AgentCore Operations Review
ПродвинутыйopsМинимальный контекст: 64K
Reviews Amazon Bedrock AgentCore runtime, memory, identity, gateway, policy, browser, and code-interpreter operations before deployment. Separates read-only, billable, mutating, and destructive actions and produces scoped enablement, observability, rollback, and cost-control recommendations.
Варианты использования
- Reviewing AgentCore runtime and gateway rollout plans
- Scoping memory, identity, browser, and interpreter tools
- Separating billable and destructive operations
- Designing rollback and audit controls for agent infrastructure
Пример промпта
Review this Amazon Bedrock AgentCore deployment and operations plan. Context: [architecture, regions, environments, IAM roles, expected traffic] Enabled primitives: [runtime, memory, identity, gateway, policy, browser, code_interpreter] Return: 1. A primitive-by-primitive necessity review. 2. Read-only, billable, mutating, and destructive operation classes. 3. Least-privilege IAM and identity boundaries. 4. Session lifecycle, timeout, and cost controls. 5. Observability signals and incident runbooks. 6. A staged rollout and tested rollback plan.
Рекомендуемые модели
Совместимые инструменты
claude-codecursorkirogemini-cliany
Модальности
Вход: text, code
→Выход: text
Похожие Skills
Автор
OpenModels Community
Издатель
Проверенный источникOpenModels Community
Адаптировано по указанному источнику