Skip to main contentSkip to Ask Learn chat experience

Learn
Sign in
Azure
Version
Search
Filter by title
Bot Framework SDK documentation
What is the Bot Framework SDK?
Choose the right chatbot solution
What's new
Learn Azure AI Services AI Bot Service
What is the Bot Framework SDK?
Article
10/09/2024
4 contributors
In this article
What is a bot?
How to build a bot
Next steps
APPLIES TO: SDK v4

Microsoft Bot Framework and Azure AI Bot Service are a collection of libraries,
tools, and services that let you build, test, deploy, and manage intelligent bots.
The Bot Framework includes a modular and extensible SDK for building bots and
connecting to AI services. With this framework, developers can create bots that use
speech, understand natural language, answer questions, and more.

Tip

For a list of Microsoft products and services for building bots, who they support,
and a brief description of each, see Choose the right chatbot solution for your use
case.

What is a bot?
Bots provide an experience that feels less like using a computer and more like
dealing with a person—or intelligent robot. You can use bots to shift simple,
repetitive tasks—such as taking a dinner reservation or gathering profile
information—onto automated systems that may no longer require direct human
intervention. Users converse with a bot using text, interactive cards, and speech.
A bot interaction can be a quick answer to a question or an involved conversation
that intelligently provides access to services.

One way to think of a bot is as a web application that has a conversational

interface. Your users connect to your bot through a channel, such as Facebook,
Slack, Microsoft Teams, or a custom application.

Depending on how the bot is configured and how it's registered with the channel,
interactions can be in text or speech and can include images and video.
The bot processes the user's input to interpret what the user has asked for or
said.
The bot evaluates input and performs relevant tasks, such as ask the user for
additional information or access services on behalf of the user.
The bot responds to the user to let them know what the bot is doing or has done.
A remote bot interacts with a user on a device via text, speech, images, or video.

Bots are often implemented as a web application, hosted in Azure and using APIs to
send and receive messages. What's in a bot varies widely depending on what kind of
bot it is and what its purpose is. A bot can receive messages and echo them back to
the user, with little code involved. A more complex bot can rely on various tools
and services to deliver richer experiences on a wide variety of platforms.

Bots can do the same things other types of software can do—read from and write to
files, use databases and APIs, and do the regular computational tasks. What makes
bots unique is their use of mechanisms used in human-to-human communication.

Azure AI Bot Service and the Bot Framework include:

Bot Framework SDKs for developing bots in C#, JavaScript, Python, or Java. (The
Java SDK is retired with final long-term support ending in November 2023.)
CLI tools for help with end-to-end bot development.
Bot Connector Service, which relays messages and events between bots and channels.
Azure resources for bot management and configuration.
Additionally, bots may use other Azure services, such as:

Azure AI services to build intelligent applications

Azure Storage for cloud storage solution
How to build a bot
Azure AI Bot Service and Microsoft Bot Framework offer an integrated set of tools
and services to help you design and build bots, through all stages of the bot life
cycle. SDKs exist for C#, Java, JavaScript, TypeScript, and Python. Choose your
favorite development environment or command line tools to create your bot.

Illustration of the steps in the bot life cycle.

Plan
As with any type of software, having a thorough understanding of the goals,
processes and user needs is important to the process of creating a successful bot.
You can create a simple bot or include more sophisticated capabilities such as
speech, natural language understanding, and question answering.

Before writing code, review the bot design guidelines for best practices and to
identify the needs for your bot.

Build
Typically, a bot is a web service hosted in Azure. In Azure, you can configure your
bot to send and receive messages and events from various channels. You can create
bots in any number of environments and languages. You can create a bot for local
development.

With Azure AI Bot Service and the Bot Framework, you can use other libraries and
services to extend your bot's functionality. This table describes some of the
features supported by the SDK.

Feature Description More information

Memory and storage Persist user and conversation state Managing state
Natural language understanding Interpret and extract information from user
input Language understanding
Rich cards Combine text and other media, such as images, audio, video, and buttons
How to add media and cards
Command line tools to help you to create, manage, and test bot assets. For more
information, see Azure CLI and Bot Framework Tools.

For complete code samples, see the Bot Framework Samples repo. The samples
demonstrate many capabilities of the SDK.

Test
Bots are complex apps with many different parts working together. Like any other
complex app, this can lead to some interesting bugs or cause your bot to behave
differently than expected. Before publishing, test your bot. We provide several
ways to test bots before they're released for use:

Test your bot locally with the Bot Framework Emulator. The Bot Framework Emulator
is a stand-alone app that not only provides a chat interface but also debugging and
interrogation tools to help understand how and why your bot does what it does. The
Emulator can be run locally alongside your in-development bot application.

Test your bot on the web. Once configured through the Azure portal your bot can
also be reached through a web chat interface. The web chat interface is a great way
to grant access to your bot to testers and other people who don't have direct
access to the bot's running code.

Unit Test your bot with the current Bot Framework SDK.

Publish
When you're ready for your bot to be available on the web, deploy your bot to Azure
or deploy to your own web service or data center. Having an address on the public
internet is the first step to your bot coming to life on your site, or inside chat
channels.

Connect
Connect your bot to channels, such as Facebook, Messenger, Slack, Microsoft Teams,
Telegram, and SMS via Twilio. Bot Framework does most of the work necessary to send
and receive messages from all of these different platforms—your bot application
receives a unified, normalized stream of messages regardless of the number and type
of channels it's connected to. For information on adding channels, see channels
topic.

Evaluate
Use the data collected in Azure portal to identify opportunities to improve the
capabilities and performance of your bot. You can get service-level and
instrumentation data like traffic, latency, and integrations. Analytics also
provides conversation-level reporting on user, message, and channel data. For more
information, see how to gather analytics.

Next steps
Read customer stories
Create a Bot Framework bot
Additional resources
Training

Module

Introduction to Azure Bot Service and Bot Framework Composer - Training

Introduction to Azure Bot Service and Bot Framework Composer

Certification

Microsoft Certified: Azure AI Fundamentals - Certifications

Demonstrate fundamental AI concepts related to the development of software and

services of Microsoft Azure to create AI solutions.

Documentation

Create a basic bot - Bot Service

Create your first bot with the Bot Framework SDK, in C#, Java, JavaScript, or
Python.

Choose the right chatbot solution for your use case - Bot Service

Learn about different chatbot solutions, who they're for, and when to use them.

Basics of the Microsoft Bot Framework - Bot Service

Become familiar with the Microsoft Bot Framework. Understand how bots communicate
with users, and learn about activities, channels, HTTP POST requests, and more.

Show 3 more
Previous Versions
Blog
Contribute
Privacy
Terms of Use
Trademarks
© Microsoft 2025