How Postman runs Agent Mode for 40 million developers on Amazon Bedrock

Key points

• Building an AI agent for a demo and operating one for 40 million developers are different engineering problems.1
• We also explain how Agent Mode uses Amazon Bedrock for model flexibility, geographically scoped cross-Region inference, model-dependent zero data retention, and multi-tier prompt caching.1
• Figure 1: Agent Mode works directly against the Postman application.1
• Figure 2: Postman Agent Mode combines client-side tools, agent orchestration, purpose-built context, and Amazon Bedrock model inference.1

Sources (1)

• [1]How Postman runs Agent Mode for 40 million developers on Amazon Bedrock
  AWS Machine Learning Blog · Oct 9, 03:35 PM

  Postman set out to build Agent Mode, an AI-native way to work across API testing, documentation, discovery, and implementation.

  Building an AI agent for a demo and operating one for 40 million developers are different engineering problems.

Extractive summary: sentences quoted from the sources.