NTU CCDS · Learn with AI Framework Peer-reviewed · ACM DIS 2026 2026 GMA Award

AlgoGPT: Learning with AI
for Data Structures & Algorithms

From Answer Keys to Socratic Mentors

Fostering Learner Agency and Self-Regulated Learning through Adaptive AI Scaffolding in Programming Education

AlgoGPT is an AI-powered learning platform for programming education, conceptualised and led by Dr Owen Noel Newton Fernando and supported by an NTU EdeX grant. It supports learning through guided hints rather than direct answers. Using Socratic questioning and a Driver–Navigator learning model grounded in Cognitive Load Theory and Self-Regulated Learning, students alternate between implementing solutions independently, explaining their reasoning, and critically evaluating AI-generated code to strengthen algorithmic thinking, reflection, and problem-solving skills.

SC1007 — Data Structures and Algorithms is a foundational, compulsory course for every undergraduate at the College of Computing and Data Science (CCDS), Nanyang Technological University — a cohort of around 1,000 students each year. It was redesigned under the College's Learn with AI framework for an AI-shaped future, where understanding why code works matters more than simply generating it.

0
active students across one compulsory semester
0
code submissions analysed (Jan–Apr 2026)
0
independent AI-scaffolded learning sessions
700+
practice questions: 400+ programming tasks & 300+ MCQs
01 Awards & Recognition

Recognised on the global stage for technology-enhanced STEM teaching.

SC1007 Data Structures and Algorithms, incorporating AlgoGPT, was selected as one of ten winners of the 2026 GMA Award for Outstanding Courses — achieving the highest overall evaluation score among the ten award-winning courses, according to communication from the GMA organisers.

Dr Owen Noel Newton Fernando (eighth from left) with fellow award recipients on stage at the 2026 GMA Awards Ceremony, each holding a certificate
GMA Awards Ceremony Dr Newton Fernando (eighth from left) receives the 2026 GMA Award for Outstanding Courses for SC1007 Data Structures & Algorithms, alongside fellow winners at the Global MOOC and Online Education Conference.
2026 · International

GMA Award for Outstanding Courses

Global MOOC and Online Education Alliance (GMA)

SC1007 Data Structures and Algorithms, incorporating AlgoGPT, was selected as one of ten winners of the 2026 GMA Award for Outstanding Courses.

This recognition highlights its innovative approach to personalised learning, independent problem-solving and critical evaluation of AI-generated code.

Evaluated by an international committee of education experts and learners drawn from UNESCO and other leading institutions.

Highest overall evaluation score among the ten winners

According to communication from the GMA organisers.

Official Award Announcement →
2026 · NTU

John Cheung Emergent Technology Award

Nanyang Technological University

Dr Owen Noel Newton Fernando was selected for NTU’s 2026 John Cheung Emergent Technology Award, recognising his contributions to technology-enhanced education, including the innovative application of AlgoGPT in Data Structures and Algorithms.

2026 · Peer-reviewed

ACM DIS 2026 & NIE RPIC 2026

Research venues

Navigator Mode's flawed-AI-partner design was published at ACM DIS 2026, and AlgoGPT was featured by NTU InsPIRE in October 2026.

02 Learn with AI

SC1007 doesn't teach around AI — it teaches students to learn with it.

NTU's College of Computing & Data Science is embedding AI into how computing is taught, practised and assessed through its Learn with AI framework. In SC1007, students explore core data structures and algorithms in an AI-supported environment that offers guided hints and feedback — never finished solutions — as they solve problems. Practice is dynamically generated to each student's skill level, so a cohort of over a thousand learns at its own pace while building the judgement to evaluate AI-generated code.

From the Dean

“Artificial intelligence is a multiplier. But if the multiplicand is zero, the outcome is zero.”

Professor Luke OngDean, College of Computing & Data Science, Nanyang Technological University

The learning cycle

Every problem moves a student through three modes of thinking — the structured approach at the heart of SC1007's redesign. AlgoGPT supports each stage with Socratic questions, never finished code.

01
Explain

Articulate the reasoning

Students put their algorithmic logic into words before any code is written, externalising the mental model so gaps surface early.

02
Implement

Build it independently

Students write and refine the solution themselves, receiving tiered Socratic nudges only on request — direction, never the answer.

03
Evaluate

Judge the AI's code

Students review AI-assisted output critically, verifying it against the fundamentals — the skill that matters most in an AI-shaped world.

One lab, two halves

Each two-hour lab is built around the Zone of Proximal Development — students first build reasoning unaided, then extend it with adaptive AI support. The same AI-ON / AI-OFF principle carries into assessment: independent mastery is always verified separately from effective tool use.

Hour 01 · AI-OFF

Tutor-led conceptual work

Students design and analyse linked lists, stacks, queues, trees and graphs by hand — developing problem decomposition and debugging with no GenAI in the room.

Hour 02 · AI-ON

AI-supported pair programming

Students pair with AlgoGPT in Driver and Navigator modes while Teaching Assistants act as meta-coaches — guiding responsible, reflective use of every piece of AI feedback.

Supporting NTU2030’s four dimensions of AI learning

AlgoGPT supports NTU2030’s emphasis on personalised, AI-supported education. The course follows a deliberate sequence: AI-OFF conceptual learning builds foundations, AI-supported practice provides guided application, and independent assessment requires students to show their own competence. Each of NTU2030’s four dimensions maps to a specific part of the platform.

Learn about AI

Understanding what AI is, how it works, its capabilities and societal impact.

Recognising capabilities & limits

Deliberately flawed AI code makes the strengths and failure modes of generative AI visible in every lab.

Learn how to use AI

Engaging with AI tools effectively, ethically and responsibly.

Responsible critical review

In Navigator Mode, students review AI-generated code, decide whether to accept or reject it, and identify, explain and correct the flaw.

Learn with AI

Collaborating with AI to enhance teaching, creativity, and learning experiences.

Socratic guidance

In Driver Mode, students write their own code while a four-tier Socratic ladder guides them without ever giving runnable solutions.

Learn beyond AI

Developing meta-intelligences underpinning human wisdom, ethics and emotional understanding that AI cannot replace.

Independent judgement

Reflection and No-AI practice build independent judgement, self-regulation and problem solving.

Learn with AI pilot
SC1007 · Data Structures & Algorithms SC2000 · Probability & Statistics SC2006 · Software Engineering SC4052 · Cloud Computing
03 The Challenge

In the age of AI, the villain isn't a hard concept — it's frictionless learning.

Standard large language models act as a black box: they hand over working solutions instantly, letting students bypass the very struggle that builds deep understanding. Learning theory is clear that durable knowledge requires effortful, active construction — and frictionless assistance short-circuits it.

“Being denied the answer forced me to actually think. For the first time, I felt I owned the code, not the AI.”
— SC1007 STUDENT
Standard AI

AI as Answer Key

Immediate, complete solutions. Speed without comprehension — and a learner who never owns the logic.

AlgoGPT

AI as Socratic Mentor

Structured friction by design. Hints, questions and deliberately flawed code that force reasoning — turning answers into earned insight.

AI systems can generate code remarkably quickly, but understanding why that code works remains fundamental. In our courses, students learn to use these tools responsibly while still making sound design decisions, reasoning through problems, and verifying the correctness of their solutions.

Dr Newton Fernando  — Faculty lead, SC1007 Data Structures & Algorithms · NTU CCDS
04 The Platform

More than a chatbot — a classroom operating system for DSA courses.

Alongside its four learning modes, AlgoGPT provides personalised and adaptive learning support through several integrated features. Students can practise at their own pace, assess their understanding and receive personalised support based on their progress.

⌨
FEATURE 01

Programming Practice

Over 400 programming questions covering fundamental and advanced topics in Data Structures and Algorithms.

◍
FEATURE 02

Conceptual Assessment

Over 300 MCQs to assess understanding, reinforce key concepts and identify knowledge gaps.

⟳
FEATURE 03

Adaptive Recommendations

Personalised practice recommendations based on MCQ responses, laboratory submissions and programming attempts.

◧
FEATURE 04

Learner Profiles

Individual profiles that help students monitor their progress, understand their proficiency and identify areas requiring improvement. Each profile begins with a ten-question adaptive assessment and is updated as students learn.

▤
FEATURE 05

Learning Analytics

Dashboards that provide students and educators with insights into learning progress, common difficulties and areas requiring additional support.

⚿
FEATURE 06

Institution-Ready

A closed lab system with access codes, enrolment, and session tracking — built around the professor → TA → student hierarchy.

These features support students in planning their learning, monitoring their understanding, adjusting their strategies and reflecting on their progress. Educators can also use learning analytics to identify common misconceptions and provide more targeted support.

05 The Pedagogical Engine

Four learning modes that keep students actively involved in learning.

AlgoGPT supports four complementary learning modes that balance independent problem-solving with structured AI assistance.

1

No-AI Mode

Independent Problem-Solving

Students solve programming problems independently without AI assistance, applying their knowledge and developing confidence in their own problem-solving abilities. This mode provides opportunities to practise and assess independent understanding.

2

Normal Mode

Personalised AI Guidance

Students receive personalised hints, explanations and guiding questions to help them understand programming concepts and overcome difficulties without receiving complete code solutions. The AI provides assistance while encouraging students to develop their own answers.

3

Driver Mode

Student-Led Programming

Students write their own code while AI provides Socratic questions and structured guidance. This mode supports productive struggle by encouraging students to reason through problems, make decisions and refine their solutions rather than relying on AI to write code for them.

Together, these modes provide different levels of AI assistance while keeping students actively involved in the learning process. Driver and Navigator Modes particularly emphasise learner agency, productive struggle and critical engagement with AI-generated solutions — powered by two specialised, role-reversing agents explored below.

The core interaction loop within AlgoGPT — Driver Mode and Navigator Mode
Figure 1 The core interaction loop. Driver Mode (top): the student writes code and receives non-directive, multi-tiered Socratic feedback. Navigator Mode (bottom): the student instructs in natural language and the agent intentionally generates subtly flawed code to provoke critical review.

The Driver

Socratic Coach · Student-Led Programming

Students write their own code; the AI intervenes only on a student-initiated request. Rather than offering fixes, the Driver decomposes feedback into four escalating tiers — functioning like a senior instructor who scaffolds through questions, never supplying runnable code.

1High-level analysisFrame the problem without revealing the path.
2Conceptual hintsSurface the relevant idea — a tree, a hash, an invariant.
3Guiding questionsPrompt the student to locate their own gap.
4Pseudocode suggestionsHigh-level direction, never runnable code.
AlgoGPT interfaces: (1) Navigator Mode, where the student prompts the AI Lab Assistant with their solution logic and accepts or rejects the generated code; (2) Driver Mode, where the AI Lab Assistant delivers Socratic nudges on request
Figure 2 (1) Navigator Mode: the student prompts the AI Lab Assistant with their solution logic to generate code, then reviews the highlighted changes and accepts or rejects them. (2) Driver Mode: when the student asks, the AI Lab Assistant delivers Socratic nudges (analysis, hint, question to consider, suggestion) to scaffold independent problem solving.

Normal Mode

Personalised AI Guidance

Students receive personalised hints, explanations and guiding questions to help them understand programming concepts and overcome difficulties — without receiving complete code solutions. For research, it also serves as a within-system baseline that isolates the effect of Driver and Navigator Modes.

○Always reachableA floor of support beneath every learner.
○Comparative baselineLets researchers measure the friction effect directly.
○Graceful fallbackCognitive walls become detours, not dead ends.

No-AI Mode

Independent Problem-Solving

Students solve programming problems independently without AI assistance, applying their knowledge and developing confidence in their own problem-solving abilities. Automated test cases still give performance feedback independently of generative AI.

∅Unaided problem solvingBuild and assess skills without any AI support.
∅AI-blind feedbackAutomated test cases check correctness objectively.
∅Learn beyond AIPairs with AI-supported tasks to check independent understanding.
06 System Architecture

A theory-driven, multi-agent system — engineered to scale.

AlgoGPT is built on a stateless backend with LangGraph agent orchestration and Azure-hosted GPT-4o models providing pedagogically constrained reasoning. Each agent has one job; together they manage cognitive load end to end.

LP

Learner Profiling Agent

Runs the diagnostic quiz, classifies mastery, and generates each student's personalised learner profile.

CA

Code Analysis Agent

Inspects submissions to detect misconceptions and the specific reasoning gap behind a failed attempt.

RV

Response Validation Agent

Guards the Socratic protocol — ensuring feedback never leaks runnable solutions to the student.

IC

Instructional Chatbot

Delivers real-time, non-directive feedback through reflective prompts and scaffolding strategies.

TS

Adaptive Task Scheduler

Sequences problems and difficulty, moving learners along a personalised topic progression.

RG

Problem-Context RAG

Grounds every agent response in the exact problem statement and course knowledge base.

Frontend  Next.js / React Monaco Editor Backend  FastAPI LangGraph orchestration ATLAS NALA integration Reasoning  Azure GPT-4o Stateless API Code Runner Service LSP Backend Service Storage  PostgreSQL Azure Container Registry
07 The Evidence

35,000+ data points prove that desirable difficulty works.

Across a 14-week semester, AlgoGPT's friction modes produced significantly higher-quality behavioural patterns than standard AI assistance.

Eventual success rate by mode

Lower "frictionless" passing in friction modes reflects deeper cognitive effort — not failure.

Normalbaseline
88.0%
Driversocratic
58.6%
Navigatorevaluator
55.0%

Session outcomes

26% ran to time expiry — an "immersion effect", not abandonment.

10,333 SESSIONS
60.2% · Completed
26.4% · Cognitive immersion
8.1% · Skipped

Performance & persistence by interaction mode

Driver mode raises iterative engagement; Navigator mode shows the "efficiency of insight" — fewer attempts, deeper pre-submission analysis. Structured modes roughly double time on task, which suggests sustained engagement (time alone does not prove deeper understanding).

MetricNormal · BaselineDriver · SocraticNavigator · Evaluator
Eventual success rate88.0%58.6%55.0%
Mean attempts per session3.073.242.36
Attempts to first accept2.462.661.80
Mean tests passed / submission3.51 / 105.13 / 103.57 / 10
Mean session duration10.9 min21.6 min20.1 min
87.0%
of 5,474 Driver sessions completed without a single AI nudge — proof against AI-dependency.
|rb| = 0.28
effect size, Normal vs Driver (Mann–Whitney U, p < 1×10⁻¹⁹⁰).
t = 6.97
highest significance in the study — students checking their own understanding.

Engagement deepens over the term

Across the 14-week semester, 35,433 submissions were processed without meaningful attrition. Lab-level success climbed steadily as students adapted to friction-first practice — engagement increased rather than eroded.

60 40 20 0 18.7% 22.7% 46.6%
Lab 1 — Linked ListsLab 2 — Stacks & QueuesLab 3 — Binary Trees

In students' words

“Driver and Navigator modes are quite engaging—it really forces me to think instead of just copying answers.”

SC1007 student

“Navigator Mode helped me understand the logic better because I had to explain it clearly to the AI.”

SC1007 student

“The hints guide me without giving the answer, which improves my confidence.”

SC1007 student

“Explaining my reasoning for each MCQ really helped me understand the concepts better.”

SC1007 student
08 Pedagogical Foundations

Friction, embedded structurally.

AlgoGPT draws on three complementary educational principles to support meaningful learning with AI.

Self-Regulated Learning

Taking ownership of learning

Students take an active role in managing their learning through four processes: planning, monitoring, control and reflection. They identify areas for improvement, monitor their understanding, adjust their problem-solving strategies and reflect on feedback — supported by personalised learner profiles, adaptive practice recommendations and learning analytics.

Cognitive Load Theory

Managing learning complexity

Programming requires students to understand problems, select appropriate algorithms and translate their reasoning into code. Structured hints, guiding questions and adaptive scaffolding help manage these demands — offering support when needed rather than complete solutions, to reduce unnecessary load while preserving the mental effort required for learning.

Productive Struggle

Learning through challenges and mistakes

Students work through meaningful challenges instead of immediately relying on AI-generated answers: investigating difficulties, testing their reasoning and revising their solutions. In Navigator Mode, deliberately introduced errors create opportunities to identify and explain mistakes. The aim is to make struggle productive through appropriate guidance and feedback, rather than leaving students frustrated or dependent on AI.

Self-Regulated Learning survey — N = 155

Reflective self-evaluationM 3.46
Metacognitive monitoringM 3.41
Metacognitive planningM 3.40
Cognitive scaffoldingM 3.24
Affective outcomesM 3.23

Overall mean 3.39 / 5.0; all 12 items significantly above the neutral midpoint. "Checking understanding" gave the study's largest effect (t = 6.97).

09 Adaptive & Equitable

A personal mentor — calibrated to where each learner actually struggles.

AlgoGPT profiles every learner and detects struggle at a fine grain, so 24/7 Socratic coaching reaches a diverse cohort once shaped by access to private tutoring.

Diagnostic skill distribution

Week-2 profiling quiz — N = 760 students classified by the Learner Profiling Agent.

Beginner53.4% · 405
Unclassified32.0% · 243
Intermediate14.5% · 110
Advanced0.3% · 2

A mostly-beginner cohort — the profile that benefits most from progressive, confidence-building scaffolding.

Algorithmic struggle detection

A 9-level ordinal scale moves beyond code correctness to capture cognitive difficulty.

36.0%
33.7%
22.9%
7.4%
Moderate struggles · Levels 3–6 — 263 students with recurring reasoning challenges.
No explicit struggle · 246 students with stable conceptual fluency.
Severe struggles · Levels 7–9 — 167 students needing structured intervention.
Minor confusion · Levels 1–2 — brief, self-resolved uncertainty.
⊕

Infrastructure equity

A lightweight, web-based platform — no high-end hardware, no installs. World-class scaffolding on any device.

◷

The 24/7 tutor

Immediate, personalised feedback for learners who cannot afford private academic support — available at every hour.

⇄

Naturally differentiated

Scaffolded support for struggling learners; critical evaluation for advanced ones — diverse entry points, one system.

10 Scale, Sustainability & Roadmap

Proven at scale — and built to evolve with every cohort.

A stateless architecture scales from ten students to ten thousand on standard infrastructure. The pedagogy is domain-agnostic, and the roadmap turns today's uniform friction into tomorrow's adaptive scaffolding.

⇗

Horizontal scaling

Stateless sessions with no server-side memory overhead scale effortlessly on Azure container infrastructure and a React frontend.

⌥

Domain-agnostic blueprint

The tiered-nudge protocol is tied to structured reasoning, not a language — ready for Systems Programming, Maths, Physics and beyond.

◎

Quality at scale

Automated, AI-blind test cases keep grading objective; submission logs let instructors detect unproductive frustration early.

Ready to adapt across CCDS

The Driver–Navigator framework fits any course with practical tasks, identifiable errors and clear evaluation criteria. Adapting it needs course-specific diagnostic questions, task banks, guidance prompts, representative flaws and automated checks — packaged as reusable templates, rubrics and instructor orientation.

Closest fits
SC1003 · Computational Thinking & Programming SC1008 · C & C++ Programming SC2001 · Algorithm Design & Analysis SC2002 · OO Design & Programming SC2207 · Introduction to Databases SC2006 · Software Engineering SC3061 · Human-Computer Interaction

On the roadmap

01

Performance-triggered adaptive scaffolding

Calibrating the intensity of "friction" to a student's real-time struggle, so productive struggle never tips into unproductive confusion.

02

Diagram-based explanations

Mermaid.js integration to render data-structure and algorithm visuals inside the feedback loop, anchoring abstract concepts.

03

Audio-based feedback

Whisper-based models to let students give and receive feedback by voice — humanising the pair-programming experience.

04

Controlled learning-gains study

Pre/post assessments and difficulty-controlled comparisons to move from evidence of engagement to measured learning gains.

11 The Team

Built at NTU's College of Computing & Data Science.

Drawing on more than ten years of teaching Data Structures and Algorithms, Dr Fernando conceptualised AlgoGPT and led its educational design, development and integration into SC1007, supervising PhD, FYP and URECA students who turn pedagogical requirements into platform features. Faculty collaborators Dr Siyuan Liu and Mr Ong Chin Ann work alongside him to deploy and refine AlgoGPT in SC1007. PhD student Mr Yeo Shi Jing investigates how AI can improve, rather than degrade, students’ learning. Current and former FYP and URECA students contribute to its research, development, testing and evaluation, bringing student perspectives into the design of AI-supported learning.

Principal Investigator & Project Lead
OF

Dr Owen Noel Newton Fernando

NTU Profile →
Senior Lecturer
College of Computing and Data Science, Nanyang Technological University
Faculty

Faculty Collaborators

Dr Siyuan LiuLecturer · CCDS, NTU
Mr Ong Chin AnnLecturer · CCDS, NTU
Doctoral

PhD Student

Mr Yeo Shi JingPhD (Part-Time) · CCDS, NTU

Improving Learning with AI — co-supervised with Prof Jagath C Rajapakse.

Final Year Project

FYP Students

  • Eva Faith Wong Jie Ting
  • Ng Qi Cheng
  • Jolie Tan (Jolie Chen En)
  • Agarwala Grisha
URECA

URECA Students

  • Balakrishnan Vaisiya
  • Kway Ler Koon
  • Mishra Suhani
  • Manoj Siddhanth
  • Nikita Saravanan
Alumni

Former Contributors

  • Harvande Advika Sandeep
  • Summit Bajaj

We acknowledge the contributions of former students who supported the development and advancement of AlgoGPT.

12 Research & Recognition

Peer-reviewed and validated by the global academic community.

AlgoGPT also serves as a research platform for investigating how students learn through interactions with generative AI, particularly when AI-generated solutions contain mistakes that encourage critical evaluation, reflection and independent problem-solving.

The peer-reviewed deployment analysed 907 students and 14,958 submissions across 27 DSA problems; the figures throughout this site reflect the expanded post-publication dataset of 35,433 submissions.

ACM DIS

Beyond the Perfect Assistant: Provoking Learning with Flawed AI Partners

V. Balakrishnan, L. K. Kway, A. H. Sandeep, E. F. J. T. Wong, C. A. Ong, O. N. N. Fernando. “Beyond the Perfect Assistant: Provoking Learning with Flawed AI Partners,” DIS Companion ’26: Companion Publication of the 2026 ACM Designing Interactive Systems Conference, 13–17 June 2026, Singapore, pp. 270–274. Association for Computing Machinery.

Explores how deliberately imperfect AI partners can encourage students to question AI-generated solutions, identify errors and engage more actively in programming problem-solving — the approach reflected in AlgoGPT’s Navigator Mode.

2026
NIE RPIC

On the Evolution of Pair Programming in AI-Scaffolded Learning

Accepted — NIE Redesigning Pedagogy International Conference 2026
2026
NTU InsPIRE

AlgoGPT: Designing an AI Coding Mentor to Foster Productive Struggle and Learner Agency

Featured article · NTU InsPIRE · 28 October 2026

Published by NTU’s Institute for Pedagogical Innovation, Research and Excellence (InsPIRE), the article highlights how AlgoGPT encourages productive struggle, learner agency and independent problem-solving through structured AI guidance rather than complete solutions — and how educational principles can inform the design of AI learning experiences.

2026
Ethics  NTU IRB-2023-735 Funding  NTU EdeX Grant #025734-00001 Instrument  12-item Likert SRL survey, 5 dimensions Recognition  2026 GMA Award · 2026 John Cheung Emergent Technology Award Platform  algogpt.azurewebsites.net
Our Vision

The technology doesn't replace the human —
it amplifies the ability to think.

We envision a future where AI supports students in becoming more capable, confident and independent learners — combining personalised AI guidance with meaningful opportunities for productive struggle, reflection and critical thinking.

Rather than measuring success solely by what students can accomplish with AI, we focus on what they can understand, explain and solve independently after learning with it.

Platform  algogpt.azurewebsites.net Contact  ofernando@ntu.edu.sg Course  SC1007 · NTU Singapore