NEWS · COMPANIES · #1794
Postman runs Agent Mode for 40 million developers on Amazon Bedrock
Postman describes how its Agent Mode — an AI-native interface for API testing, documentation, discovery, and implementation — is run in production for ~40 million developers using Amazon Bedrock. The post details architectural patterns (controlling tool sprawl, schema-based reads, treating context as the bottleneck), operational choices (geographically scoped cross-Region inference, model-dependent zero-data-retention, multi-tier prompt caching), human approval before state changes, and use of Amazon Bedrock Guardrails to redact PII; it also explains narrowing >170 tools to ~15 via a vector database of tool embeddings to limit the model's tool surface.
KEY POINTS
- Postman describes how its Agent Mode — an AI-native interface for API testing, documentation, discovery, and implementation — is run in production for ~40 million developers using Amazon Bedrock.
- The post details architectural patterns (controlling tool sprawl, schema-based reads, treating context as the bottleneck), operational choices (geographically scoped cross-Region inference, model-dependent zero-data-retention, multi-tier prompt caching), human approval before state changes, and use of Amazon Bedrock Guardrails to redact PII; it also explains narrowing >170 tools to ~15 via a vector database of tool embeddings to limit the model's tool surface.
- Provides practical, production-proven patterns for scaling and operating AI agents at global scale while limiting tool surface, protecting data, and meeting latency needs via managed foundation-model infrastructure.
WHY IT MATTERS
Provides practical, production-proven patterns for scaling and operating AI agents at global scale while limiting tool surface, protecting data, and meeting latency needs via managed foundation-model infrastructure.