AWS published a setup guide combining OpenAI Codex, LiteLLM, Amazon ECS, and Amazon Bedrock to give enterprises centralized controls over AI coding agents. The pattern addresses managed adoption needs: model-access control, budget and rate-limit enforcement, consumption attribution, and observability. Codex agents run their task loop on the developer workstation while the LiteLLM layer centralizes governance.
AWS published guidance for building visibility into OpenAI Codex coding agents running on Amazon Bedrock. The approach uses OpenTelemetry metrics emitted by Codex, routed through a local OTel collector to Amazon CloudWatch, giving an AWS-native view of adoption, consumption, and reliability.
AWS published guidance for building visibility into OpenAI Codex coding agents running on Amazon Bedrock. The approach uses OpenTelemetry metrics emitted by Codex, routed through a local OTel collector to Amazon CloudWatch, giving an AWS-native view of adoption, consumption, and reliability.
Anthropic introduced Claude apps gateway, a self-hosted governance layer for Claude Code and Claude Desktop on AWS, providing centralized controls over authentication, model access, cost attribution, and spend enforcement. It integrates with Amazon Bedrock and Claude Platform on AWS, reducing operational overhead for enterprise administrators.
Anthropic introduced Claude apps gateway, a self-hosted governance layer for Claude Code and Claude Desktop on AWS, providing centralized controls over authentication, model access, cost attribution, and spend enforcement. It integrates with Amazon Bedrock and Claude Platform on AWS, reducing operational overhead for enterprise administrators.
Amazon Bedrock AgentCore Gateway is a new offering that centralizes governance of AI agent tool access, addressing the recurring customer question of which agents can reach customer data and what happens if credentials leak. It provides a single point to manage and audit agent permissions across internal tools.
Amazon Bedrock AgentCore Gateway is a new offering that centralizes governance of AI agent tool access, addressing the recurring customer question of which agents can reach customer data and what happens if credentials leak. It provides a single point to manage and audit agent permissions across internal tools.
Jefferies built an AI-powered trade assistant that helps front office traders get real-time insights into client behavior, trade patterns, and market trends without needing to code or rely on subject matter experts. The system uses LLMs to enable natural language queries over millions of rows of trading data, reducing the time to insight from hours to seconds.
Jefferies built an AI-powered trade assistant that helps front office traders get real-time insights into client behavior, trade patterns, and market trends without needing to code or rely on subject matter experts. The system uses LLMs to enable natural language queries over millions of rows of trading data, reducing the time to insight from hours to seconds.
DiDi built a contact center quality assurance system with AWS for its International Business Group, using LLMs on Amazon Bedrock. It runs three pipelines — intent verification, compliance evaluation, and Voice of Customer analysis — across Spanish and Portuguese. It replaces an opaque third-party QA tool with a transparent, self-owned AI architecture for DiDi's CX team.
DiDi built a contact center quality assurance system with AWS for its International Business Group, using LLMs on Amazon Bedrock. It runs three pipelines — intent verification, compliance evaluation, and Voice of Customer analysis — across Spanish and Portuguese. It replaces an opaque third-party QA tool with a transparent, self-owned AI architecture for DiDi's CX team.