Page Comparison

An extension can be anything and we First of all, we want to emphasize that you can implement any extension that you can think of that makes sense (argue for that in your report). We thus want to encourage you to get be creative! Feel free, for example, to add anything that you think would will enhance the user’s user experience. The harder it is to implement or the more creative/innovative , innovative, or sophisticated your design idea is and the better your implementation of it is, the more points you will get for them. Feel free to do something a bit bigger and even if it is not perfectly functioning by the testing time we will go beyond what we have suggested for this reason. Even if your design idea has not been perfectly implemented and testing still reveals issues with it, we may still award you some points if you explain everything well in your report: you should justify the extensions and, in case it is not working optimally, explain what is not working and how you could possibly fix it.

There are a lot of options you can consider for suggestions we provide below that you may consider extending your agent. We list Again, we provide some examples below, but you should feel free to explore other options we do not mention below. The list has been ordered by first presenting from the relatively more easy extensions to the more elaborate extensions. although Of course, this also depends on the effort that you put into it!

Here is the list of suggestions that you can use for inspiration:

• Add a Filter: Make a new filter by adding a rule and entity in order to sort filter 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.

, for example:

• Check if the user has all the ingredients: before confirming the recipe you , your agent 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 Ask to restart or quit: you would need to add a pattern, intent, entity, etc.

• Allow the user to ask for Ask a random recommendation: a “Recommend me something” . This capability which would require a pattern, intent or entity, response, and rule.

• Add a rating system for the bot to get feedback.

• last Last topic check: ask the user after a succesful successful recipe selection recommendation if they want to find select another recipe and if so, restarting the recipe selection conversation, the agent should restart the recipe recommendation conversation.

• Repair: add more advanced handling of repair. For example, if a user does not know how to continue the conversation, the agent could suggest (alternative) ways of continuing it. It may also happen that a user initiates repair (“I don’t understand that”, “what do you mean by 'X’”?), in which case the agent should now how to response (e.g.: understand this user-initiated repair, and respond with a further explanation of a concept or utterance). Finally, rather than stating misunderstanding, the agent could provide more information on what aspect of the user utterance it did not understand, or provide pointers to what the user can say at that point in the conversation.

• Small talk capabilities related to the recipe domain: small talk can make the agent more engaging for a user. It 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 recommendation conversation. You would need one or more new intents, patterns, and responses.

• Extend Visuals: In In the visuals section, we already talk about ways for extending it. There we mostly refer to We mostly mentioned some aesthetic changes that should be addedyou can add. Now, we are specifically referring to extending functionality of the visuals functionality, i.e. adding something that makes the visuals more supportive. An example would be to show the filtering history at any point. Another example would be to add a rating system for the agent to get feedback. However, keep in mind that the interaction should primarily be conversational in nature!

• 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.