Show HN: OQP – A verification protocol for AI agents
hackernews
|
|
{'이벤트': '📰', '머신러닝/연구': '📰', '하드웨어/반도체': '📰', '취약점/보안': '📰', '기타 AI': '📰', 'AI 딜': '📰', 'AI 모델': '📰', 'AI 서비스': '📰', 'discount': '📰', 'news': '📰', 'review': '📰', 'tip': '📰'} AI 서비스
#ai agents
#autonomous code
#oqp
#standard
#verification
#code deployment
#protocol
요약
AI 에이전트가 자율적으로 코드를 작성하고 배포할 때 비즈니스 요구사항 충족 여부를 검증할 표준이 없는 문제를 해결하기 위해 OQP 프로토콜이 개발되었습니다. OQP는 에이전트의 검증 기능 파악, 워크플로우 규칙 확인, 검증 실행, 변경 사항 위험 평가를 위한 4가지 핵심 엔드포인트를 정의하며 MCP와 호환됩니다. 이 프로토콜은 REST API를 위한 OpenAPI처럼 AI 에이전트 소프트웨어 검증의 표준 역할을 하며, XBOSoft와 W3C JSON-LD 워킹 그룹 전문가 등이 초기 기여자로 참여하고 있습니다.
왜 중요한가
본문
As AI agents autonomously write and deploy code, there's no standard for verifying that what they shipped actually satisfies business requirements. OQP is an attempt to define that standard.<p>It's MCP-compatible and defines four core endpoints:
- GET /capabilities — what can this agent verify?
- GET /context/workflows — what are the business rules for this workflow?
- POST /verification/execute — run a verification workflow
- POST /verification/assess-risk — what is the risk of this change?</p><p>The analogy we keep coming back to: what OpenAPI did for REST APIs, OQP does for agentic software verification.</p><p>Early contributors include Philip Lew (XBOSoft) and Benjamin Young (W3C JSON-LD Working Group). Looking for feedback from engineers building on top of MCP, agent orchestration frameworks, or anyone who has felt the pain of "the agent shipped something wrong and we had no way to catch it."</p><p>Repo: github.com/OranproAi/open-qa-protocol</p>
- GET /capabilities — what can this agent verify?
- GET /context/workflows — what are the business rules for this workflow?
- POST /verification/execute — run a verification workflow
- POST /verification/assess-risk — what is the risk of this change?</p><p>The analogy we keep coming back to: what OpenAPI did for REST APIs, OQP does for agentic software verification.</p><p>Early contributors include Philip Lew (XBOSoft) and Benjamin Young (W3C JSON-LD Working Group). Looking for feedback from engineers building on top of MCP, agent orchestration frameworks, or anyone who has felt the pain of "the agent shipped something wrong and we had no way to catch it."</p><p>Repo: github.com/OranproAi/open-qa-protocol</p>