Microsoft Dataverse: Build your low code hyperscale backend on Dataverse - Build your agentic flows with Dataverse SDK for Python

Microsoft Dataverse: Build your low code hyperscale backend on Dataverse - Build your agentic flows with Dataverse SDK for Python is a Microsoft 365 roadmap item published via Microsoft Release Communications. Current status: Launched.

The Microsoft Dataverse SDK for Python empowers data scientists and developers to build intelligent, compliant, and scalable agentic flows that integrate seamlessly with Dataverse. In the agentic age, where autonomous agents orchestrate workflows and act on behalf of users, the SDK provides the essential tools to interact programmatically with enterprise data platforms. The SDK supports structured data access, composable APIs, and governance features that are critical for building trustworthy and efficient agents. Key capabilities can include: Autonomous data agents that can query, update, and evaluate data quality Form prediction and autofill Support for agentic primitives like Model Context Protocol (MCP) and Agent-to-Agent (A2A) collaboration The SDK for Python offers a streamlined developer experience with support for common Create, Retrieve, Update, and Delete (CRUD) operations, bulk data processing, metadata access, and observability tools. SDK Python packages are to be published on PyPI.org with open-source support. The SDK is strategically positioned to enable agent-native development with semantic modeling, secure impersonation, and compliance built-in. Business Value: Enables data scientists and developers to create, access, and manage Dataverse business data using Python programming. The Dataverse SDK for Python implements common Python programming paradigms and best practices, provides a more natural Python interface to Dataverse, and supports community contributions. Enabled for: Enabled for admins/makers/marketers automatically

Wave 0 first: Security → GRC → Cost & Value → Licence → Adoption. Put this on the agent register with a named owner. Do not enable broadly until permissions, DLP, and reclaim rules exist.

12 Panes: 03 Horizon · 05 GRC · 08 Adoption · 04 Security · 09 Work & Skills

• Security: Assess exposure, Conditional Access, and agent/tool permissions.
• GRC: Update AI/agent register and evidence path; confirm DPIA triggers if personal data is in scope.
• FinOps: Forecast seat or credit impact; align to frozen value case.
• Adoption: Plan cohort messaging, clinics, and success measures.
• Comms: One story for board and staff — what changes, what does not, who owns risk.

• May improve productivity on a specific Microsoft 365 surface when permissions and data quality allow.
• Roadmap visibility helps Horizon planning without guessing dates.
• Agents can automate multi-step work inside existing Microsoft 365 permissions.

• Status and dates change; treat MRC as directional, not a contract.
• Enabling without Steady controls can amplify overshare or cost leakage.
• Agents act; over-privilege and ownerless agents create lasting exposure.

• MRC id: 576876
• Status: Launched
• Products: Microsoft Dataverse
• GA / disclosure: June CY2026
• Preview: November CY2025
• Platforms: Web
• Cloud instances: Worldwide (Standard Multi-Tenant)
• moreInfoUrls: https://learn.microsoft.com/en-us/power-apps/developer/data-platform/sdk-python/
• Open on Microsoft 365 Roadmap

Microsoft Release Communications / Microsoft 365 Roadmap (AI at Work). Content is subject to Microsoft API Terms of Use. Dates and status change; verify in the official roadmap before acting.