Potions Matcher agent

We are using Copilot Studio to make an agent that can answer user questions about what potions they can make with the ingredients that they have collected in they beaded bag inventory.

We look to claim these badges with this blog post

Hogwarts Enchantment

Hogwarts Enchantment

Because we are truly making magic happen when the user can both get answers to what potions they can make and the AI agent can automatically add new potions to their inventory.

Plug N’ Play!! I mean, we are pluggi’n everything in everything in our solution, and this copilot agent will be plugged into every interface the young wizard turns to

We are leveraging the latest of the latest in AI cutting-edge technologies with autonomic Copilot Agent. Doesn’t get more hip than that!

We are claiming Feature Bombing because we are adding the copilot to all interfaces; Teams, Power Pages and Canvas app. The users are bombarded with this copilot feature wherever they turn. Sounds familiar? 😀

Using an autonomous agent to search both the internet (Harry Potter Wiki) and Dataverse tables and combining the results is using search in an interactive and innovative way

And last, but not least, in the vast world of potions and ingredients, this agent is not only smarter than a 5th grader – but even Hermione Granger herself!

Creating the Agent

The magical wizard who knows more about potions and spells and ingredients than Hermione Granger herself is actually a Copilot Agent.

Adding a public knowledge source

We created it with the Harry Potter Wiki as a knowledge source: https://harrypotter.fandom.com/wiki/List_of_potions

Connecting the agent to Dataverse as a knowledge source

In the setup we choose the tables that we want to make available as sources for the agent to draw data from.

Allow the Potions Matcher to create potions

The agent will be able to create new potions in your inventory in the beaded bag based on the ingredients you have. To allow for this the agent is granted permissions to create new rows in the Potion Inventory table on the users behalf

Create custom prompts

We all know how hard it can be to understand what exactly an AI chat service can do, so we wanted to add predefined custom prompts to our agent chat experience, to give the users a better user experience.

We created a set of custom prompts that we added to the bot.

Testing the bot in the studio is one thing, but secretly, Dumbledore also adds it to to Teams

Testing the agent with a chat experience in Teams

Adding it to the Power Pages site and using it, logged in as Dumbledore to create new items in inventory

and this is a video of what the copilot agent looks like in a Canvas App on the phone

Leave a Reply