Back to all discussions

  •   almost 2 years ago

Contradictory description

Hi, thanks for holding this hackathon. Please help me to understand a contradiction.

On the competition homepage…
> First thing under “Requirements”, “what to build”, “Build a no/low-code conversational AI agent…”
> First thing under “Judging Criteria”, “Technological Implementation”, “Does the project demonstrate quality software development? … How is the quality of the code?”

This hackathon says it’s no-code. Yet its first judging criteria is ‘quality software development’ and high quality code. How does that make sense?

  • 4 comments

  • Manager   •   almost 2 years ago

    Hi there,

    Your “code” is the prompts you enter when creating your agent (i.e. Goal, Instructions) and any Examples, Tools, or Integrations or that you choose to use. So while it is low/no code friendly, we will be judging on how well you used the tool. Hope this helps!

  •   •   almost 2 years ago

    Do we need to share our prompts, tools and functions? Is there a way to keep our code integration confidential if we consider them sensitive, such as redacting certain information?

  • Manager   •   almost 2 years ago

    Prompts are required as part of the What to Submit:
    Include a Project built with the required developer tools and meets the above Project Requirements.
    Include a text description that includes a summary of the Project’s features and functionality.
    Include at least one Test Scripts for your Project
    Include at least one screenshot of the results of running the Test Script
    Include a demonstration video of your Project.

    We’re looking for a document such as a PDF that walks a user or tester through recommended prompts so they can experience the agent themselves. Two options would suffice:
    [Preferred] serve agent on an endpoint, indicated endpoint in the submission, and provide recommended conversation starters or prompts that a new user or tester could use to demo the abilities and features of your AI Agent.
    [Also Ok] If unable to serve the agent to other users, submit the same as above but also include screenshots of the responses your AI Agent outputs in the UI using the Preview Agent right-hand sidebar.

    I probably wouldn't suggest prompting any private information as your submission and materials are public. Please read the full rules if you have further questions about that.

  •   •   almost 2 years ago

    Yes that helps, thank you Shawni. Calling the prompts 'code' made it very confusing. Thank you for clarifying.

Comments are closed.