The Evolution of Power Virtual Agents to Copilot Studio
With this year’s Microsoft Ignite event we received many exciting announcements — one of which was Power Virtual Agents getting rebranded to Copilot Studio!
The Evolution of Power Virtual Agents
Before we delve into what has changed, it’s important to explain exactly what Power Virtual Agents is. Power Virtual Agents (PVA) is a cloud-based software service offered by Microsoft, as part of the broader Power Platform.
It allows users, even those without programming knowledge, to create and deploy sophisticated AI-powered virtual agents, commonly known as chatbots. These chatbots can interact in a natural, conversational manner, and are typically used for automating various customer service and internal workflow tasks.
It is also important to touch on the history of PVA and what has led to this rebranding in the first place; when the general availability of PVA was announced in December 2019, nearly 4 years ago, the boom in generative AI was not something that was anticipated by many.
The progression of concepts within the AI space like LLMs (Large Language Models), text generation, recognition and translation quickly changed what could be achieved with chatbots.
Over the past two years especially, the evolution in generative AI has allowed chatbots to output natural, conversational and engaging responses as opposed to the pre-defined templates they were initially made with.
This introduction of combining AI with chatbots has allowed them to learn from data and user feedback which improves their performance over time.
Transforming Chatbot Interactions
For those of you who have played around with PVA (or even used it for enterprise use) you will be familiar with the building blocks of how to create a chatbot. These include:
- Trigger phrases to teach the bot different ways that someone might ask for a topic
- Topics to determine the general category of the conversation and narrow down the scope of conversation
- Actions to execute to the user’s request, such as providing information, completing a task or directing the user to further resources
With this in mind, the signs from PVA shifting from pre-defined answers to a chatbot which can converse using context-aware and personalised answers were indeed visible.
The Dawn of Copilot Studio
So what does all of this mean for the, now, Copilot Studio? Well, licensed users will be able to:
- Quickly build, test, publish and analyse your own copilot experience by connecting to your websites, documents and business data within a single interface
- Leverage plugins by importing or creating new ones from existing platform components including data sources, connectors, flows, AI prompts and custom topics
- Quickly generate topics (conversation paths) by using natural language prompts and receive a custom topic within a matter of seconds
For end users who are on the receiving end of a Copilot Studio chatbot, this means chatbots will be able to provide customers with more accurate and contextually relevant answers with time. As a result, customers will be able to have more engaging, satisfactory and personalised conversations to aid with their pain points.
As we say goodbye to Power Virtual Agents and welcome Copilot Studio, it’s clear that this shift marks a leap in the field of conversational AI. Moving from static responses to context-aware and flexible chatbots represents the growth of AI. It is not just a rebranding, it is a commitment to its capabilities moving forward.
Originally published at https://www.changingsocial.com on November 30, 2023.