Agile Advisor Plugin for Microsoft Teams

Agile Advisor Plugin for Microsoft Teams

Estimated reading time: 3 minutes

Advisory Role in Microsoft Team Communications

Agile Advisor Plugin for #Microsoft Teams is able to observe team interactions, such as conference calls within Microsoft Teams. The Advisor can derive “dialog intents” and provide recommendations for improvement. A retrospective on communications, such as Scrum ceremonies

Voice Recognition During Teams Meetings

Technology that leverages voice recognition, such as Interactive voice response (IVR) solutions are fraught with failed recognition. IVRs are used to answer calls in just about every company, which prompts for either a phrase from the user on what they want and the ability to enter a numeric value correlating to the desired intent. Challenge #1.

Dialog and Intent Identification

Beyond trying to identify the user’s intent from a phrase or sentence, a dialog, a series of interactions between two or more team members is even more complex. Current AI models that identify intent from a sentence or phrase have a mixed variable of accuracy, which is why these models must be tuned over time. A collective of interactions, a dialog between two or more team members, has a much higher level of complexity to identify intents. Challenge #2. Once a dialog intent(s) has an “N”% level of accuracy, rules may be fired with any number of outcomes, such as unintrusive logging of Agile suggestions for best practices, and next steps: e.g. a retrospective of the scrum ceremony.

Dynamically Identify Roles in Teams Meetings

Who participates in Microsoft Teams meetings and team chats can be associated with Microsoft Teams’ member profiles, such as Scrum Master, and Product Owners.

Enhance the Adherence to Agile Principles

12 Principles Behind the Agile Manifesto, and opportunities for rules to be trigger based on conversations, the interactive dialogs.

  1. Our highest priority is to satisfy the customer through early and continuous delivery of valuable software.
  2. Welcome changing requirements, even late in development. Agile processes harness change for the customer’s competitive advantage.
  3. Deliver working software frequently, from a couple of weeks to a couple of months, with a preference to the shorter timescale.
  4. Business people and developers must work together daily throughout the project.
  5. Build projects around motivated individuals. Give them the environment and support they need, and trust them to get the job done.
  6. The most efficient and effective method of conveying information to and within a development team is face-to-face conversation.
  7. Working software is the primary measure of progress.
  8. Agile processes promote sustainable development. The sponsors, developers, and users should be able to maintain a constant pace indefinitely.
  9. Continuous attention to technical excellence and good design enhances agility.
  10. Simplicity–the art of maximizing the amount of work not done–is essential.
  11. The best architectures, requirements, and designs emerge from self-organizing teams.
  12. At regular intervals, the team reflects on how to become more effective, then tunes and adjusts its behavior accordingly.

Dialog Intent Rules for Agile Guidance

From the above agile principles, we can derive the following dialog intents and precise recommendations for improvement.

Barriers to Implementation

At the current level of Artificial Intelligence (AI) Digital Assistants, i.e. chatbots, even the “best in breed”, has “difficulty”, i.e. lower probability with intent recognition, with a single sentence or phrase. Multiply that by interpreting an interactive dialog with multiple sentences, multiple participants, and exchange of responses, feasibility is highly speculative.

And Still More Opportunity: Recognition of Facial Emotional Expressions 

Expressions of people may be able to be determined, and opportunities for suggestive posture can be advised. Even body posture folded arms as an example, can imply a guarded opinion, and not open to compromise.

Reference article – Emotion recognition using facial expressions

Caution and Opportunities

This plugin output could be used for annual employee evaluations.

Leave a Reply

Your email address will not be published. Required fields are marked *