You are on fire! We hope you had success in finishing the basic version of your bot. As mentioned the completed version you get at the end of our instructions you get won’t get you a great grade( see the 2023:Assessment rubric for more information). Thus we encourage you to read through this section to get an idea of how you can extend your project and improve your grade.
An extension can be anything and we encourage you to get creative! Feel free to add anything you think would enhance the user’s experience. The harder it is to implement or the more creative/innovative the more points you will get. Feel free to do something a bit bigger and even if it is not perfectly functioning by the testing time we will still award you some points if you justify the extensions and explain what is not working and how you could possibly fix it.
There are a lot of options you can consider for extending your agent. We list some examples but you should feel free to explore other options we do not mention below. The list has been ordered by first presenting the relatively more easy extensions to the more elaborate extensions. although this also depends on the effort that you put into it:
Add a Filter: Make a new filter by adding a rule and entity in order to sort recipes in a new way.
Add a Functionality or Capability: The basic agent is quite limited in what it can do, so you could add something like:
Small talk capabilities: small talk can make the agent more engaging to the user, and would require you to think of small talk patterns, either initiated by the user or by the agent, that can be naturally integrated at some point in the recipe selection conversation. You would need a new intent, and/or pattern, and/or response.
Reading the recipe steps to the user: once the user confirms a recipe, the bot could read the recipe steps. You could add a pattern, response, and a new page for this.
Check if the user has all the ingredients: before confirming the recipe you could ask the user if they have the ingredients the recipe requires, so they can check before starting. This would require a new page, pattern, and response.
Allow the user to ask to restart or quit: would need a pattern, intent, entity, etc.
Allow the user to ask for a random recommendation: “Recommend me something”. This would require a pattern, intent or entity, response, and rule.
Add a rating system for the bot to get feedback.
last topic check: ask the user after a succesful recipe selection if they want to find another recipe and if so, restarting the recipe selection conversation.
Extend Visuals: In the visuals section we already talk about extending it. There we mostly refer to aesthetic changes that should be added. Now, we are specifically referring to extending visuals functionality, i.e. adding something that makes the visuals more supportive. An example would be to show the filtering history at any point.
Agent personality, style, and characteristics: You can work on designing and shaping the responses from your agent to suggest a particular personality, to provide it with a specific conversational style, or with social characteristics that may increase the user experience. See e.g. this paper for more ideas.
We can highly recommend more than one extension unless the extension is a large and time-consuming one. We will rate extensions on perceived added contribution to the agent. So multiple useful smaller things that contribute about the same as one bigger thing will merit about the same grade.
Add Comment