/
Setting up context for AI Space

Setting up context for AI Space

This documentation is for Kyvos 2026.8.x. To view documentation for other Kyvos versions, click here.

This documentation is for Kyvos 2026.8.x. To view documentation for other Kyvos versions, click here.

Note

This section applies to Kyvos Dialogs Quick Analysis and Deep Dive Analysis.

Overview

Space Instructions provide contextual information and guidance that help the AI generate more accurate queries and responses for an AI Space. These instructions are applied to all queries executed within the AI Space and improve the quality and relevance of the generated responses.

Setting up Space Instructions

To specify space instructions, perform the following steps.

  1. Navigate to AI Space.

  2. Select the required AI Space.

  3. From the left navigation pane, under Context, click Space Instructions.

  4. Configure the required instructions:

    • Business Context: Provide business-specific information that helps the AI understand the purpose, domain, and scope of the AI Space.

      The business context enables the AI to:

      • Understand the business domain.

      • Identify relevant semantic models.

      • Interpret business terminology correctly.

      • Generate responses that align with your business context.

      • Sample:

        This AI Space contains retail sales data for customers, orders, products, and regions. Use this information to analyze sales performance, customer behavior, inventory trends, and product profitability.

    • Querying Instructions: Provide instructions that guide how the AI interprets and processes user queries.

      Querying instructions can be used to:

      • Specify preferred business terminology.

      • Define calculation or filtering preferences.

      • Restrict or prioritize specific semantic models.

      • Guide query generation for consistent results.

      • Sample

        Always use completed orders for sales analysis. Prefer fiscal year calculations over calendar year. Return the top 10 results unless the user specifies otherwise.

    • Summary Instructions: Provide instructions for formatting and presenting the generated response.

      Summary instructions help the AI:

      • Organize the response consistently.

      • Highlight important business insights.

      • Present results in the preferred format.

      • Sample

        Provide a concise executive summary followed by key insights and recommendations. Highlight significant trends, anomalies, and business observations.

  5. Click The Instruction Tips panel provides guidance and sample content for creating effective instructions. It includes:

    • Best practices for writing business context.

    • Sample business purpose statements.

    • Guidance for writing querying instructions.

    • Example instructions that can be customized for your AI Space.

    Use these examples as a starting point and tailor them to your organization's business requirements.

  6. Click Save to apply the changes.

On this page:

Verified Queries

You can add Natural Language Queries (NLQ) in Kyvos to allow users to ask questions about their data in plain business language and automatically generate relevant queries or insights. This feature enables users to define commonly used business questions in natural language and map them to corresponding SQL queries, store them at different access levels, and leverage them both as suggested prompts in chat sessions and as reference examples for RAG-based SQL generation. These verified questions help improve SQL generation accuracy by providing contextual guidance during conversational analytics experience with Kyvos Dialogs.

Set the context for Natural Language Queries (NLQ) on the Managed Verified Queries dialog box. This improves query interpretation and generate more accurate insights based on the user’s business terminology and data context. You can add a new query, export query, and import query.
To add a new query, perform the following steps.

  1. Navigate to Verified Queries under the Context section.

    image-20260629-094612.png

  2. Click Add Queries. The Manage Verified Queries dialog is displayed.

    image-20260417-123443.png

     

    1. In the Queries panel, click the + icon to add a new query, or select an existing query from the list.

    2. In the Natural Language Query text box, enter the business question in plain language (for example, “What is sum sales for 2025?”).

    3. In the SQL Query editor, enter the corresponding SQL statement using Spark SQL syntax.

    4. (Optional) Click Execute Query to validate and test the SQL query.

    5. In the Additional Context field, provide additional context to clarify the intent or usage of the query.

    6. In the Applicable For field, select the relevant users for whom this query should be available.

    7. Enable Show as suggested questions in Dialogs if you want this query to appear as a suggested question in Kyvos Dialogs.

    8. Repeat the above steps to add more natural language queries as required.

    9. Click Apply to save the configuration. The query has been added. You can now edit or delete the query as needed.

      image-20260629-094942.png

       

      1. Edit: You can edit natural language queries by clicking the pencil edit icon. The Manage Verified Queries dialog is displayed. Make the necessary changes and click Apply.

      2. Delete: You can delete natural language queries by clicking the delete icon. The query will be deleted.

      3. Revert: You can also click back to previous changes without saving changes.

Importing sample queries

You can import sample queries in CSV format and use them to query the semantic model.

To import sample queries, perform the following steps.

  1. From the Toolbox, click Semantic Models.

  2. Select a semantic model from the list. 

  3. Click the Settings tab and then select the Verified Queries tab under the Context section.

  4. Click Import Queries. The Import Verified Queries dialog is displayed.

  5. Select the Choose file option to upload the file. The file will be uploaded.

  6. Specify the settings as: line separator, field separator, and enclosed as needed.

  7. Click Import. The CSV file will be imported.

    image-20260629-102855.png

Exporting sample queries

This section details how to export sample queries in CSV format.

To export sample queries, perform the following steps.

  1. From the Toolbox, click AI Space.

  2. Select an AI Space from the list. 

  3. Click the AI Settings tab and then select the Verified Queries tab under the Context section.

  4. Click Export Queries at the bottom of the page. The Export Verified Queries dialog is displayed.

  5. Specify the settings as: line separator, field separator, and enclosed as needed.

  6. Click Download. The CSV file will be downloaded.

    image-20260629-101419.png

Copyright Kyvos, Inc. 2026. All rights reserved.