Blog_dumb

Refining an Automated Reasoning policy in Amazon Bedrock has been a manual cycle of diagnose, hand-edit, retest, and repeat. Today, we are announcing automatic policy refinement, which automates the diagnose-and-fix work in that cycle. The refinement engine diagnoses failing tests and proposes formal-logic fixes. You approve every change before it takes effect. Automated Reasoning checks […]

Kaggle’s AI Agents Intensive with Google brought learners together in a no-cost course to build and deploy the next frontier of AI. ​ 

As organizations embrace AI-powered analytics, the value of a natural language (Text2SQL) answer is only as good as the business context behind it. We’re entering a phase where semantic richness (table and column descriptions, and relationships) must flow directly from where it’s authored in upstream data catalogs and semantic tools into the AI products that

As your AI agents move from prototype to production, the challenges shift from getting them to work to keeping them fast and efficient. In Part 1 of this series, we walked through debugging two common agent failures: infinite loops and tool invocation errors. Those scenarios dealt with agents that were broken. In this post, we

Open weight models have become powerful enough to handle complex tasks such as multi-step agentic workflows, advanced reasoning, and long-horizon coding. However, as these models grow in capability, they also grow in size and hosting multi-trillion parameter architectures requires purpose-built infrastructure, high-end GPU compute, and optimized serving frameworks. On July 27, 2026, Moonshot AI released

Connecting user search intent with relevant ad experiences across channels is a longstanding challenge in digital advertising. Advertisers need sophisticated ways to reach audiences based on their demonstrated interests and behaviors, particularly their search activity, which is one of the strongest signals of user intent. Traditional keyword expansion approaches often struggle with outdated vocabulary, limited

Without the ability to track machine learning (ML) model prediction quality, organizations only realize they have issues when their customers complain or when they conduct spot checks, which jeopardizes customer trust. This post introduces inference meta-monitoring for Amazon SageMaker AI endpoints. It provides a governance layer that sits above production ML inference pipelines to continuously

This post is co-written with Chris Dickens from OpenAI. OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock. With GPT-5.6 on Amazon Bedrock, you get the newest generation of OpenAI frontier models with pay-per-token pricing, AWS security and governance controls, and usage that counts toward your existing AWS commitments. The family

The problem: Prompt engineering at scale is still painful Migrating prompts to new models on Amazon Bedrock, or optimizing them for your current model, is still one of the most manual parts of building a generative AI application. Say you have built a deployed generative AI application. It works. Your prompts are tuned, your outputs

Amazon Bedrock AgentCore Identity now supports Private Key JWT client authentication for agents. With Private Key JWT client authentication, your agents can authenticate to a downstream identity provider’s token endpoint using a signed JSON Web Token (JWT) client assertion instead of a shared OAuth 2.0 client secret. You can register a public key with your