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 Software: Step-by-Step Assistants
Grades 9-12: software architecture for AI apps, fallback...
- Free consultation and level check
- Apgujeong classroom or online
- One-to-one or small group
- Registered academy no. 11882
Is High School AI Software: Step-by-Step Assistants a good fit for high school students in Grades 9-12?
High School AI Software: Step-by-Step Assistants is a good fit for students in grades 9-12 who are interested in software architecture for AI apps and fallback paths for LLM output. CIT offers online or in-person lessons in Apgujeong, Gangnam, Seoul, in one-to-one or small-group formats. Students make a non-AI baseline app with tests, a bounded agent with an evaluation set, and a capstone evidence pack with a demo.
Students define a user problem, requirements, and acceptance tests, then finish and defend an app that works without AI, built in tutor-prepared repositories with de-identified data, before any model is added. The LLM then enters as a replaceable component with schema checks, limited retries, and a fallback path, followed by tools with separate read and write permissions and a bounded agent with budgets and stop conditions. A 12 to 20 case evaluation run repeatedly, prompt-injection tests, and user testing lead to a go, revise, hold, or stop recommendation that the student defends orally. 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)
My child found the AI classes interesting and stayed with them. It made for a worthwhile school break. Thank you for teaching so attentively.
- Age group
- Grades 9-12
- Academic subject
- AI & Data, Computer Science & Coding, Engineering & RoboticsBrowse 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
- Learning studioA structured learning studio with goals, deliverables, and follow-up work is available. Tutors confirm supporting materials before delivery.
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 software architecture for AI apps or fallback paths for LLM output keep making you ask why, High School AI Software: Step-by-Step Assistants lets you investigate the question with evidence, then build and defend an extension of your own.
Which interests suggest this course?
- software architecture for AI apps
- fallback paths for LLM output
- agent permissions and prompt injection
What does the student finish?A non-AI baseline app with tests, a bounded agent with an evaluation set, and a capstone evidence pack with a demo.
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 user problem into requirements and acceptance tests and build a baseline app that works without AI first.
- Validate LLM output against a schema and connect it as a replaceable part with timeouts, retries, and a fallback.
- Give each tool read or write permissions and approval steps, and build an agent loop with budgets and stop conditions.
- Defend a go, revise, hold, or stop decision using repeated evaluations and a threat model.
How does the course progress?
- 1System and Product Foundations
Compare rules, learned models, and generative models, pick the lowest autonomy level each feature needs, and define requirements and states.
- 2Connected Software Architecture
Split modules, define interface and JSON contracts, choose storage, and defend a working non-AI app before AI is added.
- 3The LLM as a Controlled Component
Add structured output, validation, timeouts, retries, and versioned prompts to LLM calls, with a fallback when the model fails.
- 4Tools, Retrieval, State, and Workflows
Build typed tool contracts, read and write permissions, a bounded agent loop, sourced retrieval, and human approval gates.
- 5Evaluation, Security, and Open Source
Run 12 to 20 cases repeatedly, classify failures from traces, test prompt-injection defenses, and evaluate an open-source repository.
- 6Capstone Validation and Launch Decision
User testing, a one-variable improvement, logging, and rollback plans lead to an evidence pack and an oral launch decision.
What counts as useful evidence?
A non-AI baseline app with tests, a bounded agent with an evaluation set, and a capstone evidence pack with a demo.
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?
- CSTA · 2026 PK-12 Computer Science Standards
- CSTA · AI as Part of Computer Science
- UNESCO · AI Competency Framework for Students
Catalog reviewed: 2026-09-30
Questions parents search before choosing this course
Is High School AI Software: Step-by-Step Assistants a good fit for high school students in Grades 9-12?
High School AI Software: Step-by-Step Assistants is a good fit for students in grades 9-12 who are interested in software architecture for AI apps and fallback paths for LLM output. CIT offers online or in-person lessons in Apgujeong, Gangnam, Seoul, in one-to-one or small-group formats. Students make a non-AI baseline app with tests, a bounded agent with an evaluation set, and a capstone evidence pack with a demo.
Can my child take High School AI Software: Step-by-Step Assistants 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 Software: Step-by-Step Assistants?
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 Software: Step-by-Step Assistants?
The main evidence is a non-AI baseline app with tests, a bounded agent with an evaluation set, and a capstone evidence pack with a demo. Students also document decisions, tests, feedback, and limits in age-appropriate language.
How can a student describe work from High School AI Software: Step-by-Step Assistants 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 Software: Step-by-Step Assistants 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.
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.
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.