microsoft/promptflow

Health v2 · maintenance only

Adoption not part of the score

11229 stars · 1118 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Prompt flow is a suite of Python SDK, CLI, and VS Code extension tools for the end-to-end development of LLM-based AI applications, linking LLMs, prompts, and Python code into executable flows. It supports prototyping, debugging with tracing, evaluation, CI/CD integration, deployment, and monitoring. Note: feature development ended April 2026 and the project retires April 2027 in favor of Microsoft Agent Framework.

Use cases

• build and iterate LLM app workflows linking prompts and python code
• trace and debug interactions with LLMs
• evaluate flow quality and performance on datasets
• integrate LLM flow testing into CI/CD pipelines
• deploy prompt flows to a serving platform
• prototype chat-with-pdf style RAG applications

When to choose

• you need structured orchestration and evaluation for LLM app development
• you want tracing and CI/CD quality gates for prompt-based flows
• you are already invested in the Azure AI ecosystem with existing flows

When to avoid

• starting a new project - the project is retiring and Microsoft recommends migrating to Microsoft Agent Framework
• you need long-term supported tooling beyond April 2027
• you want a lightweight prompt library without workflow orchestration

Facets

framework · maturity maintenance

prompt-engineering llm-inference agent-framework testing workflow-automation tracing ci-cd large-language-models artificial-intelligence developer-tools machine-learning python cross-platform cli editor-plugin cloud llm-app-development prompt-flow evaluation vscode-extension azure-ai orchestration retiring ai-agents

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/promptflow")