Education Platform / Domain-Specific AI

Structured teaching plus AI-powered game analysis.

Sunday Go Lessons

Full-stack platform for learning the game of Go, combining traditional teaching methods with AI-powered analysis and interactive training tools.

Next.jsKataGoTeaching tools
Sunday Go Lessons screenshot 1
Sunday Go Lessons screenshot 2
Sunday Go Lessons screenshot 3
Sunday Go Lessons screenshot 4
Sunday Go Lessons screenshot 5
Sunday Go Lessons screenshot 6
Sunday Go Lessons screenshot 7
Sunday Go Lessons screenshot 8
Sunday Go Lessons screenshot 9
Sunday Go Lessons screenshot 10
Sunday Go Lessons screenshot 11
Sunday Go Lessons screenshot 12

1 / 12

Summary

Project summary

Go learning platform combining structured lessons, problem training, and AI-powered game analysis using KataGo.

Full-stack platform for learning the game of Go, combining traditional teaching methods with AI-powered analysis and interactive training tools.

Problem

What needed to be solved

Go is difficult to learn because feedback is limited, analysis is complex, and strong players are required to review games.

  • Feedback is limited.
  • Analysis is complex.
  • Most tools either focus only on AI or lack structured teaching.
Approach

How it was built

Key implementation decisions, system behavior, and workflow structure.

  • Built a full learning platform with lessons, problem training, and a lecture system.
  • Integrated KataGo for game reviews and position evaluation.
  • Developed lecture tooling to record and present lessons directly in the platform.
  • Combined structured teaching, AI insights, and interactive practice.
Tech stack

Tools and platform choices

Core technologies used in the project.

  • Next.js
  • Supabase
  • KataGo (AI engine)
  • TypeScript
Tradeoffs and lessons

What mattered during implementation

Challenges, tradeoffs, and takeaways from the project.

Challenges / Tradeoffs

  • Translating AI output into human-understandable teaching.
  • Balancing complexity vs beginner accessibility.
  • Integrating AI analysis without overwhelming users.

Outcome / Lessons

  • AI alone doesn’t teach — structure plus explanation does.
  • Domain expertise is critical when applying AI.
  • Teaching tools need to simplify, not just analyze.

Related projects

More systems and applied AI work in the portfolio.

Coding Your Career screenshot 1
Coding Your Career screenshot 2
Coding Your Career screenshot 3
Coding Your Career screenshot 4
Coding Your Career screenshot 5
Coding Your Career screenshot 6
Coding Your Career screenshot 7
Coding Your Career screenshot 8
Coding Your Career screenshot 9
Coding Your Career screenshot 10
Coding Your Career screenshot 11

1 / 11

Education Platforms

Coding Your Career

AI-powered learning platform with a custom LMS, AI teaching assistant, and automated content generation.

Custom LMS with AI teaching and grading workflows.

Next.jsSupabaseAI assistant
Workflow IQ screenshot 1
Workflow IQ screenshot 2
Workflow IQ screenshot 3
Workflow IQ screenshot 4
Workflow IQ screenshot 5
Workflow IQ screenshot 6

1 / 6

AI Systems

Workflow IQ

Agent-based workflow system using DAG architecture to safely constrain and orchestrate AI agents.

2nd place at Tetrate buildathon.

Agentic AIDAG orchestrationSupabase
Journey to the Middle Kingdom screenshot 1
Journey to the Middle Kingdom screenshot 2
Journey to the Middle Kingdom screenshot 3
Journey to the Middle Kingdom screenshot 4
Journey to the Middle Kingdom screenshot 5
Journey to the Middle Kingdom screenshot 6

1 / 6

Creative & Educational Work

Journey to the Middle Kingdom

A time-travel adventure comic inspired by Chinese mythology. Action, humor, culture, and meaningful life lessons for curious young readers and families.

Long-term storytelling project with its own world, tone, and visual identity.

Original comicWorld-buildingSerialized storytelling