General
Controls which AI features are available in the account, plus Agentic BI question and synonym settings.
AI Features
- AI Agents Access - Enable or disable AI Agents for the account.
- AI Q&A Across Datasets - Enable natural language Q&A over your datasets.
- Index by Default - Automatically index new datasets for AI search. Indexed datasets are managed under the Dataset Indexing tab.
- Bot Integration (Slack / Teams) - Enable AI Q&A via Slack or Microsoft Teams bot integrations.
- Show Visualization First - When enabled, AI search results display a chart before the data table.
Agentic BI
- Saved Questions / Favorites - Click the pencil icon to manage a list of saved questions surfaced as suggestions in the AI search interface.
- Field Synonyms - Account-wide field synonyms are managed as aliases on business terms in the Semantic Layer glossary. Click Manage in Semantic to open the glossary (Data > Semantic > Glossary).
Keys & MCP
Controls API keys for external AI providers and MCP token generation.
Global Keys
Account-wide keys, available to AI features for all users in the account.
- Knowi In-House AI - Knowi's built-in AI model. Shown as Included and enabled by default.
- OpenAI - Add or update your OpenAI API key to make OpenAI models available across AI features. Once a key is saved, it is displayed in masked form with Change and Remove options.
- Anthropic (Claude) - Add your Anthropic API key to make Claude models available.
- Google (Gemini) - Add your Google API key to make Gemini models available.
- Azure OpenAI - Add your Azure AI API key and endpoint URL to make Azure OpenAI models available.
User Keys
Keys that belong to an individual user. The same providers are available: OpenAI, Anthropic (Claude), Google (Gemini), and Azure OpenAI. Click Add Key to add your own key for a provider. If a global key is already configured for that provider, the row shows Global Key Configured.
MCP Access
- Claude / MCP Token - Click Generate to create a token for use with Claude Desktop or other MCP-compatible clients.
Models
Controls which AI model is used for each AI-powered feature. By default, features use Knowi In-House AI (App Generation defaults to a Knowi-selected frontier model). Click Change next to any feature to select a different model. Available options depend on which API keys have been configured under the Keys & MCP tab.
- Agentic BI - Model used for Agentic BI chat.
- AI Agents - Model used for AI agent workflows.
- Semantic AI - Model used to suggest asset descriptions, glossary definitions, and business term definitions in the Semantic Layer. Suggestions always stay in the form for review and are never saved or published automatically. If no model is set here, Semantic AI uses the AI Agents model.
- Data Lineage - Model used for AI-generated data lineage explanations.
- AI Q&A - Model used for natural language search queries.
- Documents AI - Model used for document analysis features.
- InstantSights AI - Model used for automated chart and insight generation.
- AI Dashboard Generation - Model used for AI-generated dashboard creation.
- Recommendation Widget - Model used for AI recommendation widgets. Supports multiple models simultaneously (e.g., Knowi In-House AI, GPT-4.1, GPT-4o, GPT-5, GPT-5 Chat).
- App Generation - Model used when generating Knowi Apps with AI. Defaults to a Knowi-selected frontier model.
- Apps - Model used for AI features inside Knowi Apps.
Dataset Indexing
Lists all datasets in the account with two toggles per dataset:
- Indexed - Include the dataset in AI/Agentic BI so users can query it through AI chat. Only indexed datasets can be set as default. See Indexing for what indexing controls and when to leave a dataset out.
- Agentic BI Default - Pre-select the dataset for all users when they open the Agentic BI chat. Defaults apply customer-wide, but users only see defaults they have access to. Disabling indexing on a dataset automatically clears its default flag. See Default Datasets for guidance.
For the full setup workflow - including field naming, descriptions, direct vs. non-direct datasets, and runtime token design - see Setting Up Datasets for Agentic BI.
The list sorts indexed datasets first, then alphabetically by name. Use the search box to filter by dataset name. Click the pencil icon next to a dataset to open its dataset management page. Use Enable All or Disable All to bulk-update indexing across all datasets.
After making changes, a Save Changes button will appear at the bottom of the section. Changes are not applied until you click Save Changes.