---
title: Build planner-driven agent workflows with Microsoft Semantic Kernel
slug: build-planner-driven-agent-workflows-with-microsoft-semantic-kernel
description: Compose prompts, plugins, memory, planners, and connectors into repeatable Python, .NET, or Java agent workflows with Microsoft Semantic Kernel.
github_stars: 27861
verification: security_reviewed
source: https://github.com/microsoft/semantic-kernel
category: Developer Tools
framework: Multi-Framework
tool_ecosystem:
  github_repo: microsoft/semantic-kernel
  github_stars: 27861
---
# Build planner-driven agent workflows with Microsoft Semantic Kernel

Compose prompts, plugins, memory, planners, and connectors into repeatable Python, .NET, or Java agent workflows with Microsoft Semantic Kernel.

Use Microsoft Semantic Kernel when an agent or operator needs to turn a one-off assistant idea into a repeatable orchestration workflow: define native functions or plugins, connect model providers, add memory/vector-store integrations, and coordinate single-agent or multi-agent plans across business systems. Invoke this skill when the desired output is a maintainable workflow scaffold or orchestration pattern. The scope boundary is implementation planning for agent orchestration using Semantic Kernel primitives—tools/plugins, planners, memory, connectors, and multi-runtime setup.

## Prerequisites

- Microsoft Semantic Kernel
- Python 3.10+, .NET 10.0+, or Java 17+ (depending on runtime)
- LLM provider credentials as required by the chosen connector

## Installation

```bash
# Python
pip install semantic-kernel

# .NET
dotnet add package Microsoft.SemanticKernel
```

## Source

- [Microsoft Semantic Kernel on GitHub](https://github.com/microsoft/semantic-kernel)
- [Agent Skill Exchange](https://agentskillexchange.com/skills/build-planner-driven-agent-workflows-with-microsoft-semantic-kernel/)