CodeHelp is a coding and CS assistant.

It can explain issues and answer questions about your code and CS concepts. It uses large language models (LLMs) to understand code and natural language queries and respond in natural language as well.

You can:

  • Ask how to start writing a program.
  • Get an explanation of a confusing error message.
  • Ask why your code isn't working correctly in a particular spot.
  • Learn more about specific syntax, functions, or techniques in your programming language.
  • ... and a lot more.

For instructors:

CodeHelp helps your students any time they have a question, and it provides help without writing code for them. It is made specifically to guide and explain rather than provide solution code.

  • Incorporate LLMs into your teaching in a managed way, offering your students the eductional benefits LLMs can provide without compromising their learning.
  • See your students' queries to gain insights into what they are working on and the sorts of questions they are asking.
  • Tailor responses to your class by providing keywords that responses should not use (e.g. sum() if you want students practicing for loops instead of using a built-in function).

You can share CodeHelp with everyone in your class with a simple link. There are two options:

Request an LMS Connection to automatically connect from an LMS like Canvas, Moodle, etc.
  • Everyone will log in automatically via a link from your course page.
  • Takes some time to set up, and may require support from your LMS administrator.
Log in using Google, Github, or Microsoft and manually create a class from your profile page.
  • You will share an access link, and everyone will log in using a Google, Github, or Microsoft account.
  • Can be set up in less than ten minutes.

The documentation provides more details.

References

[1] CodeHelp: Using Large Language Models with Guardrails for Scalable Support in Programming Classes.
Mark Liffiton, Brad Sheese, Jaromir Savelka, and Paul Denny. 2023. In Proceedings of the 23rd Koli Calling International Conference on Computing Education Research (Koli Calling '23). DOI: 10.1145/3631802.3631830

[2] Patterns of Student Help-Seeking When Using a Large Language Model-Powered Programming Assistant.
Brad Sheese, Mark Liffiton, Jaromir Savelka, and Paul Denny. 2024. In Proceedings of the 26th Australasian Computing Education Conference (ACE '24). DOI: 10.1145/3636243.3636249

Pricing

CodeHelp itself does not take payment, but the OpenAI LLMs it uses are not free. We will ask you to provide an OpenAI API key to be used for your students' queries.

Costs are low: OpenAI will charge you roughly US$0.02 for each query made with the GPT-4 model (GPT-3.5 is roughly 1/20 the cost, though less accurate). If your students use CodeHelp regularly and average 50 queries each over a semester (higher than the average we've observed), your total costs would be roughly $1 per student (or $0.05 per student if using GPT-3.5).

Example: