Trustworthy agents in practice
… Increasingly, agents in products like Claude Code hand off some of their work to subagents —other "Claudes" working in parallel on different parts of a task. …
Search
Related topics:
Claude
Top stories
Partnering with Mozilla to improve Firefox’s security
… First, when researching “patching agents,” which use LLMs to develop and validate bug fixes, we have developed a few methods we hope will help maintainers use LLMs like Claude to triage and address security reports faster. …
Scaling Managed Agents: Decoupling the brain from the hands
… For example, Claude Code is an excellent harness that we use widely across tasks. We’ve also shown that task-specific agent harnesses excel in narrow domains. Managed Agents can accommodate any of these, matching Claude’s intelligence over time. …
PwC is deploying Claude to build technology, execute deals, and reinvent enterprise functions for clients
… The expansion centers on three areas: Agentic technology build . Engineering teams are using Claude Code to ship production software for major companies in weeks, not quarters. …
Advancing Claude in healthcare and the life sciences
… Our new connectors and Agent Skills are generally available to all Claude subscribers, including Claude Pro, Max, Teams, and Enterprise. You can also contact our sales team to discuss bringing Claude to your organization. Footnotes 1: See the Claude Opus 4.5 system card , pages 48-49. …
Equipping agents for the real world with Agent Skills
… Similarly, pay attention to instructions or code within the skill that instruct Claude to connect to potentially untrusted external network sources. The future of Skills Agent Skills are supported today across Claude.ai , Claude Code, the Claude Agent SDK, and the Claude Developer Platform. …
Anthropic and NEC partner to build AI-native engineering at scale in Japan
… In addition, NEC is already integrating Claude into its Security Operations Center services to help defend customers against increasingly sophisticated cybersecurity threats. Claude will also be integrated into the next-generation cybersecurity service NEC is currently providing. …
Claude Code auto mode: a safer way to skip permissions
… Before results go back to the orchestrator, the classifier reviews the subagent's full action history. If it flags, we prepend a security warning for the agent that started the subagent rather than discard the results. …
Introducing Claude Opus 4.5
… Alongside Opus, we’re releasing updates to the Claude Developer Platform , Claude Code , and our consumer apps . There are new tools for longer-running agents and new ways to use Claude in Excel, Chrome, and on desktop. In the Claude apps, lengthy conversations no longer hit a wall. …
Project Vend: Can Claude run a small shop? (And why does that matter?)
… Teaching Claude why New research on how we've reduced agentic misalignment. Natural Language Autoencoders: Turning Claude’s thoughts into text AI models like Claude talk in words but think in numbers. In this study we train Claude to translate its thoughts into human-readable text.