InfoQ - Claude - News

Anthropic Details How it Contains Claude across Web, Code, and Cowork

Eran Stiller — Wed, 22 Jul 2026 12:25:00 GMT

Anthropic detailed the containment architectures it uses for Claude across its products. It argues that agent safety depends on placing deterministic limits on an agent’s filesystem, network, and execution environment rather than on permission prompts or safeguards. Most notably, it examines failures at trust boundaries and along permitted egress paths that led Anthropic to revise those designs.

By Eran Stiller

Stripe Benchmark Shows AI Agents Build Integrations but Struggle with Validation

Leela Kumili — Wed, 15 Jul 2026 14:25:00 GMT

Stripe introduces a benchmark suite to evaluate whether AI agents can build real-world Stripe integrations across backend, frontend, and browser-based checkout workflows. The study examines end-to-end software engineering capability, focusing on execution, testing, and validation gaps in agentic systems under production-like constraints.

By Leela Kumili

AWS Ships Claude Apps Gateway as Self-Hosted Control Plane for Claude Code and Claude Desktop

Steef-Jan Wiggers — Wed, 15 Jul 2026 11:04:00 GMT

AWS and Anthropic have released the Claude apps gateway for AWS, a self-hosted control plane that centralizes identity, policy, telemetry, routing, and spend caps for Claude Code and Claude Desktop. The gateway runs as a single stateless container and routes inference to Amazon Bedrock or Claude Platform on AWS.

By Steef-Jan Wiggers