待翻譯：Scaling cloud migrations with agentic AI on Amazon Bedrock AgentCore

AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。

Scaling cloud migrations with agentic AI on Amazon Bedrock AgentCore starts with recognizing where large-scale migrations break down. Discovery consumes weeks per application. Engineers write infrastructure code from scratch for each workload. Post-migration operations devolve into reactive firefighting. Multiply those bottlenecks across over 300 applications and a fixed fiscal year deadline, and migration programs struggle to keep pace. The multi-agent framework in this post reduced infrastructure as code (IaC) development time from 3–4 weeks per application to minutes across a over 300 application portfolio. This result is based on internal project tracking data. AWS Professional Services builds a suite of purpose-built AI agents to address these bottlenecks across the migration lifecycle, from automated discovery to proactive post-migration operations. The agents use the Strands Agents SDK and run on Amazon Bedrock AgentCore, a platform to build, connect, and optimize agents at scale, with any framework or model. In this post, you explore the architecture of a multi-agent orchestration framework that accelerates enterprise cloud migrations end-to-end. You also see the code that defines an agent, connects it to its tools, and applies responsible AI controls. The framework includes four agents: The Intake Agent for automated discovery. The IaC Agent that generates infrastructure as coded (IaC) adhering to your security best practices. The Migration Intelligence and Governance Agent for portfolio-wide reporting and well-architected assessments. The Site Reliability Engineering (SRE) Agent for proactive operations. To follow along, you need an AWS account with access to Amazon Bedrock AgentCore and to Amazon Bedrock foundation models (FM). You also need familiarity with the Strands Agents SDK and Model Context Protocol (MCP) server patterns, plus the IaC tooling used by your organization. Why migration programs need a different approach Three core bottlenecks emerge consistently across large enterprise data center exit migration programs. Manual intake overhead: Most application migrations begin with discovery: understanding the on-premises architecture, inventory, dependencies, and intake questionnaires. Manual discovery consumes weeks per application. Across over 300 applications, this bottleneck alone threatens an aggressive migration timeline. Redundant infrastructure development: When engineers define a target architecture, they write IaC to provision the AWS infrastructure. Without automation, writing IaC from scratch for each application typically requires 3–4 weeks per application. Across a over 300 application portfolio, that translates to years of engineering effort. Reactive post-migration operations: After migration, teams rely on manual monitoring and reactive response. Without proactive intelligence to detect performance degradation or automatically remediate issues, ongoing operational drag compounds over time. These three bottlenecks span the migration lifecycle. Addressing them requires shifting repetitive work to AI agents while humans retain decision authority. Architecture overview A multi-agent orchestration framework addresses each bottleneck with purpose-built agent capabilities. The architecture spans the migration lifecycle from on-premises discovery to post-migration operations. The framework applies security at each phase of that lifecycle. The following diagram shows how the agents, tools, and AWS services connect. Figure 1: How the agents connect across the migration and operations journeys through Model Context Protocol tool calling The framework organizes agents into two journeys. The migration journey agents handle discovery through deployment. The operations journey agent handles post-migration monitoring. Migration journey agents: Intake Agent (Phase 1): Automates application discovery and target state architecture definition with dependency mappings. IaC Agent (Phase 2): Generates IaC code adhering to your security best practices and standards. Migration Intelligence and Governance Agent: Provides automated portfolio reporting, well-architected assessments, and migration governance across Jira, Confluence, and Webex. Operations journey agents: SRE Agent (Phase 3): Provides proactive post-migration monitoring and automated remediation. AWS managed services complement the custom agents: AWS Database Migration Service (AWS DMS): Generative AI-assisted schema conversion and automated cutover for database migration. AWS Transform: Application-specific modernization for legacy code. How the components connect This section describes how the framework components interact at runtime. Each agent is a Strands agent, defined by a foundation model, a system prompt, and a set of tools. Amazon Bedrock AgentCore runtime hosts them in a serverless environment with session isolation and multi-agent orchestration. Amazon Bedrock foundation models power the reasoning that interprets documents, generates code, and drives multi-step workflows. For model availability by AWS Region, refer to Supported foundation models in Amazon Bedrock. Each agent calls MCP tools scoped to its function through AgentCore Gateway, a capability of Amazon Bedrock AgentCore, which converts your APIs, AWS Lambda functions, and existing services into MCP-compatible tools. AgentCore Identity, a capability of Amazon Bedrock AgentCore, authenticates each call through scoped AWS Identity and Access Management (IAM) roles and your identity provider. Amazon Bedrock AgentCore memory stores agent session state and shared context. Agents use this shared context to persist outputs and track migration progress across over 300 applications. When the Intake Agent completes discovery, it writes the target architecture and dependency mappings to AgentCore memory. The IaC Agent reads this shared context to begin code generation without manual handoff. Defining an agent in code The following Python example defines the IaC Agent and prepares it for Amazon Bedrock AgentCore runtime. The agent reaches your MCP tools through AgentCore Gateway, and it calls a foundation model through Amazon Bedrock with an Amazon Bedrock Guardrails policy attached. import logging import os from bedrock_agentcore.runtime import BedrockAgentCoreApp from strands import Agent from strands.models import BedrockModel from strands.tools.mcp import MCPClient from strands.tools.mcp.mcp_types import MCPClientCredentials logger = logging.getLogger(name) app = BedrockAgentCoreApp() REGION = os.environ["AWS_REGION"] # url+auth lets the SDK run the client_credentials grant and re-mint the # token on expiry. A statically captured bearer token would go stale. gateway = MCPClient( url=os.environ["GATEWAY_MCP_URL"], auth=MCPClientCredentials( client_id=os.environ["GATEWAY_CLIENT_ID"], client_secret=get_secret("gateway/client_secret"), scopes=[os.environ["GATEWAY_SCOPE"]], ), ) model = BedrockModel( model_id=os.environ["MODEL_ID"], region_name=REGION, guardrail_id=os.environ["GUARDRAIL_ID"], guardrail_version=os.environ.get("GUARDRAIL_VERSION", "1"), guardrail_trace="enabled", ) @app.entrypoint def invoke(payload, context): prompt = (payload.get("prompt") or "").strip() if not prompt: return {"status": "error", "error": "missing required field: prompt"} try: # tools=[gateway]: SDK owns the connection lifecycle and paginates # tool discovery, which list_tools_sync() alone does not. agent = Agent( model=model, system_prompt=IAC_AGENT_PROMPT, tools=[gateway], ) result = agent(prompt) if result.stop_reason == "guardrail_intervened": logger.warning("guardrail blocked request, session_id=%s", getattr(context, "session_id", None)) return {"status": "blocked_by_guardrail"} return {"status": "ok", "iac": str(result)} except Exception as e: logger.exception("invocation failed, session_id=%s", getattr(context, "session_id", None)) return {"status": "error", "error": str(e)} if name == "main": app.run() The entrypoint returns generated IaC to the caller, and AgentCore runtime handles session isolation and scaling. For deployable end-to-end examples, see the Amazon Bedrock AgentCore samples repository and the Strands Agents samples repository on GitHub. For the deployment steps, refer to Getting started with AgentCore runtime. Phase 1: Intake Agent for automated discovery The Intake Agent automates the most time-consuming first step of migration: understanding what exists on-premises and defining where it goes on AWS. The agent ingests on-premises architecture documentation, application inventory lists, intake questionnaires, and dependency maps. It then produces a target AWS architecture with a recommended migration pattern, resource sizing specifications, and a compliance validation report. The Intake Agent addresses the manual intake bottleneck. The output feeds directly into the IaC Agent, creating an automated handoff from discovery to infrastructure provisioning. Phase 2: IaC Agent for automated infrastructure code generation AWS Professional Services deployed the IaC Agent first in the portfolio, and it delivers the most immediately measurable impact. It generates IaC code adhering to your security best practices and standards. How it works The agent workflow proceeds through five steps: Step 1: Ingest the steering document. The agent reads the steering document from the wave team. It extracts deployment scope, compliance constraints, and Security Office-approved wave-specific overrides. Step 2: Interpret the target state architecture diagram. Using the Intake Agent’s output, the IaC Agent identifies infrastructure components, their relationships, and dependencies. Step 3: Generate IaC. Based on this interpretation, the agent generates IaC using your defined and established patterns. It populates configurations with wave-specific parameters and configures remote state management. It then applies mandatory tagging and adds monitoring configurations required by organizational standards. Step 4: Validate through Policy in Amazon Bedrock AgentCore. Before execution, Policy in AgentCore evaluates each tool call against Cedar rules. It calculates the scope of potential change, checks dependency conflicts with concurrent waves, and confirms compliance window validity. Step 5: Execute and report. The centralized execution plane triggers the IaC, monitors deployment, and reports outcomes through AgentCore Observability, a capability of Amazon Bedrock AgentCore. Post-deployment validation runs automatically and compliance metrics update in real time. Custom MCP tools: The security foundation Each action passes through custom MCP tools exposed by Amazon Bedrock AgentCore Gateway and governed by AgentCore Identity and Policy in AgentCore. AgentCore Identity authenticates each agent action through scoped IAM roles with least-privilege access. The framework validates inputs against defined schemas and rejects malformed inputs at the boundary. No credentials or sensitive values pass through agent context, because AgentCore Identity resolves secrets at runtime from a centralized credential provider. AgentCore Observability and AWS CloudTrail write each agent action to an immutable, centralized audit trail. Policy in AgentCore enforces Cedar rules that help prevent a single operation from affecting more than a defined threshold. IaC generation based on your patterns The IaC Agent generates infrastructure code based on your defined and established patterns. These patterns encode organizational standards into reusable constructs. They include network configurations, security group rules, IAM roles, Amazon CloudWatch alarms, Amazon Elastic Compute Cloud (Amazon EC2) configurations, Amazon Virtual Private Cloud (Amazon VPC) layouts, and mandatory tagging. This approach provides consistency across waves, speed for wave teams who don’t write infrastructure code [truncated for AI cost control]