Adaptive-depth requirements analysis for AIDLC Inception. Simple features produce a 1-paragraph brief; complex features produce structured REQ-001/REQ-002 functional and…
AWS Pricing과 Cost Explorer를 MCP로 조회하여 agent별 비용 귀속을 집계하고 예산 alert을 발행하며, 사용 패턴이 정당하면 Opus → Sonnet → Haiku 모델 다운그레이드를 권고한다.
Agent 또는 skill의 프로덕션 배포를 canary 1% → 10% → 50% → 100% 4단계로 자동 진행한다. 각 단계는 continuous-eval 통과와 SLO 준수를 gate로 하며 circuit breaker가 SLO 위반을 감지하면 즉시 이전 단계로 자동 롤백한다. 100% 승격은 사람 승인이 필수다.
Inception 아티팩트(requirements, user-stories, workflow-plan)를 입력으로 받아 agentic 시스템의 컴포넌트 경계·인터페이스 계약·데이터 모델을 설계하고 `.omao/plans/construction/design.md`를 생성한다.
Strategic workflow planning for AIDLC Phase 1 close-out. Chooses sequential / parallel-units / iterative execution mode via a decision tree, maps stories to units, and defines…
AIDLC Inception 시작 시 자유 형식 발화 대신 구조화된 템플릿으로 프로젝트 정보를 수집한다. project-info 템플릿과 requirements 템플릿을 순차 생성하여 후속 workspace-detection·requirements-analysis·user-stories skill이 소비할 단일 진실원을…
Detect whether the workspace is greenfield (new project) or brownfield (existing codebase). For brownfield, trigger reverse-engineering to recover implicit requirements.
Build AI agents with Strands Agents SDK. Use when developing model-agnostic agents, implementing ReAct patterns, creating multi-agent systems, or building production agents on…
Expert AWS solution architecture for startups focusing on serverless, scalable, and cost-effective cloud infrastructure with modern DevOps practices and infrastructure-as-code
Expert AWS solution architecture for startups focusing on serverless, scalable, and cost-effective cloud infrastructure with modern DevOps practices and infrastructure-as-code
Detect accidentally committed secrets, credentials, and sensitive information in code.
Lets an agent supervisor spawn and steer isolated terminal-based worker agents with explicit handoff, assign, and message patterns.
Build AI agents with AWS Bedrock AgentCore. Use when developing agents on AWS infrastructure, creating tool-use patterns, implementing agent orchestration, or integrating with…
Run concurrent scripted conversations against a target agent to measure whether it stays on task, responds correctly, and holds up in repeatable test cases.