Prompt flow is being retired

2026-04-30 · Source: Microsoft Foundry Blog articles · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, short

Summary

Microsoft is retiring Prompt flow in Microsoft Foundry and Azure Machine Learning, with full cessation of support on April 20, 2027. During the deprecation period until this date, Prompt flow will receive security and critical bug fixes but no new feature development. This retirement impacts the web authoring experience, VS Code extensions, and base images for deployments. Microsoft recommends migrating to the Microsoft Agent Framework, which achieved General Availability (GA) on April 3, 2026, for both Python and .NET, offering a production-ready foundation for agent and workflow-based AI applications. Customers must identify current Prompt flow usage, plan migration targets, rebuild and validate applications, and update deployments before the retirement deadline.

Key takeaway

For AI Architects and VP of Engineering overseeing AI application development, you must audit your organization's Prompt flow usage immediately. Plan your migration to the Microsoft Agent Framework, prioritizing critical workloads, and begin rebuilding and validating solutions well before the April 20, 2027, retirement date to ensure continuity and leverage stable, supported APIs.

Key insights

Microsoft is retiring Prompt flow, urging migration to the production-ready Microsoft Agent Framework by April 20, 2027.

Principles

• Plan for application redesign, not just platform switch.
• Prioritize migration of business-critical scenarios first.

Method

Identify Prompt flow usage, plan migration to Microsoft Agent Framework, rebuild and validate applications, then update deployments and operations, ideally in phases.

In practice

• Review existing Prompt flow applications and workflows.
• Utilize the provided migration guide and code samples.
• Engage Azure support for technical assistance.

Topics

• Prompt Flow Retirement
• Microsoft Agent Framework
• Azure Machine Learning
• Microsoft Foundry
• AI Application Migration

Best for: CTO, VP of Engineering/Data, AI Architect, AI Engineer, Machine Learning Engineer, MLOps Engineer

Related on AIssential

• Prompt Engineering is Dead — Context Engineering Is the Only Skill That Pays in Late 2026 — Effective AI agent performance relies on structured, living context packs, not just advanced prompt engineering.
• OpenAI is retiring GPT-4o and three other legacy models tomorrow, likely for good — Low user engagement drives OpenAI's decision to retire legacy models from ChatGPT, despite past user attachment.
• Modernizing regulated industries with cloud and agentic AI — Agentic AI and cloud modernization are crucial for operational efficiency, resilience, and regulatory compliance across industries.
• Transitioning from Azure Language Features to Foundry Models — Azure AI Language features are deprecating, requiring migration to Foundry models using LLMs, RAG, or fine-tuning for equivalent functionality.
• The TechBeat: Your Coding Agent Will Get Ripped Out. Build Workflows That Survive It (6/3/2026) — Coding agents are transient; design resilient workflows to survive their inevitable replacement.
• 3 Actionable AI Recommendations for Businesses in 2026 — Winning with AI by 2026 requires redesigning workflows, treating AI as an OS, and restructuring human roles.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Microsoft Foundry Blog articles.