In partnership with
News of the day
1. Anthropic launches Claude Security plugin beta, a terminal-based multi-agent scanner that finds vulnerabilities and generates patch files for review. → Read more
2. AI is revolutionizing drug discovery by speeding up complex design processes, enabling the creation of novel therapies, and reducing development timelines significantly. → Read more
3. Google CEO Sundar Pichai reveals Gemini's future advancements hinge on developing significantly larger base models, with an ambitious training run underway. → Read more
4. Cisco unveils two open-source AI models for cybersecurity, claiming they detect 150x more vulnerabilities per dollar than large AI agents. → Read more
Our take
Hi Dotikers!
Anthropic has just released its Claude Security plugin for Claude Code in beta, and for once, the word security is not just a marketing sticker slapped on a release. In practice, a single command in the terminal launches a vulnerability scan on an entire repository or on a diff before a commit. Behind the scenes, an army of agents splits the work into six phases: mapping the code, modeling threats, hunting for flaws, then verification.
That last step is exactly what makes the project credible. Every candidate finding goes before a panel of three independent verifiers, who vote on its real-world exploitability, its impact, and the existing defenses. It takes two votes out of three to make it into the report, and a non-unanimous vote caps the displayed confidence level. Same story on the fix side: patches are developed in an isolated clone, reviewed by a different agent than the one that wrote them, and never applied automatically. Anthropic has clearly understood that an AI scanner grading its own homework is worthless, and that is precisely what most tools of this kind were missing, notorious as they are for churning out false positives.
There is still a lovely irony in seeing Claude hired to hunt down flaws in code that Claude probably wrote the day before. The snake is biting its own tail, but at least it is treating the wound.
This launch also fits into a broader strategy. After Record a Skill, unveiled this week in Claude Cowork, which lets you teach Claude a task by recording your screen and narrating out loud, Anthropic is methodically locking down every step of the daily workflow: we show it our moves, it executes, and now it circles back to double-check. The coworker position has officially been filled.
Alex.
Try the AI that knows your customers. No commitment.
Most platform evaluations start with a demo request and end three weeks later in a conference room. This one takes 15 minutes and puts you directly inside Gladly's interface — navigating it on your own terms.
See how AI surfaces real-time customer context before a conversation starts. Watch how a single conversation thread pulls in purchase history, channel history, and account details without a handoff.
No installation. No commitment. Start the interactive demo and see the platform for yourself.
Meme of the day
