Azure Bot Service Makes Microsoft Bots Ready for Primetime

Last year Microsoft announced the availability of its Bot Framework to enable the implementation of bots that an run on different messaging runtimes. The framework became instantly popular and today it counts with tens of thousands of developers and hundreds of bots running on diverse messaging stacks.

Considering the popularity of Microsoft Bot Framework, many were surprised when, a few months ago, Microsoft announced the Azure Bot Service, a platform to enable an end-to-end experience for the implementation and management of bot solutions.

Do we really need another Microsoft offering for bots?

The question is perfectly logical but irrelevant as soon as we realize that Azure Bot Service is a natural complement to Microsoft Bot Framework. Conceptually, Azure Bot Service expand Microsoft Bot Framework with capabilities in areas such as backend services, continuous integration, artificial intelligence(AI) services, scalability and many other foundational elements of the lifecycle of bots. In some context, Azure Bot Services makes Microsoft Bot Framework bots ready to operate and scale in real world, mission critical environments. Even though the different capabilities of the Azure Bot Service can be independently used together with the Microsoft Bot Framework, it takes a considerable level of effort to do so. Azure Bot Service brings together several Microsoft products to provide a complete and sophisticated experience for the implementation of bot applications.

Using the Azure Bot Service, developers can implement bots using Microsoft Bot Framework directly from an in-browser experience powered by the azure Editor. Developers can leverage components such as Azure Functions to enable serverless backend routines or Microsoft Cognitive Services to provide AI features to bot applications. Additionally, Azure Bot Service enables continuous delivery by integrating with service such as GitHub, BitBucket or Visual Studio Team Systems. The Bot Service also provider a library of templates that streamlines the implementation of common bot scenarios.

Factoring all those capabilities, it is very easy to see how Azure Bot Service complements Microsoft Bot Framework. Using some industry analogies, we can compare the connection between the two bot platforms with other well-understood technology relationships such as Confluent-Kafka in the messaging space, Cloudera-Hadoop in big data or Loopback-NodeJS in the server-side JavaScript application market.

Azure Bot Service is a very unique offering in the bot platform space that Microsoft ahead of competitors such as Howdy, Facebook Messenger or Slack that provide relevant platforms in the space. Knowing that, we can speculate about what could be next for the Azure Bot Service.

Five Cool Ideas for the Azure Bot Service Roadmap

Here are some interesting ideas that I would like to see added the the Azure Bot Service in the near future:

1 — Serverless Connectors: Leveraging technologies such as Azure Functions and LogicApps to implement serverless connectors to SaaS systems.

2 — Relational and NOSQL Storage: Provide libraries that abstract the storage of relational and semi-structured data in bot solutions.

3 — Analytics: More advanced bot performance monitoring analytics integrated into Azure Application Insights.

4 — Bot Search and Discovery: Smart mechanisms for searching and discovering bots based on a specific criteria.

5 — Knowledge Services: Integration with Cognitive Services that bring domain specific knowledge from public repositories such as WebMD, Wikipedia, etc.

Written by

CEO of IntoTheBlock, Chief Scientist at Invector Labs, Guest lecturer at Columbia University, Angel Investor, Author, Speaker.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store