|
| 1 | +--- |
| 2 | +title: Agents |
| 3 | +description: Introduction to agents |
| 4 | +author: luisquintanilla |
| 5 | +ms.author: luquinta |
| 6 | +ms.date: 10/01/2025 |
| 7 | +ms.topic: concept-article |
| 8 | +--- |
| 9 | + |
| 10 | +# Agents |
| 11 | + |
| 12 | +This article introduces the core concepts behind agents, why they matter, and how they fit into workflows, setting you up to get started building agents in .NET. |
| 13 | + |
| 14 | +## What are agents? |
| 15 | + |
| 16 | +**Agents are systems that accomplish objectives.** |
| 17 | + |
| 18 | + |
| 19 | + |
| 20 | +Agents become more capable when equipped with the following: |
| 21 | + |
| 22 | +- **Reasoning and decision-making**: Powered by LLMs, search algorithms, or planning and decision-making systems. |
| 23 | +- **Tool usage**: Access to Model Context Protocol (MCP) servers, code execution, and external APIs. |
| 24 | +- **Context awareness**: Informed by chat history, threads, vector stores, enterprise data, or knowledge graphs. |
| 25 | + |
| 26 | +These capabilities allow agents to operate more autonomously, adaptively, and intelligently. |
| 27 | + |
| 28 | +## What are workflows? |
| 29 | + |
| 30 | +As objectives grow in complexity, they need to be broken down into manageable steps. That's where workflows come in. |
| 31 | + |
| 32 | +**Workflows define the sequence of steps required to achieve an objective.** |
| 33 | + |
| 34 | +Imagine you're launching a new feature on your business website. If it's a simple update, you might go from idea to production in a few hours. But for more complex initiatives, the process might include: |
| 35 | + |
| 36 | +- Requirement gathering |
| 37 | +- Design and architecture |
| 38 | +- Implementation |
| 39 | +- Testing |
| 40 | +- Deployment |
| 41 | + |
| 42 | +A few important observations: |
| 43 | + |
| 44 | +- Each step might contain subtasks. |
| 45 | +- Different specialists might own different phases. |
| 46 | +- Progress isn’t always linear. Bugs found during testing might send you back to implementation. |
| 47 | +- Success depends on planning, orchestration, and communication across stakeholders. |
| 48 | + |
| 49 | +### Agents + workflows = agentic workflows |
| 50 | + |
| 51 | +Workflows don't require agents, but agents can supercharge them. |
| 52 | + |
| 53 | +When agents are equipped with reasoning, tools, and context, they can optimize workflows. |
| 54 | + |
| 55 | +This is the foundation of multi-agent systems, where agents collaborate within workflows to achieve complex goals. |
| 56 | + |
| 57 | +### Workflow orchestration |
| 58 | + |
| 59 | +Agentic workflows can be orchestrated in a variety of ways. The following are a few of the most common: |
| 60 | + |
| 61 | +- [Sequential](#sequential) |
| 62 | +- [Concurrent](#concurrent) |
| 63 | +- [Handoff](#handoff) |
| 64 | +- [Group chat](#group-chat) |
| 65 | + |
| 66 | +#### Sequential |
| 67 | + |
| 68 | +Agents process tasks one after another, passing results forward. |
| 69 | + |
| 70 | + |
| 71 | + |
| 72 | +#### Concurrent |
| 73 | + |
| 74 | +Agents work in parallel, each handling different aspects of the task. |
| 75 | + |
| 76 | + |
| 77 | + |
| 78 | +#### Handoff |
| 79 | + |
| 80 | +Responsibility shifts from one agent to another based on conditions or outcomes. |
| 81 | + |
| 82 | + |
| 83 | + |
| 84 | +#### Group chat |
| 85 | + |
| 86 | +Agents collaborate in a shared conversation, exchanging insights in real-time. |
| 87 | + |
| 88 | + |
| 89 | + |
| 90 | +## How can I get started building agents in .NET? |
| 91 | + |
| 92 | +The building blocks in <xref:Microsoft.Extensions.AI> and <xref:Microsoft.Extensions.VectorData> supply the foundations for agents by providing modular components for AI models, tools, and data. |
| 93 | + |
| 94 | +These components serve as the foundation for Microsoft Agent Framework. |
| 95 | + |
| 96 | +For more information, see [Microsoft Agent Framework](/agent-framework/overview/agent-framework-overview). |
0 commit comments