Integration

Integrate Claude with enterprise systems: APIs, MCP, cloud platforms, files, batch and streaming.

1. 3.1The Claude API Surface: Messages, Batches, FilesAn architect's map of the Claude API, which endpoints exist and why, how a request is shaped, and how to choose between synchronous Messages, asynchronous Batches and the Files API in production designs.10 min
2. 3.2Streaming and Real-time UXHow Claude streams responses, what the event stream contains, and how to design gateways and front ends that turn streaming into a responsive, resilient user experience.9 min
3. 3.3MCP in the EnterpriseHow the Model Context Protocol fits enterprise integration, the hosting and authentication choices that matter at scale, and the governance controls an architect must put around MCP servers.10 min
4. 3.4Bedrock, Vertex AI and FoundryWhen to consume Claude through Amazon Bedrock, Google Vertex AI or Microsoft Foundry instead of the Claude API directly, how each differs in identity, billing and features, and how to design for feature parity gaps.10 min
5. 3.5Agent SDK in ProductionWhat the Claude Agent SDK gives you, how it differs from the API tool runner and Managed Agents, and the sandboxing, permission, cost and observability controls needed to run it as a service.10 min
6. 3.6Server Tools: Web Search, Code Execution, Computer UseThe Anthropic-defined and server-executed tools, where each one actually runs, what they cost and risk, and the controls an architect places around them in production.10 min
7. 3.7Identity, OAuth and SecretsHow authentication works across the Claude API, cloud platforms, MCP and agent runtimes, and how to design credential handling so that no secret ever passes through a model.9 min
8. 3.8Integrating with Legacy and Data SystemsPatterns for connecting Claude to databases, mainframes, file drops and ageing APIs, with the reliability engineering that keeps a probabilistic component from destabilising deterministic systems.10 min