Building your Agent

The core of this project surrounds building a recipe recommendation agent as a team. There are different tasks that you will encounter:

We encourage you to work on these assignments as a team as much as possible. Throughout the project go here for instructions on

[TBU]Your Project Pipeline .

1. Getting Started with your MARBEL Agent

Summary Description

Begin by setting up your MARBEL agent integrated with a Dialogflow agent to manage user interactions. Dialogflow will handle ASR, intent detection, and entity extraction, while MARBEL manages dialogue patterns. This foundational setup prepares the agent for future customization and functionality enhancements.

Implementation Tasks Overview

1. Set Up Dialogflow Agent

   • Create a Dialogflow agent with default settings (English as the language).

   • Share it with team members by assigning the Developer role.

   • Import the provided zip file for basic setup.

2. Integrate Dialogflow with MARBEL

   • Download the JSON key file for Dialogflow and add it to the agent folder in your repository.

   • Retrieve the Dialogflow Project ID and update the flowkey and flowagent parameters in the .mas2g file.

3. Initialize MARBEL Agenda

   • Replace the empty agenda in the dialog_init.mod2g file with the start pattern (agenda([start])).

4. Create the Start Page

   • Design a basic start page in html.pl using Prolog and Bootstrap, including a title, introductory text, and a “Start” button.

5. Run and Debug the Agent

   • Test the integration by running the MARBEL agent and verifying state changes in Eclipse’s Debug perspective.

Instructions

Getting Started with your MARBEL Agent

2. Greet, and Self-Identify

Summary Description

Natural conversations are typically opened. Our agent should not just straight away embark on the task of recommending a recipe. It should first secure the attention of its user. Opening a conversation is a basic conversational competence. A common way of opening a conversation is by greeting each other. You should provide your agent with this basic conversational competence too. It should, moreover, be able to introduce itself to its user as in the following conversational pattern. A welcoming webpage should also be created.

A: Hello.

A: My name is ____*.

U: Hi!

• insert your agent’s name here

Implementation Tasks Overview

https://socialrobotics.atlassian.net/wiki/pages/createpage.action?spaceKey=PM2&title=2025%20Capability%201%3A%20Greet%2C%20and%20Self-Identify

Request a Random Recipe Recommendation

Summary Description

The second capability will enable the agent to recommend a recipe when a user does not care (to refine) what kind of recipe they are looking for (see the example conversational pattern below). A new pattern will be introduced to this purpose for selecting a recipe, and a new intent should be added to your Dialogflow agent to enable understanding user requests for recommending “just some recipe”. Quite some work will need to be done for introducing the first code needed for retrieving recipes from the recipe database. The first versions of two new pages will also need to be created. One page for making clear to the user that they should inform the agent about features of recipes that help refine the selection of recipes and clarify what the user is looking for. Another page for asking a user to (dis)confirm that the recipe that the agent has selected and recommends to the user is what the user is looking for.

A: What recipe would you like to cook?

U: Please, just recommend me something.

A: What about ___*?

• insert a recipe name here (from the agent’s database)

Implementation Tasks Overview

Instructions

Select Recipes by Name

Summary Description

Instead of leaving it up to the agent to suggest a recipe and choose one out of all remaining recipes, a user also can mention a specific recipe themselves and ask the agent to present that. This means that the Dialogflow agent should have knowledge of all of the recipes that are in the database too. We will make this available to that agent by adding a recipe entity (type). That will also enable the agent to recognize these recipes in user expressions.

A: What recipe would you like to cook?

U: I'd like to make ____ *.

A: ____* is a great choice!

• insert name of a recipe from the recipe database here, such as “artichoke and pine nut pasta”

Implementation Tasks Overview

Instructions

Filter Recipes by Ingredients, Cuisines and Meal Types

Implementing this capability will involve implementing some of the conversational and reasoning competences that a conversational recipe recommendation agent should have. It will enable users to request recipes which use specific ingredient (types) or ask for recipes from a specific cuisine. This one of the capabilities that requires quite a big amount of work. Some of the bigger challenges will be to make Dialogflow understand ingredients (at least those that are in our database; and cuisines, for that matter, but those are fewer), to implement the logic to filter the recipe database with the feature requests of a user, and to present those in a nice way to the user on a webpage.

Summary Description

A: What recipe would you like to cook?

U: I'd like to make a recipe with ____ *.

A: All the recipes left include ____ *. Do you want to add another preference?

• insert name of an ingredient (type) or cuisine here

Implementation Tasks Overview

Instructions

Unexpected Intents

Summary Description

A conversational agent should be able to handle dialog moves of users that do not necessarily fit into the currently active pattern. Such moves are “unexpected” in the sense that they do not fit into a conversational pattern, but should be expected as users will almost always slightly deviate from a rigidly framed pattern. Typical examples are expressions of appreciation and requests for information about how the agent can assist a user (a capability check). A second type of unexpected move is not due to user behavior but due to failures of speech recognition. Dialogflow will match with a so-called default fallback intent in cases where it is unable to recognize what a user says as and cannot classify it as one of the (other) intents of the agent. There is another case that we will look into too where what a user says does not seem to fit into the conversational context. Again, we can capture the “unexpected” in patterns, which will enable the conversational agent to handle them:

Appreciation example pattern:

U: Thanks

A: You're welcome.

Capability check example pattern:

U: What can you do?

A: I can ____.

Repair example pattern:

U: Have you read the Hobbit?

A: What do you mean?

Implementation Tasks Overview

Instructions

Filter Recipes by Ingredients and Cuisine

Implementing this capability will involve implementing some of the conversational and reasoning competences that a conversational recipe recommendation agent should have. It will enable users to request recipes which use specific ingredient (types) or ask for recipes from a specific cuisine. This one of the capabilities that requires quite a big amount of work. Some of the bigger challenges will be to make Dialogflow understand ingredients (at least those that are in our database; and cuisines, for that matter, but those are fewer), to implement the logic to filter the recipe database with the feature requests of a user, and to present those in a nice way to the user on a webpage.

Summary Description

A: What recipe would you like to cook?

U: I'd like to make a recipe with ____ *.

A: All the recipes left include ____ *. Do you want to add another preference?

• insert name of an ingredient (type) or cuisine here

Implementation Tasks Overview

Instructions

Filter Recipes by Dietary Restrictions

Summary Description

We continue to extend the capabilities of the agent to handle user requests. The focus will be to enable a user to ask for recipes that meet dietary restrictions. This will also involve extending the logic of reasoning about ingredients. The main challenge will be to come up with an efficient approach to define this logic.

A: What recipe would you like to cook?

U: I'd like to make a ____ * recipe.

A: Here is a list of recipes that fit your preferences.

• insert a recipe feature such as vegan, for example, here

Implementation Tasks Overview

Instructions

Filter Recipes by Excluding Features

Summary Description

The last extension to increase the capabilities of our agent will look into feature requests that exclude aspects of a recipe. There are many examples of this, but we will focus on user requests that ask for excluding an ingredient (type), for recipes that are not from a particular cuisine (e.g., not from Asia), or do not have a specific dietary restriction (e.g., are not vegan). You are, of course, invited to extend the agent with other similar capabilities to exclude aspects of a recipe.

A: What recipe would you like to cook?

U: I want a recipe without ____ *.

A: Here is a list of recipes that fit your preferences.

• insert an ingredient such as salt here

Implementation Tasks Overview

Instructions

Confirm the Chosen Recipe

Summary Description

When users have finished their search for a nice recipe to cook, their choice should be displayed (which we already implemented for https://socialrobotics.atlassian.net/wiki/pages/createpage.action?spaceKey=PM2&title=2025%20Capability%205%3A%20Filter%20Recipes%20by%20Ingredients%20and%20Cuisine) and they should be asked to check the details to confirm the recipe is indeed what they would like to cook. Of course, we need to take at least two scenarios into account: (1) a user confirms they are happy with the recipe, or (2) they indicate it is after all not quite what they were looking for. If all is fine and well, the agent should close the conversation by saying farewell. Otherwise, the conversation should move back to the recipe selection stage. The following conversational pattern needs to be implemented:

A: Can you confirm ___* is the recipe you would like to cook?

U: Yes. (Alternatively: No.)

A: Great. (Alternatively: That is Unfortunate. [Move back to the recipe selection stage])

• insert name of recipe here

Implementation Tasks Overview

Instructions

Removing Filters and Showing Recipes on Demand

Summary Description

The last capability on our list before we ask you to extend the capabilities of the conversational agent using your own insights and ideas is about allowing users to remove requests they made before and to allow them to indicate that they are done providing their preferences. You should implement the following patterns:

A pattern enabling users to remove a recipe feature request:

U: Could you please remove the cuisine and servings requests?

A: I removed the cuisine and services requests for you.

A pattern enabling the user to express they are done:

A: Can you elaborate on what you're aiming for in your recipe?

U: I don't want to add anything else.

A: OK. Here is a list of recipes that you can choose from. [Alternative: Sorry, there are still too many recipes left to show them all. Please add more preferences.]

Implementation Tasks Overview

Instructions

Extend Your Agent (Make it Nicer)

Summary Description

Extend your agent even further; look at the

page or talk to your TA for inspiration!

Implementation Tasks Overview