{"data":[{"active":true,"blog_title":null,"blog_url":null,"feature_description":"The Data Agent is now better at selecting the right data source when answering your questions--especially in setups with multiple sources. It more effectively evaluates schema, example queries, and source descriptions to determine the best place to route each request. This leads to more accurate results and fewer misrouted queries across both SQL, Semantic Model, and KQL sources.","feature_name":"Improved Data Agent Routing Across Sources","last_modified":"2026-07-15","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q2 2026","release_item_id":"4493d060-d848-f111-bec7-6045bd0a8ec1","release_status":"Shipped","release_type":"General availability"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"Creator Agent is expanding support for Semantic Models in Data Agent, helping users generate semantic-model specific instructions and example queries more easily. The feature can explore Semantic Model tables, measures, columns, and recent query patterns to produce more relevant configurations while preserving transparency through visible run steps and explored queries. Users remain in control by reviewing, refining, and committing generated configurations before they update their Data Agent setup.","feature_name":"CreatorAgent: Support Semantic Models","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"df9398eb-fb68-f111-a826-6045bd0066ad","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"You can now organize large instructions into topics, allowing the Data Agent to automatically select only the most relevant context for each question. This helps the NL2SQL tool focus on what matters, even when working with extensive guidance or complex scenarios. By enabling more targeted use of instructions, this improvement supports better query generation and gives you a scalable way to provide richer context without overwhelming the model.","feature_name":"Large Instructions & Topic-Aware Context for Smarter NL2SQL","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"dc64604a-d948-f111-bec7-6045bd0a8ec1","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"Production Datawarehouses, Lakehouses, Semantic Models, and SQL DBs contain hundreds to tens of thousands of Tables, Views, Functions, and Measures. This feature highlights the requirements to support production scale database systems and semantic models across data agent scenarios within the Data Agent UX seamlessly:  - Enabling the UX to allow users to load large schemas into Data Agent and select Objects easily and efficiently.- Enabling the UX to search for elements allowing users to easily identify key entities required for data agent input - Enabling pagination in the UX to seamlessly browse the schema in the Object explorer.","feature_name":"Explore Large Schemas in the Data Agent Schema Explorer","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"a6aadfd9-4924-f011-8c4d-00224804b6c3","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":"What\u2019s New for Fabric Data Agents at Ignite 2025: Unlocking Deeper Data Reasoning and Seamless AI Interoperability","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/whats-new-for-fabric-data-agents-at-ignite-2025-unlocking-deeper-data-reasoning-and-seamless-ai-interoperability","feature_description":"Microsoft Fabric Data Agent is improving its Ontology experience so customers can build agents that deliver more accurate, reliable, and verifiable answers grounded in their business concepts and relationships. With this release, customers should see better support for complex questions, clearer visibility into answer generation, stronger customization and scoping, and improved confidence as ontologies evolve over time.","feature_name":"Data Agent to Upgrade Ontology Integration","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"8640c298-fc68-f111-a826-6045bd0066ad","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":"Fabric Data Agent now supports CI/CD, ALM Flow, and Git Integration","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/fabric-data-agent-now-supports-ci-cd-alm-flow-and-git-integration","feature_description":"The Data Agent charting library now uses Fabric visuals, improving quality and ensuring greater consistency across Fabric for a more unified and predictable user experience.","feature_name":"Enhanced Data Agent Visualizations with Fabric Visuals","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"71a7bef8-b766-f111-a826-6045bd0066ad","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"The Data Agent now uses an upgraded semantic model query pipeline that more accurately translates natural-language questions into structured queries. This update introduces instance value indexing and delivers higher response accuracy and consistency.","feature_name":"Improved Semantic Model Querying in the Data Agent","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"681eef41-b566-f111-a826-6045bd0066ad","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"The primary goal is to enable creators to understand how consumers interact with their data agents and bridge the gap between the data agent creators and the consumers. This comprehensive monitoring system will enable creators to have access to the feedback provided by consumer across consumption channels such as M365 Copilot, Fabric, Org App so they can refine the data agent based on customer feedback.Our initial release will only cover the M365 Copilot and will then expand to other consumption channels.","feature_name":"Consumer to Creator feedback loop","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"5db8bce1-2b43-f111-88b5-6045bd00fc61","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"Creator Agent file support lets users upload existing text-based business context such as documentation, glossaries, process guides, and data dictionaries, so Creator Agent can use it to generate more complete and accurate Data Agent configurations. This reduces repetitive setup work by allowing users to reuse knowledge that already exists in files, rather than manually recreating that context through long chat interactions.","feature_name":"Creator Agent Supports Files as Context","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"54678565-fb68-f111-a826-6045bd0066ad","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"Data Agent automatically follows the foreign key relationships in your SQL source to query the right tables -- including ones you didn't explicitly select. When you scope an agent to a schema or just a couple of base tables, the agent expands along those foreign keys to bring in the other tables a question needs and generates SQL that joins them correctly, so you get accurate multi-table answers from a small starting selection. For relationships that aren't defined in the source or live only in how your business uses the data, creators and advanced users can define additional relationships through the SDK & Data Agent experience. These configurations are stored alongside the rest of the agent configuration in a consistent, source-controllable format -- so they flow through your CI/CD pipeline","feature_name":"Relationship Context for SQL Sources","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2026","release_item_id":"34631b0a-c065-f111-a826-6045bd00fc61","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"Fabric Data Agent's visualization support turns natural-language questions into clear and interactive visuals, such as line charts, bar charts, area charts, and more. By choosing visualizations that fit the data and intent, the agent helps users quickly spot trends and validate insights, making analytics faster, clearer, and more accessible.","feature_name":"Data Agent Visualization Support","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q2 2026","release_item_id":"f00fb079-0b06-f111-8406-000d3a36696c","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"Recent NL2SQL improvements make the system more reliable and flexible by better leveraging few-shot examples, asking clarifying questions when queries are ambiguous, and using data exploration to handle gaps or novel scenarios. It also improves accuracy through smarter filter mapping and provides clearer debugging via visible run steps, example usage, and structured diagnostics.","feature_name":"Improved NL2SQL Experiences","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q2 2026","release_item_id":"7d8ccddd-a1f0-f011-8406-6045bd026004","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":"Creator Improvements in the Data Agent","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/creator-improvements-in-the-data-agent","feature_description":"The Creator Agent is a specialized AI assistant designed to help data agent creators configure, improve, and optimize their data agents by generating and refining Agent Instructions, Data Source Instructions, and Few-Shot Examples. It addresses common customer pain points such as confusion about where to put instructions, uncertainty about the effectiveness of few shots, and difficulty diagnosing why an agent produces poor results. The agent works in a collaborative, chat-based 'setup' mode, where it analyzes existing configurations, explores database schemas and query patterns, and recommends improvements that users can explicitly accept or reject. It is designed to detect ambiguity and contradictions across configurations and suggest clearer, more consistent alternatives. Initially focused on SQL data sources, the Creator Agent is intended to expand to additional data sources (e.g., KQL, semantic models) over time. Overall, it enables a faster, more scalable, and more understandable way to build high-quality data agents without requiring deep knowledge of the underlying system.","feature_name":"Assisted Setup Mode in Data Agent","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q2 2026","release_item_id":"db90d1e4-cbf0-f011-8407-002248096d54","release_status":"Planned","release_type":"Public preview"},{"active":true,"blog_title":"Extending Outbound Access Protection to Fabric Warehouse and SQL Analytics Endpoint","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/extending-outbound-access-protection-to-fabric-warehouse-and-sql-analytics-endpoint","feature_description":"Outbound access protection is one of the top security asks from the Fabric Enterprise customers. Today WS OAP support only limited set of items which limits the adoption of Fabric for Customers. Our aim is to support Fabric Data Agent in OAP so that customers can prevent sensitive data from getting exfiltrated.","feature_name":"Outbound Access Protection for Data Agent","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q2 2026","release_item_id":"ce75a77c-88ba-f011-bbd3-000d3a5b0efa","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Expanded Data Agent Support for Large Data Sources","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/expanded-data-agent-support-for-large-data-sources","feature_description":"Fabric Data Agent's support for KQL UDFs enables richer, more optimized reasoning over Eventhouse and KQL-backed data sources, improving both accuracy and performance of generated KQL queries. By leveraging governed, reusable functions, the agent can translate natural-language questions into more efficient queries while honoring Fabric's security and schema semantics. This expands the breadth of scenarios the agent can handle, making KQL-based analytics faster and more consistent.","feature_name":"[PuPr] Data Agent to Support Kusto UDF","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2026","release_item_id":"ea64bc96-e805-f111-8406-6045bd0a886d","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"Fabric Data Agent's support for External Tables allows data agent users to include data that lives outside Eventhouse while keeping a single, governed agent configuration and schema context.This enables simpler setup and reuse of existing KQL data definitions, reducing duplication and manual query logic within data agent..","feature_name":"[PuPr] Data Agent to Support Kusto External Tables","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2026","release_item_id":"3a1e1a9b-1b12-f111-8406-6045bd0a8ec1","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Graph in Fabric (Generally Available)","blog_url":"https://community.fabric.microsoft.com/t5/Fabric-Updates-Blog/Graph-in-Fabric-Generally-Available/ba-p/5190748","feature_description":"The Fabric Graph is introduced as a new structured data source in the Fabric Data Agent, enabling the agent to reason over entities and relationships using a native graph model rather than flat tables. By leveraging Graph schemas and NL2GQL, the Data Agent can answer complex questions that require relationship traversal, multi-hop reasoning, and entity-centric insights more naturally and accurately. Fabric Graph integrates seamlessly alongside existing Fabric sources (such as Lakehouse and Eventhouse), allowing the agent orchestrator to select graphs when relational context is critical. This unlocks more intuitive analytical experiences, including plain-English answers with the ability to pivot into visual or interactive graph exploration. Overall, Fabric Graph expands the Data Agent's reasoning depth and makes relationship-driven insights first-class in conversational analytics.","feature_name":"[PuPr] DataAgent - Graph As a DataSource","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2026","release_item_id":"397e4a71-ccf0-f011-8407-002248096d54","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":null,"blog_url":null,"feature_description":"With the increasing integration of artificial intelligence in business tools, Copilots have introduced new challenges in data protection, governance and compliance. This situation demands a refined approach to how AI interacts with and manages organizational data. Purview for AI intends to address these challenges by providing a set of capabilities that enable organizations to monitor, audit, and prevent data loss and risk while their users interact with LLMs from their managed devices.Microsoft Purview enables Copilot and Data Agent to leverage data security, governance, and compliance features in their apps. It provides a smooth integration path to embed data protection capabilities into their workflows, ensuring robust enterprise security, such as:*  Audit: Send prompt and response telemetry along with all associated user and system context to Purview for auditing purposes.*  eDiscovery: Send prompt and response contents, including all associated user and system context, to Purview to support electronic discovery processes.*  Data Lifecycle Management (DLM): Send prompt and response contents with all associated user and system context to Purview to manage the data lifecycle effectively.*  Communications Compliance (CC): Send prompt and response contents, along with all associated user and system context, to Purview to detect and address unethical or improper uses of AI.*  Classification: Send prompt and response contents with all associated user and system context to Purview for classification and store the classification results in compliant storage.","feature_name":"Data Agent Audit logs with Purview","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2026","release_item_id":"2e298f0f-3801-f111-8406-000d3a36696c","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Fabric workloads are now generally available!","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/fabric-workloads-are-now-generally-available","feature_description":"**General Availability of Fabric Data Agents**We're preparing to bring the core Fabric Data Agent capabilities to general availability in March. This release will introduce broad support for key data sources, including Lakehouse, Warehouse, Semantic Models, Eventhouse, SQL Databases, and Mirrored Databases. Users will also be able to configure data agent using agent-level instructions, data source-specific instructions, and example queries to tailor behavior to your scenarios. Publishing and sharing within Microsoft Fabric will also be generally available, making it easier to operationalize and collaborate on data agents.In addition, this release includes diagnostic downloads, Git integration, and deployment pipelines as part of Microsoft Fabric's Application Lifecycle Management (ALM) capabilities, enabling robust governance and lifecycle management.","feature_name":"General Availability of Fabric Data Agents","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2026","release_item_id":"0b5b5933-5ac0-f011-bbd3-6045bd05dd14","release_status":"Shipped","release_type":"General availability"},{"active":true,"blog_title":"Data Agent Now Supports Eventhouse Functions, Materialized Views, and Shortcuts (Preview)","blog_url":"https://community.fabric.microsoft.com/t5/Fabric-Updates-Blog/Data-Agent-Now-Supports-Eventhouse-Functions-Materialized-Views/ba-p/5181801","feature_description":"SQL Views and Functions support in Data Agent enables the system to work with richer, production-grade SQL entities by incorporating views and reusable logic directly into query generation. This dramatically improves data accessibility, reduces complexity, and boosts NL2SQL accuracy by allowing Data Agent to rely on curated schemas, simplified naming, and pre-defined joins rather than raw underlying tables. The result is more reliable, performant, and business-friendly analytics experiences for creators and downstream users","feature_name":"Data Agent: Support for SQL Views + Functions","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2026","release_item_id":"504f8364-4a24-f011-8c4d-00224804b6c3","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Connecting AI Agents to Microsoft Fabric with GraphQL and the Model Context Protocol (MCP)","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/connecting-ai-agents-to-microsoft-fabric-with-graphql-and-the-model-context-protocol-mcp","feature_description":"As an MCP server, data agent can expose its tools as standardized tools to any AI assistant including VSCode, GitHub Copilot, etc. This allows other AI tools to tap into enterprise data on demand, accelerating AI adoption and ensuring consistent, secure, and auditable access to data agent tools.Data agent MCP server is considered as the main consumption endpoint.","feature_name":"Data Agent as an MCP Server","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q4 2025","release_item_id":"216667c8-3e68-f011-bec3-000d3a329ecb","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Creator Improvements in the Data Agent","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/creator-improvements-in-the-data-agent","feature_description":"The new multi-tasking experience in the Data Agent is designed to make it easier for creators to switch between different configurations and chat with their data more fluidly. With this update, users can navigate across multiple configuration setups--such as different data sources, instructions, or example queries--without losing context or progress in their conversations.This experience directly addresses key user feedback around the friction of managing and testing configurations, especially when iterating on prompt quality. By streamlining how configurations are accessed and switched, creators can move faster, compare results across variations, and troubleshoot more effectively--all within a unified interface.","feature_name":"Multi-Tasking Configuration Experience for Data Agent Creators","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q4 2025","release_item_id":"878ac7c1-a461-f011-bec1-000d3a35e553","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Unlocking LLM-Powered through Data Agent from your Mirrored Databases in Microsoft Fabric","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/unlocking-llm-powered-through-data-agent-from-your-mirrored-databases-in-microsoft-fabric","feature_description":"Supporting Mirrored SQL DBs in Data Agent will bridge the gap between technical and non-technical users, allowing them to collaborate more efficiently and make informed decisions based on accurate and timely data. This integration will also ensure that businesses can maximize the value of their existing SQL DB investments while benefiting from the advanced capabilities of Microsoft Fabric's Data Agent.","feature_name":"Data Agent to Support Mirrored Databases","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2025","release_item_id":"fdb2922d-4b24-f011-8c4d-00224804b6c3","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Fabric Data Agent now supports CI/CD, ALM Flow, and Git Integration","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/fabric-data-agent-now-supports-ci-cd-alm-flow-and-git-integration","feature_description":"Enable CI/CD for Fabric data agents.A well implemented CI/CD pipeline brings significant benefits: Automated tests integrated into the CI process validate every change to the Data agent's configuration before deployment, catching errors early and ensuring that only reliable updates reach production. A structured deployment process moves changes from a development workspace, through a test workspace that mirrors production, and finally into production, while automatically applying workspace specific configurations. This rapid, reliable iteration not only reduces operational errors but also allows improvements and fixes to be pushed quickly in response to user feedback and evolving business needs, ultimately leading to a better enduser experience.","feature_name":"CI/CD for Fabric Data Agent","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q3 2025","release_item_id":"4ec0e5ee-2a22-f011-9989-6045bd030c4d","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Accelerate Data Transformation with AI Functions in Data Wrangler (Preview)","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/accelerate-data-transformation-with-ai-functions-in-data-wrangler","feature_description":"A new suite of AI-powered operations in Data Wrangler will allow users to describe code transformations with natural language and generate the corresponding Python; translate custom Python code into PySpark code; and view high-confidence suggestions for operations based on their working data.","feature_name":"Low-Code AI-Powered Operations in Data Wrangler [Public Preview]","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q2 2025","release_item_id":"6a229e5c-1a03-ef11-a1fd-000d3a33ff0b","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Empowering agentic AI by integrating Fabric with Azure AI Foundry","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/empowering-agentic-ai-by-integrating-fabric-with-azure-ai-foundry","feature_description":"With the Fabric data agent integration in Azure AI Foundry, Fabric data agent will serve as a knowledge source for Agent Service in Microsoft Azure AI Foundry. This enables the agent to use Fabric as a data hub, tapping into the insights available within Fabric to answer user queries accurately and efficiently. By connecting to Fabric data agent, the agent can retrieve data insights directly from Fabric, allowing consumers to interact with and analyze their Fabric data seamlessly through the AI applications in Azure AI Foundry.","feature_name":"Fabric data agent integration with Azure AI Foundry","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2025","release_item_id":"b1c46b53-f390-ef11-ac21-6045bd062aa2","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"Semantic link in Microsoft Fabric: Bridging BI and Data Science","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/semantic-link-use-fabric-notebooks-and-power-bi-datasets-for-machine-learning-data-validation-and-more","feature_description":"This feature allows users to query their Power BI Semantic Models in Fabric using natural language, receiving both a concise answer and the corresponding DAX query. Users can ask questions like 'What were the total sales over the last 12 months?' and get not only the result but also the underlying DAX query for transparency and reuse. In future, user should also be able to provide few-shot examples--sample questions- to guide the AI Skill that semantic model is the best tool to answer those questions. This approach makes data insights more accessible to all users while providing advanced users with greater control and transparency over the analysis.","feature_name":"Semantic Models as new data source for AI Skill","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2025","release_item_id":"b53e0bb7-4c95-ef11-8a6a-002248098a98","release_status":"Shipped","release_type":"Public preview"},{"active":true,"blog_title":"New improvements coming to the AI Skill","blog_url":"https://blog.fabric.microsoft.com/en-us/blog/new-improvements-coming-to-the-ai-skill","feature_description":"The AI Skill is now conversational, enabling users to engage in natural, back-and-forth dialogue to explore and understand their data with ease. This enhancement allows users to ask follow-up questions, refine queries, and receive dynamic insights, making data exploration more intuitive and interactive.","feature_name":"AI Skill becomes a conversational AI agent","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2025","release_item_id":"a6cf3d58-6aa0-ef11-8a6a-6045bd062aa2","release_status":"Shipped","release_type":"General availability"},{"active":true,"blog_title":"Introducing Copilot for Real-Time Dashboards: Write KQL with natural language","blog_url":"https://blog.fabric.microsoft.com/en-US/blog/introducing-copilot-for-real-time-dashboards-write-kql-with-natural-language","feature_description":"This feature allows users to query their Kusto databases in Fabric using natural language, receiving both a concise answer and the corresponding KQL (Kusto Query Language) query. Users can ask questions like 'What was the total number of logins last week?' and get not only the result but also the underlying KQL query for transparency and reuse. To enhance accuracy, users can provide few-shot examples--sample questions with expected answers. The system supports iterative queries, enabling users to refine their questions or update notes for more precise outputs, making data analysis more accessible while empowering advanced users with greater control.","feature_name":"KQL database as new data source in AI Skill","last_modified":"2026-06-24","product_id":"951b64e0-a663-f111-a826-6045bd00f798","product_name":"Conversational Analytics","release_date":"Q1 2025","release_item_id":"7c9a04b4-0997-ef11-8a6a-6045bd062aa2","release_status":"Shipped","release_type":"General availability"}],"links":{"first":"/api/releases?product_name=Conversational+Analytics&page_size=50&page=1","last":"/api/releases?product_name=Conversational+Analytics&page_size=50&page=1","next":null,"prev":null,"self":"/api/releases?product_name=Conversational+Analytics&page_size=50&page=1"},"pagination":{"has_next":false,"has_prev":false,"next_page":null,"page":1,"page_size":50,"prev_page":null,"total_items":29,"total_pages":1}}