Agentic-Ai

China’s biggest tech companies aren’t sitting out the agentic AI race — they’re building platforms that address what enterprise customers actually want: the power of OpenClaw with none of the operational burden. Baidu AI Cloud has launched DuClaw, a fully managed, zero-deployment AI agent platform targeting Chinese enterprise customers. The timing couldn’t be more loaded: DuClaw arrives the same week CNCERT issued its stark warning about OpenClaw’s weak security defaults, effectively validating Baidu’s entire pitch. ...

The Model Context Protocol has had a remarkable year. What started as Anthropic’s attempt to standardize how AI models connect to external tools and data sources has become, almost by accident, the de-facto tool layer for the entire agentic AI ecosystem. Claude uses it. OpenAI-compatible agents use it. Builders across the industry are shipping MCP servers like it’s the new API endpoint. But if you’ve tried to run MCP seriously in production, you’ve bumped into the same set of friction points. Authentication is awkward. Streaming is limited. Discovering MCP servers requires manual configuration. Multi-agent handoffs lack proper task lifecycle semantics. And when things fail — network blips, agent restarts, timeout conditions — the retry behavior is undefined. ...

Breaking news from MiniMax: the company has officially released M2.5, the latest entry in its M2 model family — and the benchmarks are going to raise some eyebrows. SOTA on coding. Twice the speed of its predecessor. And priced so aggressively that the company’s own marketing frames it as “intelligence too cheap to meter.” At $1 per continuous hour of inference at 100 tokens per second, or $0.30 at 50 tokens/sec, MiniMax M2.5 is targeting a very specific pain point for anyone building with agentic AI at scale: cost. ...

If you’ve been hesitating to build long-context workflows because of the cost, Anthropic just removed the last excuse. As of March 13, 2026, the full 1 million token context window is generally available for both Claude Opus 4.6 and Claude Sonnet 4.6 — at standard API pricing, with no premium multiplier attached. That’s a significant shift. Until now, heavy long-context usage carried an implicit tax: either you paid a premium rate for requests over certain thresholds, or you engineered around the limitation with chunking, compaction, and lossy summarization. Those workarounds aren’t free — they cost engineering time, introduce accuracy loss, and add system complexity. Anthropic is now saying: stop doing that. ...

Alibaba just made agentic AI accessible to anyone with a smartphone. And in doing so, it’s turned what was already a heated competition among China’s tech giants into a full sprint. JVS Claw, Alibaba’s new iOS and Android application, allows users to install and deploy OpenClaw AI agents in minutes — no coding required, no command line, no developer setup. The app is free for the first 14 days. It’s a direct play for the hundreds of millions of Chinese mobile users who are curious about AI agents but have no technical background, and it lands at exactly the moment that agentic AI has become a household conversation in China. ...

NVIDIA just dropped something that’s going to matter for anyone building real agentic AI systems. Nemotron 3 Super is a 120-billion-parameter open-weight model — but here’s the key detail that separates it from the crowd: it only uses 12 billion active parameters at inference time thanks to a hybrid Mamba-Transformer Mixture-of-Experts (MoE) architecture. The result? Five times higher throughput than comparable-sized models, with a one-million-token context window that changes how agents can actually operate in the wild. ...

If you’ve ever had to manually copy data from a spreadsheet into a presentation and then re-explain the context to your AI assistant all over again, Anthropic just solved that in a way that matters for real enterprise workflows. On March 11, Anthropic launched updates to its Claude add-ins for Microsoft Excel and PowerPoint that allow the two applications to share full conversation context in a single session. The update is available immediately to paid Claude plan users on Mac and Windows. ...

Zendesk made a bold bet on March 11: it announced a definitive agreement to acquire Forethought, an agentic customer experience company, and simultaneously declared that 2026 would be the year AI agents handle more customer service interactions than humans. That’s not a cautious enterprise vendor hedging its AI roadmap. That’s a structural claim about a market Zendesk has dominated for over a decade. What Forethought Brings Forethought builds AI agents specifically for customer service workflows. Its core differentiation is self-improving agents — systems that learn from resolved tickets, update their own knowledge, and progressively get better at deflecting and resolving issues without human escalation. ...

The security industry has spent years warning about AI-powered threats in abstract terms. Flashpoint’s 2026 Global Threat Intelligence Report drops the abstraction: 47% of cybersecurity professionals now identify agentic AI as their top attack surface — and only 29% have deployed any countermeasures. That gap — 47% concerned, 29% prepared — is the most important number in the report. What the Report Found Flashpoint is a threat intelligence firm with significant data access across the criminal and state-sponsored threat ecosystem. Their annual Global Threat Intelligence Report is one of the more credible annual security surveys, drawing on both proprietary threat data and professional surveys. ...

Perplexity just announced something that sounds deceptively simple: an AI agent that lives on your Mac mini, runs 24 hours a day, and has access to your local files and applications. They’re calling it Personal Computer, and they unveiled it at their Ask 2026 developer conference. Waitlists opened immediately. This is more consequential than another AI announcement. Perplexity is making a direct architectural bet against the cloud-first model that dominates agentic AI today. ...