A user asking questions of a chat bot

My Experiences with Copilot Studio – Gen AI Agents Not Behaving as Expected? Check Your Question’s Settings


Introduction

At iThink 365, we are seeing an increase in the number of project where we are delivering Copilot Agents that are built on Microsoft 365 and Copilot Studio for our customers.

Each time we do one, we learn more and pick up tips and tricks on the way.

In this post, I wanted to share some learnings I have had as we try and do agents which are more agentic and use the orchestration features. I wanted to go through a scenario which I am sure you will have had, and some tips and tricks to help you get some control around.

Copilot Studio is going through a period of rapid change and development. New features are being rolled out each week, and it is constantly changing. Sometimes this leads us to think that something is buggy when in fact it is misunderstanding with how the platform can be configured.

In this blog post, I wanted to share an example of this.

The example is when you use the Question activity to get a response from the user.

One of the behaviours we saw was that the user would choose an option or type a response. On processing of the response, the agent would rather than continue in the same topic, it would switch and execute another topic (https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/topics-overview). What the heck, why was it doing that?

Well, it turns out that the Copilot Studio’s Question activity has a plethora of settings. These settings allow you to control the processing logic, so let’s delve into those settings.

The first set of options is the “Question behaviour”, which controls how the question is processed.

For example:

  • Can a user skip this question?
  • Does the agent enforce the question, and if so, how many times does it try?

The third option is how the question treats interruptions.

The interruption was the secret to the problem we were seeing, more on that shortly. This set of options allows you to control whether a user can switch to a different topic and, if it can switch, which topic(s) the Agent can switch to.

The reasoning is sound, if you are a user, it may be pretty frustrating to have to go down a particular route and set of questions before you can get the answer you are looking for.

However, as a developer, there will be times when you want to ensure that the user cannot deviate from the process.

So, coming back to our problem, we were seeing that the user’s response was being seen by the Agent as a match for one of the other topics. The user experience was terrible because now they were taken off down a path that was not the expected path, and certainly did not end up with the result and experience that we wanted them to have.

The solution was to uncheck “Allow switching to another topic”, and the issue stopped happening.

Now, what if you did want them to be able to switch to another topic, but you wanted to restrict which topics they can switch to. Well, in order to do that, you can check “Allow switching to another topic” and then select the topics they can switch to.

You may think, how do we ensure that the user experience is what we want it to be. This is only validated via testing with real users. Often we have seen users use language or terms which we were not aware of and then topics are not triggered as expected.

So make sure you test this piece with real users via user acceptance testing before you launch. By doing this, you can ensure the configuration of the question and topics is right. Then the user gets the experience of picking up / switching to the topics with the right content.

Conclusion

I hope you uncover this post in your time of need, and it helps you uncover the plethora of options that the Question activity has.

Please let us know if you have any question or if it helped you using the comments below and thanks for reading.

Part 4: App-Powered Microsoft Planner Tasks – Features I would like to see in App-Powered Tasks


Introduction

This blog post is part of a series discussing Microsoft Planner’s App-Powered Task feature.

In this blog post, I wanted to share some ideas, features and thoughts about where I would like to see Microsoft App-Powered Planner Tasks go.

Agent-powered Planner Tasks

Currently, we are discussing app-powered tasks which are assigned to users, as in humans. However, imagine if we could assign tasks to an AI Agent such as a Copilot Agent. These “Agent-Powered” Tasks would be really powerful. If we could assign work via a task to a Copilot Agent. The Agent could then do what is being asked, feedback the results via the task comments, and reassign the task. This truly would help us integrate Agents into our everyday work and really bring them into the flow of work and the business process flow.

I’ll coin the phrase, “Agent-Powered Tasks”; you heard it here first! ☺️

App-Powered Tasks Make It to General Availability

I am sure that Microsoft will release App-Powered Tasks into general availability (GA). I really hope that they do, as it is a big gap in the Microsoft 365 platform. Once they do then I think people will really start to make use of Planner-powered tasks because suddenly, there is enough control.

It’s a chicken and egg situation; if technology stays in preview and is not ready for production use, then it is difficult to see that organisations will use it. Fingers crossed.

Part of Microsoft 365 Base License

Additionally, I hope and expect that this feature will be a base Microsoft 365 license feature rather than a Planner Premium feature. The fact that there is all the plumbing to do and the use of Teams Apps to me means that there won’t be the additional processing and, therefore, the additional expense for Microsoft to run this feature. Compare this to a feature such as a Copilot, which has the underlying cost of running the LLM workloads.

If Microsoft don’t include this in the license, then they will really impact Microsoft Planner adoption. Additionally, as Microsoft Planner forms the base for task management and if organisations want to adopt some of the premium features, then app-powered tasks increase the likelihood of that happening.

Fingers crossed that Microsoft agree with me 🙂

Power Platform Integration

There needs to be an easy way to work with the APIs through Power Platform Connectors.

If these are available, then we could drive the task workflow via Power Apps, manage the process and task completion via Power Apps

Task Outcome Field

The other thing and maybe I am missing something, is that I think tasks need an Outcome field where you can put the final results of a task. We used to have this with SharePoint workflows back in the day.

Currently it’s difficult for a human or an AI agent to know what the outcome of the task has been in this custom logic world.

Conclusion

In this post, we discussed some ideas and thoughts that I would love to see in these Planner App-Powered Tasks.

I really do hope that licensing doesn’t become a barrier to this feature; anyway, we will see what happens as this amazing feature evolves.

Thanks for reading!