{"687351":{"#nid":"687351","#data":{"type":"news","title":"Sleepless Tutor Turns Midnight Panic Into Progress","body":[{"value":"\u003Cp\u003EIt\u2019s 1:47 a.m. in a Georgia Tech dorm room. A bleary-eyed student is staring down a homework problem that refuses to make sense. The professor is asleep. Classmates aren\u2019t texting back. Even the caffeine has lost its jolt.\u003C\/p\u003E\u003Cp\u003EIt\u2019s the kind of late-night dead end that pushed the instructors of one particularly tough class to build their own backup: a custom artificial intelligence (AI) tutor created specifically for that course.\u003C\/p\u003E\u003Cp\u003EThey call it the SMART Tutor, short for Scaffolded, Modular, Accessible, Relevant, and Targeted. It guides students through each problem step by step, checks their reasoning, references class notes, and flags mistakes. Instead of handing over solutions, it shows students how to work through them.\u003C\/p\u003E\u003Cp\u003EThat distinction matters most to\u0026nbsp;\u003Ca href=\u0022https:\/\/ece.gatech.edu\/directory\/ying-zhang\u0022\u003EYing Zhang\u003C\/a\u003E, senior associate chair in the\u0026nbsp;\u003Ca href=\u0022https:\/\/ece.gatech.edu\/\u0022\u003ESchool of Electrical and Computer Engineering\u003C\/a\u003E, who created the tool.\u003C\/p\u003E\u003Cp\u003E\u201cUnlike ChatGPT, the tutor doesn\u2019t just give answers,\u201d Zhang said. \u201cWe want to teach students how to approach the problem, think critically, and become self-regulated learners.\u201d\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBorn From One Infamously Tough Class\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EThe idea for the SMART Tutor came from a course that had challenged students for years:\u0026nbsp;\u003Ca href=\u0022https:\/\/ece.gatech.edu\/courses\/ece2040\u0022\u003ECircuit Analysis (ECE 2040)\u003C\/a\u003E. It\u2019s a foundational class for electrical engineering undergraduates and historically one of the most difficult in the curriculum.\u003C\/p\u003E\u003Cp\u003EZhang saw the same pattern semester after semester. Students often needed help at the exact moment it wasn\u2019t available.\u003C\/p\u003E\u003Cp\u003E\u201cMany students study late into the evening,\u201d she said. \u201cThey cannot really attend office hours during the day because of either class or work schedules. So, basically, when students work at night on their homework and get stuck, they have no one to go for help.\u201d\u003C\/p\u003E\u003Cp\u003EStudents were working late into the night; support wasn\u2019t. Zhang and her colleagues set out to change that.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EOffice Hours, Upgraded\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ETheir solution: The SMART Tutor which relies solely on course materials, NOT the open internet. When students upload their completed work, the tutor checks the calculations, the reasoning, and whether the solution holds up in practice, not just on paper. It also provides constructive feedback and shares insights with instructors, helping them identify common misconceptions and adjust in-class instruction.\u003C\/p\u003E\u003Cp\u003EStudents select a homework problem and watch the system break it down step by step. It also answers broader conceptual questions using lectures and notes.\u003C\/p\u003E\u003Cp\u003E\u201cThe students, the SMART Tutor, and the instructor work as a team to help students learn,\u201d Zhang said.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EStudent-Tested, Professor-Approved\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDuring a semester-long pilot with 50 students, Zhang did not require anyone to use the tutor. But nearly everyone did.\u003C\/p\u003E\u003Cp\u003E\u201cMost students felt the AI tutor helped them learn more effectively and at their own pace,\u201d she said. \u201cThey valued the immediate feedback and the chance to learn from mistakes in real time.\u201d\u003C\/p\u003E\u003Cp\u003ENidhi Krishna, a computer engineering major, used the tutor as a sounding board when she got stuck.\u003C\/p\u003E\u003Cp\u003E\u201cWhat helped most was being able to show my work and ask, \u2018Where did I go wrong?\u2019\u201d Krishna said.\u003C\/p\u003E\u003Cp\u003EShe approached it like she would a teaching assistant, working through problems independently and asking for guidance rather than solutions. Students also valued something else: help that showed up at the right moment.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETeaching Students to Think\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EWhat stood out to Zhang wasn\u2019t improved grades. It was what the tutor revealed about how students learn.\u003C\/p\u003E\u003Cp\u003EBy analyzing interaction data, she saw two patterns: students who asked questions to understand, and those who used the system to confirm answers. The difference revealed a deeper gap in learning strategies.\u003C\/p\u003E\u003Cp\u003E\u201cSome students, especially those who need help most, lack strong learning skills,\u201d Zhang said. \u201cStudents with lower academic preparation were more likely to ask guess-and-check questions instead of seeking deeper explanations.\u201d\u003C\/p\u003E\u003Cp\u003EThat insight is already shaping the next version of the tutor.\u003C\/p\u003E\u003Cp\u003EThe SMART Tutor is now part of a broader vision called NEAT: Next-Generation Engineering Education with AI Tutoring. Zhang plans to expand the NEAT framework across Georgia Tech\u2019s College of Engineering and eventually to partner institutions.\u003C\/p\u003E\u003Cp\u003EOne factor fueling that growth is affordability. The system costs about $300 per semester for a class of 50 students, a price Zhang believes most programs can absorb. The academic return, she said, far outweighs the cost.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAlways Awake, Always Ready\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EThere will always be a 1:47 a.m. somewhere on campus.\u003C\/p\u003E\u003Cp\u003EWhen everything stops making sense, students won\u2019t have to give up or wait for the next day\u2019s office hours. The SMART Tutor won\u2019t solve the problem for them, but it will remind them they can solve it themselves.\u003C\/p\u003E\u003Cp\u003EAfter midnight, that may be far more useful than another cup of coffee.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":[{"value":"Created by Georgia Tech professors for a particularly challenging class, this AI teaching assistant doesn\u2019t know the meaning of office hours."}],"field_summary":[{"value":"\u003Cp\u003EBuilt by Georgia Tech faculty for one of the institute\u2019s most demanding courses, the AI tutor steps in when traditional help disappears, guiding students through problems late at night rather than handing them answers. Grounded in course materials, it breaks questions into logical steps, checks students\u2019 reasoning, and points them back to lectures and notes so mistakes become learning moments. Early pilots show students use it heavily, value the immediate feedback, and gain confidence working through complex material on their own.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Created by Georgia Tech professors for a particularly challenging class, this AI teaching assistant doesn\u2019t know the meaning of office hours."}],"uid":"36410","created_gmt":"2026-01-15 17:29:20","changed_gmt":"2026-01-16 02:22:18","author":"mazriel3","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-01-15T00:00:00-05:00","iso_date":"2026-01-15T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"679006":{"id":"679006","type":"image","title":"AI Tutor","body":"\u003Cp\u003EIllustration of an AI tutor assisting a student.\u003C\/p\u003E","created":"1768490116","gmt_created":"2026-01-15 15:15:16","changed":"1768490773","gmt_changed":"2026-01-15 15:26:13","alt":"Illustration of an AI tutor helping a student","file":{"fid":"263117","name":"ChatGPT-Image-Jan-15--2026--10_23_34-AM.png","image_path":"\/sites\/default\/files\/2026\/01\/15\/ChatGPT-Image-Jan-15--2026--10_23_34-AM.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/01\/15\/ChatGPT-Image-Jan-15--2026--10_23_34-AM.png","mime":"image\/png","size":1861024,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/01\/15\/ChatGPT-Image-Jan-15--2026--10_23_34-AM.png?itok=pF6vkDFY"}}},"media_ids":["679006"],"groups":[{"id":"1188","name":"Research Horizons"}],"categories":[{"id":"194606","name":"Artificial Intelligence"}],"keywords":[{"id":"187812","name":"artificial intelligence (AI)"},{"id":"107031","name":"College of Engineering; School of Electrical and Computer Engineering"},{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EMichelle Azriel, Sr. Writer Editor\u003C\/p\u003E","format":"limited_html"}],"email":["mazriel3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}