61A Bot Report: AI Assistants in CS1 Save Students Homework Time and Reduce Demands on Staff. (Now What?)
Not on the map. Why?
Abstract (arXiv)
LLM-based chatbots enable students to get immediate, interactive help on homework assignments, but even a thoughtfully-designed bot may not serve all pedagogical goals. We report here on the development and deployment of a GPT-4-based interactive homework assistant ("61A Bot") for students in a large CS1 course; over 2000 students made over 100,000 requests of our Bot across two semesters. Our assistant offers one-shot, contextual feedback within the command-line "autograder" students use to test their code. Our Bot wraps student code in a custom prompt that supports our pedagogical goals and avoids providing solutions directly. Analyzing student feedback, questions, and autograder data, we find reductions in homework-related question rates in our course forum, as well as reductions in homework completion time when our Bot is available. For students in the 50th-80th percentile, reductions can exceed 30 minutes per assignment, up to 50% less time than students at the same percentile rank in prior semesters. Finally, we discuss these observations, potential impacts on student learning, and other potential costs and benefits of AI assistance in CS1.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Jun 2024.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2025: 3; 2026: 4.
7 papers.
- 2025ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluationcited by 2
- 2025Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants' Question-Answering in Asynchronous Learning Environmentscited by 1
- 2026The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectivenesscited by 1
- 2025From Pilots to Practices: A Scoping Review of GenAI-Enabled Personalization in Computer Science Educationcited by 0
- 2026Beyond Perspectives: A Trio-Ethnography of Interpretation Evolution in LLM-Supported Programming Educationcited by 0
- 2026Beyond Benchmark Scores: How Synthetic and Authentic Query Distributions Diverge in RAG Evaluationcited by 0
- 2026Guardrails or Roadblocks? Effects of Pedagogical Style and Context Awareness in AI Teaching Assistants for Programmingcited by 0
- 2026Guardrails or Roadblocks? Effects of Pedagogical Style and Context Awareness in AI Teaching Assistants for Programming24 Sep 2026
- 2026Beyond Benchmark Scores: How Synthetic and Authentic Query Distributions Diverge in RAG Evaluation13 Sep 2026
- 2026Beyond Perspectives: A Trio-Ethnography of Interpretation Evolution in LLM-Supported Programming Education24 Jul 2026
- 2026The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness7 May 2026
- 2025From Pilots to Practices: A Scoping Review of GenAI-Enabled Personalization in Computer Science Education23 Dec 2025
- 2025Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants' Question-Answering in Asynchronous Learning Environments22 Sep 2025
- 2025ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation16 Jul 2025