AACE AI SW
👤ParticipantACE AI SW
DAY 06 · MONDAY · PROJECT KICKOFF

Decide what to build,
and build it all the way
the AI Native way

Week 2's team project starts. In real service development, the most important thing isn't code but the order Why → What → How. Set the problem and scope from a founder's point of view, and design a 5-day sprint with gstack's Think → Plan → Build → Review → Test → Ship → Reflect sequence and AI Native development.

Thanks to AI, "how to build it" has become very fast. So if you get "what to build and why" wrong, you just build the wrong product faster.

HTML Presentation

Day 6 Slides · Real Service Development

Use the arrow buttons or keyboard arrow keys (←/→) to move. Press the button (or the N key) to open the lecture notes for each slide.

ACE AI SW Startup Training · Day 6 · Week 2 Kickoff

Build the Right Thing,
then Build it Right.

People choose the right problem; people and AI together build it fast and correctly. Today we draw the full map of real service development and kick off the team project.

① Choose the right thingPeople · Why / What② Build it rightPeople + AI · How
01 · WhyWhose problem, and what problem
02 · WhatWhat exactly to build this time
03 · HowHow to build it with the gstack sequence
04 · AI NativeHow people and AI split the work
Opening question

Why do services fail?
Not "couldn't build it" but "nobody wanted it"

A common start

  • "It'd be cool to build this app with AI"
  • Write a feature list first
  • Draw screens first and pick a tech stack
  • Users are "everyone"

A start that survives

  • "Who struggles, when, and because of what?"
  • Observe how that person copes today
  • Start with the single narrowest user
  • Define success in numbers
In analyses of startup failure, "no market need" is always a top cause. AI speeds up building — and also speeds you up in the wrong direction.
Analogy · Market stalls

Not the best-made stall, but the stall where it's needed survives

Umbrella stall in the dry season (Harmattan)Good umbrellas · nice stall · 0 customers"We can build it" ≠ "they want it"Water stall at a busy bus stopBUS PARKPlain water · small stall · a queue of customers"Who needs what, and when" comes first
Golden circle for products

Inside out: Why → What → How

Why · why build itWhose problem does it solve, and what problem? What evidence shows this problem is real? → PROJECT_BRIEF
What · what to buildOne key action to prove in 5 days, Must/Should/Out scope, success metrics → SITE_SPEC · USER_FLOWS
How · how to build itTech stack, data, build order, AI tools and how to verify → DATA_MODEL · IMPLEMENTATION_PLAN
What matters most

The 5 most important things in a project

1Problem firstStart from users' pain, not features
2Narrow userNot "everyone" but the one who needs it most
3Small scopeAn MVP where one key action works end to end
4Verifiable criteriaNumbers and acceptance criteria, not "make it good"
5People judgeRecord accept/change/reject of AI suggestions and why
One flow that fully solves one user's problem is a stronger demo — and a better product — than 10 flashy features.
Why · validate the problem

Validate a problem with past behavior, not opinions

Bad questions (invite compliments)

  • "Would you use an app like this?"
  • "What do you think of this idea?"
  • "Would you pay for it?"

Future promises and compliments are not evidence.

Good questions (invite facts)

  • "When did you last have this problem? How did you solve it?"
  • "What took the longest in that process?"
  • "Have you already spent money or tried something to solve it?"
Strength of evidenceCompliment"Nice idea!"Future promise"I'd probably use it later"Recent experience"I wasted an hour on this problem last week"Current alternative"Right now we manage with a WhatsApp group"Spent money · time"I already paid to solve this"
Make something people want. — Y Combinator · Ask about their life, not your idea. — The Mom Test
What · define the MVP

Lock the What with 3 sentences · a scope table · success metrics

MUSTSave attendance · update statusWithout it, it's not a productSHOULDLate mark · filtersIf there's timeOUTLogin · location check · statsNot this time ✂
3-sentence definition① Purpose: students check in with a QR code and the teacher sees it live
② Student: search name → pick card → scan QR → checked in
③ Teacher: dashboard → live update → filter absentees
Does the whole team picture the same product?
Must / Should / OutMust: save attendance, update status
Should: late mark, filters
Out: login, location check, stats report
Can you say what you're NOT building?
Success metricsStudents check in within 30 seconds
Teacher sees absentees within 10 seconds
0 duplicate check-ins
Can you prove it with numbers in the demo?
MVP = thinnest complete slice

An MVP isn't the whole thing done roughly but one small, finished slice

Building layer by layer

Day 1: 10 empty screen shells
Day 2: all DB tables
Day 3: all APIs
Day 4: connecting... doesn't work
Day 5: no flow to demo

Slicing vertically

Slice 1: student check-in → save → shows on dashboard
         (screen, data and logic all included, working)
Slice 2: duplicate/expiry exception handling
Slice 3: filters · late mark
→ a working demo every day
Every evening you need at least one "flow you can demo right now". That's the rhythm of an MVP sprint.
Analogy · From skateboard to car

MVP = a vehicle you can ride at every stage

✗ Building parts first — nobody can ride until the last dayJust a wheel😞 UnusableWheels + body😞 UnusableCar without engine😞 UnusableCar😀 Finally!✓ MVP — rideable at every stage, learning from usersSkateboard😀 Can travelBicycle😀 Can travelOkada (motorbike)😀 Can travelCar😀 Can travel
How · the real development sequence

Real service development goes through 6 phases in order

THINKIdeaPLANPlanning docsBUILDBuildREVIEWReviewTESTtestSHIPReleaseREFLECTRetro
1 · Shape the idea3 sentences on problem · users · key action, scope table, success metricsTHINK
2 · Write planning docsSITE_SPEC · USER_FLOWS · DATA_MODEL · IMPLEMENTATION_PLAN · CONVERSATIONPLAN
3 · AI-based buildHave AI read the docs first, then build in small unitsBUILD · REVIEW
4 · Scenario testingNormal/exception scenarios, defect logs and re-checksTEST
5 · Chain improvements to docs & siteDocs first for changes (Spec-First), regression testsPLAN · REVIEW · TEST
6 · History · retro presentationDecision history, updated README, 5-minute talkSHIP · REFLECT
gstack · AI team in slash commands

gstack = a skill set that calls role-based AI reviewers with one command

Install in the project folder (for Codex)

git clone --single-branch --depth 1 \
  https://github.com/garrytan/gstack.git \
  .agents/skills/gstack
cd .agents/skills/gstack && ./setup --host codex

Needs Git and Bun (v1.0+) · Windows also needs Node.js. Installed in the .agents/skills folder you learned on Day 4.

Think in roles

  • CEO: /office-hours, /plan-ceo-review
  • Engineering lead: /plan-eng-review, /review
  • Designer: /design-consultation, /plan-design-review
  • QA: /qa-only, /investigate, /qa
  • Release: /document-release, /retro

Don't accept results as-is; record accept/change/reject and why in CONVERSATION.md.

gstack across the sequence

Each phase has set skills to call and docs to update

1 IdeaTHINK/office-hours · (optional) /plan-ceo-review Reduction→ PROJECT_BRIEF.md
2 Planning docsPLAN/plan-ceo-review · /plan-eng-review · /plan-design-review · /autoplan→ 5 planning docs, test plan
3 BuildBUILD · REVIEW/freeze · /design-consultation · (AI build) · /review→ website/, README, build log
4 TestingTEST/qa-only → /investigate → /qa · (optional) /benchmark→ TEST_PLAN.md, BUG_LOG.md
5 Change & improvePLAN · REVIEW · TEST/plan-eng-review → /review → /qa→ CHANGE_REQUEST.md, regression results
6 Retro & presentationSHIP · REFLECT/document-release · /retro→ README.md, RETROSPECTIVE.md
THINK · /office-hours

/office-hours: press your idea with 6 forcing questions before code

The resulting doc is long and broad. Compress only what the team agreed on into the 3-sentence definition and PROJECT_BRIEF.md.

My idea1. Demand realityDoes anyone really have this problem?2. Status quoHow do they cope now?3. Desperate specificityWho needs it most urgently?4. Narrowest wedgeWhat's the narrowest starting point?5. ObservationWhat did others miss?6. Future-fitWill it matter more in future?
PLAN · scope & engineering review

Lock the plan: scope with the CEO review, structure with the engineering review

Scope ExpansionDream bigSelective ExpansionAdd selectivelyHold ScopeHold scope ← defaultScope ReductionCore only ← tight schedule← scope growsscope shrinks →5-day projects go here

/plan-ceo-review · 4 modes

  • Scope Expansion — dream big
  • Selective Expansion — add selectively
  • Hold Scope — lock scope, maximum rigor ← default
  • Scope Reduction — keep only the core ← when the schedule is tight

/plan-eng-review

  • Lock data flow and architecture
  • Find exceptions and hidden assumptions (duplicates, expiry, save failure)
  • Test plan per requirement ID → Phase 4 /qa takes it over
  • List contradictions between docs in a table

Short on time? /autoplan: run reviews in one go and receive only the items people must decide

BUILD → REVIEW → TEST → SHIP → REFLECT

Build, doubt, prove, and finish with the docs matching

BuildLimit changes to website/ with /freeze → have AI read the docs first, then build in small unitsExactly the Day 4 way
Review/review — find bugs that break in real use even if CI passes, and builds that differ from the planCheck the diff even for auto-fixes
Test/qa-only report → /investigate cause → /qa fix and re-checkNo PASS for items not run
Ship · ReflectUpdate docs with /document-release → reflect with /retroDocs = site
Change request · Spec-First

Changes go docs first. Changing code first isn't Spec-First

CHANGE_REQUESTLog requestFix docsFirst!/plan-eng-reviewImpact analysisTeam approvalPeople decideBuild a minimal diffSmall/reviewFind bugs/qa regressionCheck again✗ Shortcut: change code first
  • First agree on what the request really means ("real time" = refresh? polling? WebSocket?)
  • Put the impact on screens · flows · data · permissions · tests · schedule in a table
  • Don't rebuild everything for one request — a small diff
  • If it's outside the goal, put it in the next version's backlog instead of building it
What is AI Native development?

AI Native = redesigning the process on the assumption you work with AI

AI-assisted (using it as a tool)

  • People decide and write everything; AI only autocompletes
  • Paste the error into chat when stuck
  • Context disappears when the chat ends
  • No review standard — "if it runs, OK"

AI Native (working as a teammate)

  • AI roles in every phase (planning review · build · QA · retro)
  • People focus on define → review → judge
  • Context stays in MD docs and logs for the next AI to pick up
  • Done is judged by the docs' acceptance criteria and test evidence
AI has made typing fast. So people's value shifts to defining what's right and judging whether results are right.
Analogy · Orchestra

AI Native = an AI orchestra conducted by people

AI-assisted — a player with a better instrumentPlays everything alone · AI autocompletesContext disappears when the chat endsAI Native — the person conducts, AI playsPerson = conductorPlanning reviewBuildCode reviewQADocumentEveryone reads the score (MD docs) together
AI Native team roles

Each team member gets decisions they own and a paired AI

PO · planningDecides Why/What, approves scope, judges change requestsAI: /office-hours · /plan-ceo-review
Design · UXDecides user flows, screen standards, accessibilityAI: /design-consultation · /plan-design-review
Dev leadDecides structure and data, approves and merges codeAI: Codex · Antigravity · /plan-eng-review · /review
QA · releaseJudges tests, prioritizes defects, prepares the demoAI: /qa-only · /qa · /document-release
  • Name one final approver of AI output for each role
  • No direct commits to main; feature branches + review
A day in an AI Native team

Daily rhythm: decide small, build small, show it every day

09:00Scrum · today's REQ09:30Plan request · approval10:00AI build13:00/review14:30/qa-only16:00Commit · log17:00Demo!
Small batchesOne REQ = one plan = one commit. Reject big diffs you can't review
Integrate dailyDon't keep branches separate for long; merge at least once a day
Demo dailyEvery evening, demo a flow that really works to the team and mentor
Evidence over demo

Record and show the reasons for your decisions, more than results

One CONVERSATION.md entry

## C-012 · Phase 4 · /qa-only
- Question: test 6 attendance scenarios
- Key finding: double click saves 2 records
- Team decision: accepted → fixed FR-003
- Rejected: "add login" suggestion → Out of scope
- Evidence: BUG-004, TEST-007 re-check PASS

5-minute talk structure

40sProblem50sUsers · solution120sCore demo60sJudgment · evidence30sRetro5 min total · the demo is longest

In the 1-minute judgment and evidence part, be sure to show at least one case where you rejected or changed an AI suggestion.

Week 2 · 5-day sprint

Week 2 sprint: 6 phases in 5 days

Day 6 · MonStart THINK · PLANValidate the problem, 3-sentence definition, scope table, roles, repo and gstack setup/office-hours
Day 7 · TuePLAN · mid-term talk5 planning docs, CEO and engineering reviews, test plan/autoplan
Day 8 · WedBUILD · REVIEWBuild and integrate the core vertical flow, code review/freeze · /review
Day 9 · ThuTEST · ITERATEPOC talk, scenario testing, apply feedback Spec-First/qa-only · /qa
Day 10 · FriSHIP · REFLECTUpdate docs, retro, final presentation/document-release · /retro
Day 6 mission

Today's outputs and kickoff talk

Output 1 · PROJECT_BRIEF
3-sentence definition + 3 pieces of interview evidence + /office-hours result summary
Output 2 · Scope · metrics
Must/Should/Out scope table + 2+ success metrics in numbers
Output 3 · Role chart
People × AI roles, final approvers, branch rules
Output 4 · Sprint setup
Repo, AGENTS.md, gstack install, 5-day backlog
  • 3-minute kickoff per team: definition → scope → metrics → roles → tomorrow's tasks
  • Write the team draft before opening AI
  • Don't put real personal data or secret keys in docs or code
  • Record the accept/change/reject reason for every AI result
Takeaway

People own Why and What,
people and AI do How together.

An AI Native developer isn't the fastest typist, but the person who picks the right problem, conducts the AI team and finishes with evidence.

PeopleWhy · WhatPeople + AIHowPeople choose · building is shared
Power to choosePick the real problem of a user who really needs it
Power to conductCall the right AI role for each phase and lock the scope
Responsibility to proveProve it's done with tests and records
1 / 24
LECTURE NOTE

Hands-on Lab

Today's Kickoff Lab Flow

See the detailed steps and done checklists for all 6 phases in the Project Day Detailed Lab Guide. Today we finish Phase 1 (idea) and start Phase 2 (planning docs).

STEP 01 · 60 min · WHY

Find the problem & interview

Brainstorm team ideas, pick one, and do 5-minute interviews with 3 users focused on past behavior.

INTERVIEW × 3
STEP 02 · 60 min · WHAT · Key

3 sentences · scope · metrics

Write the team draft first, check assumptions with /office-hours, then confirm the PROJECT_BRIEF.

PROJECT_BRIEF.md
STEP 03 · 60 min · HOW

Roles & sprint

Make a people × AI role chart, branch rules and a 5-day backlog, and install AGENTS.md and gstack in the repo.

TEAM.md · BACKLOG
STEP 04 · 40 min · SHARE

3-minute kickoff talk

Definition → scope (including Out) → metrics → roles → tomorrow's tasks. Cut scope with mentor feedback and record it.

CONVERSATION.md

gstack Command Cheat Sheet — when and why to call each

Don't accept any command's result as-is; apply it to the doc on the right with the team's judgment, then record it in CONVERSATION.md.

CommandStage · roleWhen to callWhere to apply the result
/office-hoursThink · CEO office hoursRight after the 3-sentence draft. Check assumptions with 6 questionsPROJECT_BRIEF.md (problem · users · scope)
/plan-ceo-reviewPlan · scope reviewAfter the SITE_SPEC draft. Hold Scope / Reduction for 5-day projectsScope table, SITE_SPEC feature list
/plan-eng-reviewPlan · engineering reviewAfter the 5 docs are done, and on change requests (Spec-First)DATA_MODEL, USER_FLOWS exceptions, test plan
/plan-design-reviewPlan · design review (optional)When detailing screen design with item-by-item scoresSITE_SPEC design principles
/autoplanPlan · run all reviews at once (optional)When short on time. Receive only items people must decideList of [Undecided] items
/freeze · /guardBuild · safety guardBefore building. Limit changes to one folderBuild log (allowed scope)
/design-consultationBuild · design system (optional)When there are no color, type or spacing standardsSITE_SPEC, README
/reviewReview · code reviewAfter the core flow works, and after building a changeBuild log, fix commits
/qa-only → /investigate → /qaTest · QAReport only → investigate root cause → fix · re-check · regressionTEST_PLAN.md, BUG_LOG.md
/document-releaseShip · update docsBefore the final talk. Match the docs to the final codeREADME.md, the 5 planning docs
/retroReflect · retroAt the end of the sprintRETROSPECTIVE.md, talk retro

Kickoff Template Kit — copy and use right away

Copy each block with its Copy button and save it as a file in your team repo. Change the [bracketed] parts for your team.

WHY · WHAT

PROJECT_BRIEF.md

Today's key output. Every Phase 2 doc uses this file as input.

# [Service name] — PROJECT_BRIEF

## 1. 3-sentence definition
1. Purpose: a service that lets [who] do [what].
2. [User A]: [start] → [action] → [result]
3. [User B]: [start] → [action] → [result]

## 2. Evidence of the problem (interviews · observation)
| # | Person | Recent situation | How they solve it now | Pain point |
|---|---|---|---|---|
| I-1 | | | | |
| I-2 | | | | |
| I-3 | | | | |

## 3. Key user (the one who needs it most)
- Who:
- When · where:
- How they cope now (Status quo):

## 4. Scope
- Must (no demo without it):
- Should (if time allows):
- Out (not building this time + why):

## 5. Success metrics (in numbers)
- [User A] completes [action] within [N seconds/N steps]
- [Errors · duplicates] [N] or fewer

## 6. Risks and open questions
- [Assumption]:
- [Question]:

## 7. Applying AI review (/office-hours)
- Accepted:
- Changed:
- Rejected + why:
WHY

5-Minute User Interview Notes

The Mom Test principle: ask about the person's past behavior, not your idea.

# INTERVIEW I-[number]
- Person: [role, situation]  · Date: [ ]  · Interviewer: [ ]

## Questions (don't explain the idea)
1. When did you last face [problem situation]?
2. How did you solve it then? Can you walk me through it in order?
3. What took the longest or was most annoying in that process?
4. Have you tried any tools or methods to solve it?
5. What would change if that problem were solved?

## Notes (separate fact / interpretation)
- Fact (exactly as heard):
- Interpretation (what we think):
- Surprises (Observation & surprise):

## Verdict
- This person has the problem [a lot / a little / hardly]
- Evidence:
HOW · AI NATIVE

TEAM.md — people × AI role chart

Name one final approver for each role.

# TEAM — roles and teamwork rules

| Role | Person | Decisions owned | Paired AI |
|---|---|---|---|
| PO · planning | [name] | Why/What, scope approval, change requests | /office-hours, /plan-ceo-review |
| Design · UX | [name] | User flows, screen standards | /design-consultation, /plan-design-review |
| Dev lead | [name] | Structure · data, code merges | Codex · Antigravity, /plan-eng-review, /review |
| QA · release | [name] | Test verdicts, demo prep | /qa-only, /qa, /document-release |

## Teamwork rules
- No direct commits to main · feature/[REQ-ID]-[summary] branches
- One REQ = one plan = one commit
- Integrate at least once a day, demo every day at 17:00
- The approver checks the diff before merging AI output
- Record AI use in CONVERSATION.md

## Daily scrum (10 min)
- REQs finished yesterday / REQs to finish today / blockers
HOW

SPRINT_BACKLOG.md — 5-day plan

Arrange it so you have one more "demo-ready flow" every evening.

# SPRINT BACKLOG — Week 2

| Day | Phase | Goal (evening demo) | REQ / output | gstack | Owner |
|---|---|---|---|---|---|
| 6 Mon | Think · Plan | Brief confirmed, kickoff talk | PROJECT_BRIEF, TEAM | /office-hours | |
| 7 Tue | Plan | 5 docs + mid-term talk | SITE_SPEC, USER_FLOWS, DATA_MODEL, IMPLEMENTATION_PLAN | /autoplan | |
| 8 Wed | Build · Review | 1 core flow works | FR-001 ~ FR-00_ | /freeze, /review | |
| 9 Thu | Test · Iterate | POC talk, fix defects | TEST_PLAN, BUG_LOG, CHANGE_REQUEST | /qa-only, /qa | |
| 10 Fri | Ship · Reflect | Final presentation | README, RETROSPECTIVE | /document-release, /retro | |

## Definition of done (all REQs)
- Acceptance criteria (Given-When-Then) reproduce in the browser
- 0 console errors, mobile and PC layouts work
- Merged after review, logged in CONVERSATION.md
Log

CONVERSATION.md — decision history

Not a chat copy, but question → key suggestion → team decision → reason → evidence.

# CONVERSATION — AI conversations and decision history

## C-001 · Phase 1 · /office-hours
- Tool: gstack /office-hours (Codex)
- Question summary:
- Key suggestions · findings:
- Team decision: accept / change / reject
- Reason:
- Applied in: PROJECT_BRIEF.md §[ ]
- Evidence: [interview I-2, test ID, etc.]

## C-002 · Phase 2 · /plan-eng-review
- ...
ITERATE

CHANGE_REQUEST.md — change requests

Used from POC feedback (Day 9). Write it before the code.

# CR-001 — [change request in one sentence]

- Requested by · date:
- Reason (user value):
- Agreed real meaning: [e.g. real time = 5-second polling]
- Done criteria (Given-When-Then):

## Impact analysis
| Area | Impact | Docs/files to change |
|---|---|---|
| Screens | | |
| Flows | | |
| Data | | |
| Tests | | |
| Schedule | | |

## Decision
- This sprint / next version backlog
- Approver:
- Order: fix docs → /plan-eng-review → approval → code → /review → /qa
prompt

gstack · AI Prompts by Phase

Fill the [brackets] and paste into Codex or Antigravity chat.

[THINK] /office-hours
We want to build a service that solves [problem] for [users] in 5 days.
Ask us questions based on the 3-sentence definition and interview notes below,
and point out the riskiest assumption and the narrowest starting scope.
[paste 3-sentence definition + interview summary]

[PLAN] /plan-ceo-review
Review SITE_SPEC.md in Hold Scope mode. Suggest features that can't be demoed
in 5 days as candidates to move to Out, and tell us if any core value is missing.

[PLAN] /plan-eng-review
Review the 5 planning docs, list contradictions between docs, hidden assumptions and missing exception flows in a table,
and create a test plan for each requirement ID (FR-xxx).

[BUILD] Build request (Codex · Antigravity)
Read the 5 planning docs first and propose only the build plan for FR-[ ].
Show the files to create or change and why, and the acceptance criteria to check; build after approval.

[REVIEW] /review
Review the website/ code against SITE_SPEC's requirement IDs and acceptance criteria.
Look first for features not in the plan, and unhandled save failures and double clicks.

[TEST] /qa-only
Run the TEST_PLAN.md scenarios in the browser; don't fix any code,
and leave reproduction steps and screenshots for each defect.

[REFLECT] /retro
Using CONVERSATION.md and the work history, summarize what went well, what was hard,
cases where we rejected or changed AI suggestions, and 1 improvement for the next version.
Don't add achievements without evidence.
SHARE

3-Minute Kickoff Talk Script

For today's wrap-up talk. If the scope is big, the mentor cuts it down right there.

# Kickoff talk (3 min)

0:00 Problem (40s)
- "[Users] face [pain] in [situation]."
- One line of interview evidence: "I-2: ..."

0:40 What (60s)
- 3-sentence definition
- 3 Must / 3 Out (+ why they were cut)

1:40 Success metrics (30s)
- "[action] within [N seconds]", "0 [errors]"

2:10 How · team (30s)
- Role chart (people × AI), sprint goals for Days 7–10

2:40 Questions · requests (20s)
- 1 decision you want the mentor to confirm

10-Day Course Navigation

Click the buttons above to go to the Day 1–10 learning pages.

Learning Workspace

Startup · gstack · AI Native Videos & Day 6 AI Helper

Pick a reference video by topic on the left, and ask the AI chat on the right about Why·What·How, the gstack sequence and running an AI Native team.

Related YouTube VideosDay 6 recommended materials
  • Why · What · startup thinking
  • 1. Start with why — how great leaders inspire action (Simon Sinek)The Golden Circle · where Why → What → How begins EN
  • 2. Everything We Teach at YC in 10 MinutesY Combinator's key advice in 10 minutes EN
  • 3. How to Get and Test Startup Ideas — Michael SeibelFinding problems and testing ideas EN
  • 4. How to do customer interviews? — Rob Fitzpatrick (The Mom Test)Interview questions that get facts, not compliments EN
  • 5. What a Lean Startup MVP (minimum viable product) meansThe MVP concept, in Korean KR
  • MVP · scope
  • 6. Michael Seibel — How to Plan an MVPA YC partner on setting MVP scope EN
  • 7. How to Build An MVP (Y Combinator)Build small and launch fast EN
  • 8. How to succeed at startup MVP developmentStartup MVP development, part 1 KR
  • 9. Key strategies for MVP developmentStartup MVP development, part 2 KR
  • gstack dev sequence
  • 10. Analyzing gstack, the Claude Code plugin made by YC's CEOgstack structure and skills explained in Korean KR
  • 11. How to install gstack, the open-source hit in KoreaInstall and basic use KR
  • 12. YC CEO Open-Sourced His Entire Claude Code Setup — GStackIntro to the full gstack workflow EN
  • 13. I Tried Garry Tan’s GStack, Claude Code Skills That Run a StartupReal use from /office-hours to /qa EN
  • 14. gstack Explained: Is It Right for You?When to use it, and when not to EN
  • AI Native development
  • 15. Andrej Karpathy: Software Is Changing (Again)Software 3.0 · when natural language becomes the program EN
  • 16. What Is an AI-Native Engineering Team?Roles and ways of working in an AI Native team EN
  • 17. Maximizing AI-native development skills with GitHubAI-native development in practice (Korean) KR
  • 18. What INTENT.MD is and the AI-Native way of developing [KR/EN subs]AI Native development centered on intent docs KR
  • 19. Antigravity in practice & SDD AI developmentDoc (spec)-driven AI development (Day 4 review) KR
  • Tech reference (earlier Day 6 videos)
  • 20. Learn JavaScript - Full Course for Beginners (freeCodeCamp)Build basics · JavaScript EN
  • 21. WEB3 - Intro to Ajax (Opentutorials)Async communication concepts KR
  • 22. WEB3 - Using the Ajax fetch API (Opentutorials)Sending and receiving data with fetch KR
  • 23. JavaScript - Intro to jQuery Ajax (Opentutorials)jQuery Ajax reference KR

Videos are embedded public YouTube videos. If playback is restricted by the uploader, open them directly on YouTube. gstack and AI tools update often, so commands and screens in videos may differ from the current version.

Day 6 · Daily Feedback

Today's Course Satisfaction Survey

After Day 6 class, please answer a short survey. Your answers help us improve the next class and the course.

Open Day 6 SurveyJoin with the button or QR code
Day 6 Daily Feedback Survey QR codeSCAN TO OPENNigeria AI Training · Day 6