Optimizing latency with the Bot Framework

Responsiveness in a conversational bot is critical for a good user experience, as users want responses to be fast. With maximizing user satisfaction as a goal in mind, there are some basic operations which every bot must still do, such as getting an authorization token, and getting/setting conversation state. In this post we’d like to go over some ways to….

Debug any Channel locally using ngrok

One of the key features available when you use the Bot Framework is the ability to seamlessly connect your bot to multiple channels, all from the same bot. Click here  to learn more about currently supported channels, and how to connect to them. While your bot is in development, you can debug and test your bot locally using the debugger for….

Customize Web Chat for your websites

Every bot that is registered with the Bot Framework is automatically configured for the Web Chat channel. This channel includes the Web Chat control which can be embedded directly onto websites for users to interact with, for example – the assistant bot from the Microsoft Education homepage : Most bot developers using the Bot Framework are well aware of this,….

QnA maker revisited, with Suggested Actions and App Insights

In this post we’ll go over a few different strategies to manage user feedback for your bots. Instead of starting from the beginning with a new bot project, we’ll be continuing off of the demo QnA bot we created in a previous post – QnA Maker with rich cards in .NET. The demo we started from that post is not….

Bot Framework at Microsoft Ignite 2017

This year at Ignite 2017, Microsoft is hosting many different sessions from the Bot Framework, with a range of topics geared towards beginner – advanced bot developers. In these sessions we’ll share with you what we’ve learned about bot design and practices, how our customers have been using the Bot Framework to meet their business needs, and the different ways….

Natural Language Understanding Services – a comparison

At this years’ SIGdial conference, researchers from the Technical University of Munich, department of informatics published the following paper – Evaluating Natural Language Understanding Services for Conversational Question Answering Systems Currently, there is no established way to evaluate different NLU (Natural Language Understanding) services. One of the primary goals of the research team was to define a way to compare these….

Azure Bot Service now supports Azure Web Apps

Today we’re happy to announce the addition of Azure Web Apps to the Azure Bot Service, one of the most requested features of the past few months. You can find the Azure Web Apps option in the new “Hosting Plan” drop down, when you create a new bot using the Azure Bot Service in the Azure Portal. In particular: “App Service….

HTML is not supported in Web Chat

Client side HTML rendering is not rendered for official Web Chat channels. Web Chat is intended to support markdown, and while markdown itself can support in-line HTML, this was not an intended feature for the Web Chat in the Bot Framework. Markdown in-line HTML Why isn’t HTML  supported? The primary reason behind this decision was to ensure a consistency of….

New Channel Inspector Features

Earlier this year in February, we first announced the Bot Framework Channel Inspector. Since then, we’ve been upgrading this preview tool to support new feature releases as the Bot Framework evolves. The Channel Inspector now includes support for four additional channels: Bing Cortana Skype for Business WeChat In addition, for all channels you can now preview two new features: Adaptive Cards Suggested Actions….

QnA Maker with rich cards in .NET

If you are unfamiliar with the QnA Maker, please click here to learn more about it. A good bot is one that is actually useful to users, seems intuitive right?  Some bots may need to process payments, handle forms, track location, or perform some other sort of complex or custom operation. We also have LUIS, which can be utilized to….