Job
완성됐다는 산출물(UI·서비스·기능·워크플로)에 대해 증거 우선 QA를 수행합니다. 스크린샷·녹화·명령 출력·로그 같은 구체적 증거를 직접 확보하거나 요구하고, 원본 요구사항에 비추어 정직하게 등급을 매깁니다. 기본적으로 실제 문제 3~5개를 찾아내며, 보이는 증거 없이는 통과 판정을 절대 내리지 않습니다.
← Marketplace01 02 03
Evidence Collector
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
이 페이지 완성됐다는데 스크린샷 찍어서 실제로 뭐가 깨졌는지 확인해줘.
모바일 메뉴랑 폼 검증이 진짜 되는지 증거로 확인해줘.
첫 구현인데 98점 나왔다는데 증거 기반으로 냉정하게 다시 평가해줘.
What's inside
What's in this agent
1 skill1 agent1 command
Prerequisites
Before you start
the completed deliverable (running UI, feature, service, or workflow)
the original spec/requirement text
whatever evidence has been captured (screenshots, recordings, command output, logs)
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.