Agentic Applications for Unified Data Foundation is an open-source GitHub Repository designed to empower organizations to make faster, smarter decisions at scale by leveraging agentic AI solutions built on a Unified Data Foundation with Microsoft Fabric. With seamless integration of Azure AI Foundry agents and Agent Framework orchestration, teams can design intelligent workflows that automate routine processes, streamline operations, and enable natural language querying across enterprise datasets. This ensures that governed, high-quality data is accessible not only to technical specialists but also to business users, creating a shared environment where insights are surfaced more easily and decisions are grounded in trusted information. By unifying data access and applying AI in the flow of work, organizations gain the agility to respond rapidly to changing business needs, foster collaboration across teams, and drive innovation with greater confidence.
Agentic Applications for Unified Data Foundation can perform a variety of functions related to analyzing data stored in Fabric. The sample solution focuses on a sales analyst looking to extract actionable insights from complex data sets. The sample data leverages publicly available Contoso data sets. Names are pulled from the CELA approved names list database.
This repository is to be used only as a solution accelerator following the open-source license terms listed in the GitHub repository. The example scenario’s intended purpose is to demonstrate how users can analyze underlying customer data sets (e.g. orders, customer) to help them work more efficiently and streamline their human made decision.
As an AI-powered solution accelerator, Agentic Applications for Unified Data Foundation was evaluated through human review of the LLM output that interacts with the underlying, generated fictional data.
It's worth noting that the system is designed to be customizable and can be tailored to fit specific business needs and use cases. As such, the metrics used to evaluate the system's performance may vary depending on the specific use case and business requirements.
This solution accelerator can only be used as a sample to accelerate the creation of agentic application that are connected to unified data in Fabric. Users of the accelerator should review the system prompts provided and update as per their organizational guidance. AI generated content in the solution may be inaccurate and should be manually reviewed by the user. Right now, the sample repository is available in English only.
Effective and responsible use of Agentic Applications for Unified Data Foundation depends on several operational factors and settings. The system is expected to perform reliably and safely within a range of data types and languages that it was designed and evaluated for. Users can customize certain settings, such as the language model (e.g. GPT3.5 vs GPT4) used by the system, meta prompt, and the types of data that are analyzed. However, it's important to note that these choices may impact the system's behavior in the real world. For example, choosing a language model that is not well-suited to the data being analyzed may result in lower accuracy and performance. Similarly, analyzing data that are outside of the system's intended scope may result in errors or inaccurate results. To ensure effective and responsible use of Agentic Applications for Unified Data Foundation, users should carefully consider their choices and use the system within its intended scope.