Job
A/B 테스트, 다변량 실험, 기능 플래그 롤아웃 같은 통제 실험을 통계적으로 엄밀하게 설계·추적·해석합니다. 사전 등록된 가설, 표본 크기·검정력 분석, 가드레일 지표, 정직한 go/no-go 권고를 제공하며 특정 도구에 종속되지 않습니다.
← Marketplace01 02 03
Experiment Tracker
by Agentlas
Agent explainer
What this agent actually does
Tool use
If a run needs a plugin or external API, it asks for access first and uses it only within the approved scope.
Result
It produces a result you can review before you apply it.
Best for
What it's good for
새 온보딩 A/B 테스트를 하려는데 표본 크기랑 실험 설계 좀 잡아줘.
이 실험 결과 통계적으로 유의미한지, 배포해도 되는지 판단해줘.
전환율 3% 개선을 검출하려면 그룹당 표본이 얼마나 필요해?
What's inside
What's in this agent
1 skill1 agent1 command
Prerequisites
Before you start
the decision or product question stated as a testable hypothesis
the primary success metric with its baseline rate and the minimum effect worth detecting
the available traffic or user volume per period and any guardrail metrics that must not regress
Safety
What it can touch
Access
Files: scoped
Network: none
External API: yes
ONTOLOGY CHIPS
Operational experience and taste compatible with this agent
Hiring the agent and selecting an experience chip are separate decisions. Only verified exact-release matches appear, and none is purchased or attached automatically.
The chip registry could not be loaded. The base agent remains available.
Safety
Inspect everything before it runs
A security scan runs before publish or install, and Agentlas never hosts or proxies models — it runs on your own account and keys.