Prova 산출물

마케터를 위한 AI Builder Reality Check

첫 번째로 쓸모 있는 AI product slice를 만들 준비가 되었는지, 지금 시작하면 무엇이 먼저 깨질지 판단합니다.

이런 사람에게 적합Claude Code, Codex, v0, Replit 같은 도구를 쓰지만 꾸준히 ship하지 못하는 marketer · prototype은 있지만 실제 user path가 없는 operator · AI power user로 남을지 builder가 될지 결정하는 senior marketer · domain knowledge를 작은 product나 internal tool로 바꾸려는 consultant

영어 Prova로 계속하기

템플릿 항목

User and painful job
First useful slice
Proof that someone wants it
Current artifact or prototype
Weakest assumption
Data or workflow dependency
Review standard
Launch risk
Next 14-day build commitment

작성 예시

A marketer trying to build an internal campaign QA assistant.

아래 작성 예시는 영어로 유지합니다. Prova가 제출된 artifact를 영어로 검토하기 때문입니다.

약한 버전 vs 강한 버전

약한 버전

User: Marketing team
First useful slice: AI assistant for campaign QA
Proof: Everyone says QA is annoying
Weakest assumption: Need better prompts
Launch risk: Bugs
14-day commitment: Build MVP

User	Marketing team
First useful slice	AI assistant for campaign QA
Proof	Everyone says QA is annoying
Weakest assumption	Need better prompts
Launch risk	Bugs
14-day commitment	Build MVP

왜 부족한가

"Marketing team" is not a user.
"AI assistant" is too broad.
The proof is hearsay, not behavior.
The weakest assumption ignores source data, approval rules, and workflow ownership.
"Build MVP" is not a commitment.

강한 버전

User: Paid media manager checking campaign launch settings before client approval
First useful slice: A checklist reviewer that compares campaign setup notes against required client launch rules
Proof: Two managers already use a manual spreadsheet before every launch; mistakes still reach strategist review
Current artifact: One sample launch checklist, three anonymized campaign setup notes, and one failed QA example
Weakest assumption: The checklist rules are explicit enough for AI to evaluate without platform access
Data/workflow dependency: Client launch rules, platform screenshots, naming conventions, approval owner
Review standard: Flag missing budget, geo, naming, tracking, claim, and approval evidence; never approve launch automatically
Launch risk: False confidence before a client-visible campaign goes live
14-day commitment: Build a reviewer for one client and one platform, then test against five past launch packets

User	Paid media manager checking campaign launch settings before client approval
First useful slice	A checklist reviewer that compares campaign setup notes against required client launch rules
Proof	Two managers already use a manual spreadsheet before every launch; mistakes still reach strategist review
Current artifact	One sample launch checklist, three anonymized campaign setup notes, and one failed QA example
Weakest assumption	The checklist rules are explicit enough for AI to evaluate without platform access
Data/workflow dependency	Client launch rules, platform screenshots, naming conventions, approval owner
Review standard	Flag missing budget, geo, naming, tracking, claim, and approval evidence; never approve launch automatically
Launch risk	False confidence before a client-visible campaign goes live
14-day commitment	Build a reviewer for one client and one platform, then test against five past launch packets

왜 작동하는가

The user is specific.
The first slice is constrained.
Proof comes from an existing workflow.
Launch risk is clear.
The commitment creates evidence, not just more code.

일반 AI가 자주 놓치는 부분을 Prova가 검토합니다

Whether the first useful slice is still too large
Whether the user is real or imagined
Whether there is proof beyond personal excitement
Whether the artifact standard exists before the build starts
Whether the hard part is product judgment, data access, approval, or implementation
Whether the next step should be reality check, build brief, build plan, execution lane, or launch gate

다음 단계

내 버전에 대한 피드백이 필요하다면 Prova는 짧은 assessment로 시작합니다. 역할, 목표, 첫 audience에 맞춰 review standard를 맞춘 뒤 현재 작업에 맞는 sprint로 이동합니다.

Prova는 현재 영어로만 제공됩니다.

제출 전에는 고객명, 기밀 숫자, 팀이 training이나 coaching system에 저장되길 원하지 않는 정보를 제거하세요.

영어 Prova로 계속하기