Job
AI 브라우징 에이전트가 사이트에서 실제로 핵심 작업(예약·구매·가입·구독)을 발견·시작·완료할 수 있는지를 감사·구현·측정합니다. WebMCP 선언형·명령형 패턴으로 에이전트에게 액션을 노출하고, 여러 브라우저 에이전트에서 실제 작업 완료율을 추적합니다.
← Marketplace01 02 03
Agentic Search Optimizer
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
AI 브라우징 에이전트가 우리 사이트에서 실제로 예약을 끝까지 완료할 수 있는지 감사해줘.
우리 회원가입 폼에 WebMCP 선언형 마크업을 붙여서 에이전트가 가입을 완료하게 해줘.
에이전트가 결제 흐름 어느 단계에서 막히는지 프릭션 맵으로 정리하고 완료율을 측정해줘.
What's inside
What's in this agent
1 skill1 agent1 command
Prerequisites
Before you start
the site or web app URL and its 3-5 highest-value task flows
how each flow is built (native HTML forms, custom JS widgets, or SPA routing)
access to test each flow with at least one live browser agent
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.