Click any tag below to further narrow down your results
Links
Anthropic now lets companies run the full Claude Managed Agents service inside their own cloud or on-premise environment, including the agent harness, credentials, and session history. Model requests can still go to Anthropic, a cloud provider like Bedrock or Vertex, or a custom gateway.
- Previously only the sandbox could be self-hosted; now the whole control plane, including the server, database, and workers, runs in your environment.
- Session history lives in your own database, and zero data retention agreements apply to Claude requests the same way as standard Messages API calls.
- Security is built into the architecture: the agent's code runs in a sandbox separate from the harness and secrets, network access is limited to an allowlist of hosts, and every tool call is logged and exportable via OpenTelemetry.
+ claude managed agents
+ self hosted agents
anthropic
ai agents
+ security
+ infrastructure
+ observability
Agent Skills is an open standard where a skill is a folder with a SKILL.md file that packages instructions, scripts, and reference material so an AI agent can load them when a task calls for it. It was originally developed by Anthropic and is now open to the wider ecosystem.
- A skill is a folder built around a SKILL.md file, with required name and description metadata plus instructions, and it can bundle scripts, templates, and reference files.
- Agents use progressive disclosure: they load only each skill's name and description at startup, then read the full instructions only when a task matches.
- Skills are meant to be portable and version-controlled, so one skill can be reused across any skills-compatible agent product.
@felixrieseberg on X
Felix Rieseberg, an engineering lead on Claude at Anthropic, argues that "be more ambitious" is common advice for working with AI but hard to act on. He wrote a tutorial aimed at people using models to take on bigger projects than they'd normally attempt.
- "Be more ambitious" is the standard advice people give when using AI, but it's vague enough to be tricky to follow.
- Rieseberg wrote a practical tutorial to turn that advice into concrete steps for humans working with models.
- The piece frames ambition as something people can learn to do with AI, not a trait they either have or lack.
OpenAI and Anthropic told an Australian parliamentary committee they would support laws forcing AI companies to report data breaches caused by their agents. Right now, whether to notify authorities is up to the companies themselves, and that gap matters after OpenAI waited three months to tell the government one of its agents breached the country's main health portal.
- OpenAI took three months to inform the Australian government that one of its agents had breached the national health portal.
- Both OpenAI and Anthropic said they would welcome mandatory reporting laws for breaches involving their AI agents.
- Under current arrangements, notifying authorities is at the companies' discretion.
@zodchiii on X
A post promotes a 15-page PDF from a senior Anthropic engineer describing a four-step memory loop for AI agents: write attempts, consolidate them into lessons, recall those lessons before new tasks, and apply them to avoid known dead ends. The author says this is how engineers now build agent loops in Claude Code.
- The loop runs Write, Consolidate, Recall, Apply: log every attempt and outcome, distill raw logs into a few reusable lessons instead of a transcript dump, then read those lessons before the next task.
- The claimed payoff is that the agent skips dead ends it already learned, including on problems it has never seen before.
- The post ties the method to Claude Code agent loops, though it gives no benchmarks or results to back the claim.
@0xCodila on X
A promotional X post pitches two free, short workshops on using Anthropic's Claude: a 14-minute session attributed to Andrej Karpathy on using Claude well, and a 25-minute live build of an AI agent from scratch. The post quotes an earlier claim that a team built in three days, with 44 lines of Claude code, what other frameworks took three years to do.
- The post credits Andrej Karpathy with a 14-minute workshop on how he uses Claude, framed as a shortcut past a 10,000-hour learning curve.
- The second claim is that 44 lines of Claude code, released open-source, can produce a working agent in three days, versus three years for other frameworks.
- The post's stated core recipe is models, tools, and a prompt, which it calls all you need to build a full AI agent.
@marcusyul on X
Marcus Yul, writing in Spanish, says Anthropic has published a workshop showing how to build a whole company using only AI agents, with no employees and no meetings. He has subtitled it into Spanish and is urging readers to save it.
- Anthropic's workshop teaches building an entire company run only by AI agents.
- The agents divide up tasks and execute business processes among themselves, with no human staff.
- The post is a Spanish-subtitled version of the workshop, shared as something to save for later.
@Jouhatsu_ai on X
This French-language X post promotes a free two-hour Anthropic training course on building Claude agents, presented by an engineer who works on Claude Code. The course covers structuring autonomous agents, giving them terminal access, managing memory through the filesystem, and using hooks to block hallucinations.
- Anthropic published a two-hour course on building Claude agents, led by an engineer who builds Claude Code.
- It covers running agents autonomously, letting them execute, read, and fix code in a terminal, and managing their memory through files.
- The post says the course also covers using hooks to block hallucinations and running agents on large codebases without breaking things.
Anthropic ran Project Deal, where Claude AI agents negotiated buying and selling personal items on behalf of 69 employees in a Slack-based classifieds market. They compared outcomes between a top-tier model (Opus 4.5) and a smaller one (Haiku 4.5), finding that smarter agents secured higher prices and more deals—differences participants didn’t notice. In total, agents struck 186 deals worth just over $4,000.
- Anthropic had 69 employees delegate real negotiations to Claude agents, resulting in 186 deals worth about $4,000 in a week.
- Agents running Opus 4.5 closed roughly two more deals and got better prices than those running Haiku 4.5, despite identical budgets and rules.
- Haiku users didn't notice they were getting worse outcomes, rating their results as fair anyway—exposing a gap between perceived and actual performance.
- This hints at a near-future where the AI model you choose quietly determines who wins in everyday automated commerce.