The end report should explain your agent’s basic conversational features (functionality), discuss the progress you were able to make and how you tested your agent, and the overall findings of your project.
Your report should not exceed 10 pages.
You are allowed to add additional materials in appendices of your report (following the 10 main pages that we will grade). Your main report, however, should be self-comprehensive (a reader should get it without having to access the appendices).
We recommend writing your report in latex.
Your report needs to have the following structure:
Title
Add a title. Also add your group number, student names, emails, and student numbers right below the title.
Introduction (max. 1/2 page):
Briefly introduce your recipe recommendation agent project, and describe your aims for the conversational agent.
How does your agent interact? (1-2 pages):
Provide a functional specification of your agent, describing its main capabilities and the different flow(s) of the interaction a user can have with the agent. Make sure that you give a complete coverage of the features of your agent, so they can be tested based on your description.
Design choices and rationale (2-3 pages):
In this section, you should describe the different design choices you have made while implementing your agent. These design choices are twofold. First, the tasks that are open to interpretation in the instructions. This should include but not be limited to training phrases used (that were not provided), visuals (essentially everything), conversational patterns and agent responses. Second, the different extensions that you have made, adding among others to, for example, the agent functionalities, persona, conversational directions. Make sure to not only describe these design choices, but also to give a clear motivation.
Agent Testing (1-2 pages):
In this section, you should talk about the way in which you tested your own agent continuously. What did you find? Read a bit more about this in Agent Testing.
User Study (2-3 pages):
In this section, you should explain the testing and data gathered that was described in User Study. You should very briefly include the test setup, your goals, and then explain and analyze the data, and discuss lessons learned from your small user study. In the analysis, discuss the performance of some of your extensions separately. To what extent did they improve the interaction with your agent?
For the analysis, looking at quantitative measures found in the logs ca provide valuable insights. Examples of information that can be extracted from the logs and used for analysis include (but are not limited to):
Number of utterances/intents per interaction
Variety in intents and entities (are there unused intents?)
Confidence values for the intent classification (are there any patterns of specific intents having low/high confidence values)?
Interaction length (in time)
Conclusion: (max. 1 page):
Write a brief conclusion about the project itself, as well as a reflection on the process (what went well and what could have been done better?). If, based on the test outcomes, you have ideas on how to improve on the agent if you had more time, this could also be described here.