College application research evidence · understanding and original contribution · Seoul and online
Project courseThe student keeps the work and the record they made.
High School AI Assistants: Build, Test, and Explain
Grades 9-12: failure modes of multi-agent systems...
- Free consultation and level check
- Apgujeong classroom or online
- One-to-one or small group
- Registered academy no. 11882
Is High School AI Assistants: Build, Test, and Explain a good fit for high school students in Grades 9-12?
High School AI Assistants: Build, Test, and Explain is a good fit for students in grades 9-12 who are interested in failure modes of multi-agent systems and statistics for AI evaluation. CIT offers online or in-person lessons in Apgujeong, Gangnam, Seoul, in one-to-one or small-group formats. Students make baseline comparisons with statistical notes, a read-only MCP prototype, and a research report with a reproducible repository.
Students turn the claim that a multi-agent system is needed into a question that could be proven wrong, then compare it over repeated runs with the simplest single workflow that uses the same tools, data, and budget. Inside a prepared sandbox with synthetic data and read-only credentials, they go on to test coding-agent patches, mixed retrieval, an MCP integration, multimodal input, and latency and cost. The course ends by reproducing a tutor-vetted external result, extending one variable, and defending the research report in an oral review. The student sets their own question, then designs and tests a feature, model, interface, or solution of their own. In an application or interview, the student separates the material they drew on from their own decisions, results, failed attempts, revisions, and limits.
Google sign-in is required. Existing account permissions determine access.
Public task-board example: code, tests and assessment (teaching demo, not student work)
I appreciated that a simple early idea was extended into an 'AI debate tool'. My child has always been interested in debate and social issues, so seeing that interest connect to the project makes me expect a more complete and distinctive result.
- Age group
- Grades 9-12
- Academic subject
- AI & Data, Engineering & Robotics, Research & PortfolioBrowse subject
- Course type
- Course
- Format
- Online or Apgujeong in person · one-to-one or small group
- Teaching language
- Korean by default, with complete English materials
- Curriculum status
- Lesson-readyEvery learning item includes the evidence, worked example, practical work, and tutor guidance required by CIT's lesson-ready standard.
From open research to student-owned work
Students inspect a relevant public source, reproduce the idea, then add an original question, feature, or test. Every source is public, and each lesson names the exact page it opens.
How can I explain this course to my child?
If questions about failure modes of multi-agent systems or statistics for AI evaluation keep making you ask why, High School AI Assistants: Build, Test, and Explain lets you investigate the question with evidence, then build and defend an extension of your own.
Which interests suggest this course?
- failure modes of multi-agent systems
- statistics for AI evaluation
- reviewing coding-agent patches
What does the student finish?Baseline comparisons with statistical notes, a read-only MCP prototype, and a research report with a reproducible repository.
Is this a good fit?
A strong fit for students who want to understand, build, test, or responsibly use AI systems.
Course placement follows current subject and coding readiness.
Students should be ready to document sources, methods, and limits.
Advanced tools are introduced after a clear baseline.
What will my child learn?
- Turn a claim that multiple agents are needed into a falsifiable question with a single-workflow baseline and stop conditions.
- Run a larger benchmark repeatedly and interpret means, spread, and effect sizes, adding confidence intervals when justified.
- Review a coding agent's patch with diffs, hidden tests, and failure injection, then approve, request changes, or reject it.
- Apply minimal scopes, user consent, and secret-free logging to a read-only MCP integration.
How does the course progress?
- 1Multi-Agent Systems and Emergence
Compare a single-workflow baseline with a multi-agent design over repeated runs, separating coordination failures from undesigned behavior.
- 2Advanced Evaluation
Version a larger benchmark with boundary, adversarial, and held-out cases and reanalyze repeated runs with statistics.
- 3Coding Agents and Execution Feedback
Have an agent fix a bug in a sandboxed repository, then review the patch with diffs and hidden tests before deciding to merge.
- 4Advanced Retrieval and Knowledge Systems
Compare structured search with embedding search on the same questions and merge evidence while keeping sources, dates, and conflicts.
- 5MCP and Controlled Integration
Connect minimal scopes, token audience checks, user consent, and secret-free logging to a read-only MCP server.
- 6Multimodal and Real-Time Systems
Pick one camera, audio, sensor, or browser input and measure how timing, noise, and missing data affect results.
- 7Runtime and Performance Engineering
Measure latency, throughput, caching, and cost, and compare a sequential baseline with limited concurrency under load.
- 8Reproduction, Open Source, and Defense
Reproduce a vetted external result in a fixed environment, extend one variable, and defend the research report orally.
What counts as useful evidence?
Baseline comparisons with statistical notes, a read-only MCP prototype, and a research report with a reproducible repository.
What should an admissions reader be able to see?
The student sets their own question, then designs and tests a feature, model, interface, or solution of their own. In an application or interview, the student separates the material they drew on from their own decisions, results, failed attempts, revisions, and limits.
Useful evidence may include a documented dataset, baseline comparison, model evaluation, error analysis, and a clear record of the student's own decisions.
The evidence an application reads is what the student understood, completed, and can explain.
Which sources were reviewed?
Catalog reviewed: 2026-09-30
Questions parents search before choosing this course
Is High School AI Assistants: Build, Test, and Explain a good fit for high school students in Grades 9-12?
High School AI Assistants: Build, Test, and Explain is a good fit for students in grades 9-12 who are interested in failure modes of multi-agent systems and statistics for AI evaluation. CIT offers online or in-person lessons in Apgujeong, Gangnam, Seoul, in one-to-one or small-group formats. Students make baseline comparisons with statistical notes, a read-only MCP prototype, and a research report with a reproducible repository.
Can my child take High School AI Assistants: Build, Test, and Explain online or in person, one-to-one or in a small group?
Yes. CIT offers online and in-person lessons at its Apgujeong academy in Gangnam, Seoul, with one-to-one and small-group options. A readiness consultation confirms the available format and starting point for the course.
Does my child need prior subject knowledge or coding experience for High School AI Assistants: Build, Test, and Explain?
Course placement follows current subject and coding readiness. Students should be ready to document sources, methods, and limits. Advanced tools are introduced after a clear baseline.
What will my child make or practice in High School AI Assistants: Build, Test, and Explain?
The main evidence is baseline comparisons with statistical notes, a read-only MCP prototype, and a research report with a reproducible repository. Students also document decisions, tests, feedback, and limits in age-appropriate language.
How can a student describe work from High School AI Assistants: Build, Test, and Explain in a college application?
The student sets their own question, then designs and tests a feature, model, interface, or solution of their own. In an application or interview, the student separates the material they drew on from their own decisions, results, failed attempts, revisions, and limits. Useful evidence may include a documented dataset, baseline comparison, model evaluation, error analysis, and a clear record of the student's own decisions.
How are the schedule and tuition for High School AI Assistants: Build, Test, and Explain determined?
CIT confirms the student's readiness, goal, location, class size, and current availability before recommending a course plan. The consultation and level check are free; tuition is explained before enrollment.
When should a student start?
There is no fixed intake month. CIT reviews the student's current school term, readiness, and available hours, then names the point in the course where they should begin.
The teachers are always attentive and considerate, so we feel comfortable trusting them with our child.
Where else parents check CIT
Choose the course after a readiness check
CIT can compare this course with nearby options by age, subject, and current preparation.