, MD). Available once the project has been created.
For detailed configuration, see Sources.
Chatbot
Two sections, each with its own Save button:
- Conversation UI — initial greeting message and suggested-question prompts shown when the chat opens. See Initial message and Suggested questions.
- LLM Settings — model selection, prompt configuration (default AI Assistant or custom prompt), think mode, and web search. See Models, Custom prompt, and Reasoning modes.
Search
Two sections:
- Search Filters — filter chips that narrow search results by URL pattern. See Search filters.
- Boost Rules — rank specific URLs higher in search results. Available with the boost permission.
MCP
Configure Model Context Protocol integration so AI coding assistants can talk to this project.
- Enable MCP server: Allow access through MCP.
- MCP server name: Custom name (defaults to the project name).
- Metadata tag: Tag used to identify conversations originating from MCP.
Available from the Professional plan. See MCP server.
Security & Privacy
Two sections:
- Data Privacy — toggle PII redaction and IP-address collection. See Data privacy.
- Access Control — require authentication for API access (Business plan), and restrict which domains the chatbot widget runs on.
Integrations
Connect channel integrations. Each card links out to the platform's OAuth flow — there's no Save button on this page.
- Discord — see Discord.
- Slack — see Slack.
- Microsoft Teams — see Microsoft Teams.