Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: A pristine 1961 Ferrari 250 GT California Spyder in Rosso Corsa red parked inside an elegant library with floor-to-ceiling bookshelves, warm golden afternoon light streaming through tall windows, constitutional documents and leather-bound books arranged on an antique mahogany reading table beside the car, amber reading lamps casting soft highlights on the polished chrome and paint, cinematic automotive photography with subtle depth of field and rich shadows, scholarly and refined atmosphere
Equipping agents for the real world with Agent Skills \ Anthropic https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills
Customize Claude Code with plugins \ Anthropic https://www.anthropic.com/news/claude-code-plugins
Claude Skills are awesome, maybe a bigger deal than MCP https://simonwillison.net/2025/Oct/16/claude-skills/
Claude Skills: Customize AI for your workflows \ Anthropic https://www.anthropic.com/news/skills
Today we’re introducing Skills in claude dot ai, Claude Code, and the API. Skills let you package specialized knowledge into reusable capabilities that Claude loads on demand as agents tackle more complex tasks. Here’s how they work and why they matter for the future of agents: https://x.com/alexalbert__/status/1978877498411880550
I am not going to lie. I see a lot of potential in the Skills feature that Anthropic just dropped! Just tested with Claude Code. It leads to sharper and precise outputs. It’s structured context engineering to power CC with specialized capabilities, leveraging the filesystem. https://x.com/omarsar0/status/1978919087137804567
Claude and your productivity platforms \ Anthropic https://www.anthropic.com/news/productivity-platforms
Preparing for AI’s economic impact: exploring policy responses \ Anthropic https://www.anthropic.com/research/economic-policy-responses
Claude can now create and use files \ Anthropic https://www.anthropic.com/news/create-files
The Claude app is now a surprisingly good personal assistant. For whatever reason, Sonnet 4.5 is much better at working with Gmail/Google Calendar than other AI, even though most other models can access your email, they seem to do minimal work while Claude goes much deeper/wider”” / X https://x.com/emollick/status/1978101986357662156
Chrombot ( https://x.com/Eval_Engine/status/1958899009822892197
more than twice the speed”” is underselling Haiku tbh built a way to directly compare Sonnet v Haiku 4.5 and it’s roughly 3.5x faster, but the UX feels SO much better because Haiku stays inside the “”flow window””. obviously end to end latency varies a lot so Ant can’t report a https://x.com/swyx/status/1978524858834456620
The Claude Code SDK is now the Claude Agent SDK Why? Because we realized the Claude Code agent harness is useful for much more than coding. In fact, we’re moving to using it to power most of our own agent loops at Anthropic. https://x.com/trq212/status/1975243734083379662
New on the Anthropic Engineering Blog: Our tips for developers on using Agent Skills, a new way to extend Claude’s capabilities with instruction folders, scripts, and resources: https://x.com/AnthropicAI/status/1978896757489594404
Using this new agent in ClickUp you can totally leapfrog the IDE, Cursor, Claude Code… Codegen is now available in ClickUp. “”Hey @codegen, fix this bug”” – me “”PR submitted & ready for review!”” – Codegen “”Sweet, ship it”” – me We’ve always believed that the future of AI value https://x.com/DJ_CURFEW/status/1978568748794794476
Here’s your comprehensive guide to understanding and building Model Context Protocol (MCP) Servers for C# developers. It’s a great hands-on resource for exploring MCP and AI assistant integration in .NET environments. 📚 https://x.com/dotnet/status/1960029410649649626
GitHub Copilot + MCP = 🤯 Assign an issue → Copilot fetches data from a remote MCP server → Builds a green-themed HTML file 🎨💻 Autonomous dev workflows are here. This is next-level automation for your dev. 🔗 https://x.com/dotnet/status/1960096101333131310
We’re excited to announce that KumoRFM now supports Model Context Protocol (MCP), the open standard that connects AI agents with external tools and data. Explore more in our blog: https://x.com/Kumo_ai_team/status/1963320126843032026
ICYMI: Oracle Database now includes a Model Context Protocol (MCP) Server made available via Oracle SQLcl. Using any MCP-supported client, your favorite AI assistant and LLM, you can securely connect and interact with your database! https://x.com/OracleDevs/status/1961213462433980436
Announcing Open Agent Builder – A @firecrawl_dev powered n8n-style workflow builder example app Build AI agent workflows with a visual canvas by connecting Firecrawl, LLMs, logic nodes, and MCPs, then deploy as an API. Fork the repo and build your own workflow app today 👇 https://x.com/CalebPeffer/status/1978852506286571737
🚀 Product Highlight: @Ask_Rube (by @composiohq) — The universal MCP connector for AI agents. Access 500+ integrations like Gmail, GitHub, Slack, and Notion through one secure, managed endpoint. Highlights: • 500+ Production-Ready Integrations — Gmail, GitHub, Slack, Notion & https://x.com/MCP_Community/status/1959956426434265538
France’s @alpic_ai, a #cloud platform built specifically for Model Context Protocol (#MCP), announced today it has raised €5.1 million in #preSeed funding to build infrastructure for #AI agents to interact with the digital world 🇫🇷 🤖 https://x.com/EU_Startups/status/1963532351629136370
more side by side comparisons of @AnthropicAI Claude Haiku 4.5 vs Sonnet 4.5 in @windsurf here’s Haiku vs Sonnet on @flavioAd’s hexagon test the thing about fast models is that you can iterate with human guidance >2x in the time that it takes the slower model to do 1 round. https://x.com/swyx/status/1978578087752372452
Claude Skills | Hacker News https://news.ycombinator.com/item?id=45607117
📢 New Model Drop: Claude Haiku 4.5 is now on Yupp! @AnthropicAI’s latest small model, engineered for performance, speed and low cost. We investigated this new model with some prompts: https://x.com/yupp_ai/status/1978602716961415192
Today we’re introducing Claude Code Plugins in public beta. Plugins allow you to install and share curated collections of slash commands, agents, MCP servers, and hooks directly within Claude Code. https://x.com/claudeai/status/1976332881409737124
Claude Haiku 4.5 System Card https://assets.anthropic.com/m/99128ddd009bdcb/original/
Cerebras took Cognition’s latest code retrieval model, put it on the wafer, and it’s now running circles around Claude and Cursor. It’s now live in production for Windsurf users.”” / X https://x.com/draecomino/status/1978898418354561225
Claude’s unwillingness to continue conversations after the context window is full is very frustrating. I am okay losing early context if I am working interactively on a project & making progress, I am not okay with suddenly being cut off and being forced to start a new chat. https://x.com/emollick/status/1977604962772512800
Introducing Claude Haiku 4.5 \ Anthropic https://www.anthropic.com/news/claude-haiku-4-5
Anthropic launches their first Haiku model in 11 months – Claude 4.5 Haiku jumps 35 points in Artificial Analysis Intelligence Index to become relevant again Claude 4.5 Haiku is 3x cheaper per token than Claude 4.5 Sonnet. Running the Artificial Analysis Intelligence Index costs https://x.com/ArtificialAnlys/status/1978661658290790612
Learn how to build a Model Context Protocol (MCP) server that enables #LLM access to network devices—safely and securely. 🤖 See how it works (and get the code!) in the latest #AI Break series’ blog by @Kareem_isk. https://x.com/LearningatCisco/status/1960087189699657861
🚨 Text Leaderboard Update Community votes are in, and @anthropicAI’s Claude Haiku 4.5 ranks #22! It has quickly become one of the best value models on the most competitive leaderboard. It delivers a solid punch at a fraction of the cost of its bigger siblings. ⚡️ A few https://x.com/arena/status/1978966289248063885
Claude. make the most recursive, self-referential presentation you can imagine. seriously go big with this, don’t just run with your first idea, revise it multiple times (ironic instruction, yes)”” “”come on, i said recursive & self-referential. improve it. (see what i did?)”” https://x.com/emollick/status/1977927117212971165
🎉 𝗠𝗖𝗣 𝗶𝘀 𝗡𝗼𝘄 𝗚𝗔 𝗶𝗻 𝗩𝗶𝘀𝘂𝗮𝗹 𝗦𝘁𝘂𝗱𝗶𝗼! 🧠🛠️ Model-Context Protocol (MCP) is now generally available in @VisualStudio! Build smarter, more context-aware apps with full support and tooling baked right into your favorite IDE. It’s time to bring AI-native https://x.com/dotnetdevs_io/status/1963300959443923040
Claude now connects to Microsoft 365. Claude can search for information in SharePoint, OneDrive, Outlook and Teams, providing tailored responses seamlessly. https://x.com/AnthropicAI/status/1978864348236779675
MCP often gets criticized for its propensity to bloat context with “tool overload”. I think this criticism is unfounded. The reality is, you should never have more than a few MCP servers active in your context at a given time. And if a single MCP server has too many tools -“” / X https://x.com/tadasayy/status/1978170863192346660
Ran Haiku-4.5 against my NYT Connections Eval with DSPY project and the results are in! – Baseline score of 64% – Optimized score of 71% – Complete in only 25 minutes – Total cost $11 This means Haiku 4.5 is the fastest model I’ve tested so far (ignoring Haiku 3.5 which did https://x.com/pdrmnvd/status/1978570006863790299
Anthropic and Salesforce expand partnership to bring Claude to regulated industries \ Anthropic https://www.anthropic.com/news/salesforce-anthropic-expanded-partnership
We’re expanding our partnership with @Salesforce. Claude is now a preferred model in Agentforce for regulated industries. We’re deepening Claude’s integration with Slack, and Salesforce is rolling out Claude Code for its global engineering organization. https://x.com/AnthropicAI/status/1978125047270154567
Introducing the world’s first Portfolio Construction MCP💠 A groundbreaking Model Context Protocol server that brings Wall Street-grade portfolio optimization / re-balancing directly to AI agents, wallets, and other crypto projects. https://x.com/ChainAware/status/1958573602422358292
AI Agents can now see and test the code they generated. Chrome DevTools MCP gives AI agents live Chrome instances to analyze performance traces, inspect DOM, and debug issues in real-time. Works with Cursor, Gemini CLI, Claude Code and more. 100% Opensource. https://x.com/Saboo_Shubham_/status/1973937860626792868
Salesforce AI Research introduces MCP-Universe: the first benchmark to truly test LLM agents in real-world scenarios with live Model Context Protocol servers. https://x.com/HuggingPapers/status/1959347736429674567
Trump AI Czar Is Trying to Take Down Anthropic AI https://gizmodo.com/trump-ai-czar-is-trying-to-take-down-anthropic-ai-2000672709
The Claude Gmail & Google calendar plugins now work surprisingly well since Sonnet 4.5 came out. If you ask for a briefing and prep for tomorrow for example, it not only pulls up your events, but cross-references them with your email history & web search to give good insights.”” / X https://x.com/emollick/status/1976468892525695376
Claude-Haiku-4.5 is out in anycoder on Hugging Face https://x.com/_akhaliq/status/1978578382309753205
We have a new comprehensive Model Context Protocol (MCP) documentation section, to help you connect your AI applications to external tools and data sources through a standardized interface. 🔌 Learn how MCP works – connecting LLMs to databases, tools, and services through a https://x.com/llama_index/status/1957840992360710557
Claude Code subagents are all you need. Some will complain on # of tokens. However, the output this spits out will save you days. The code quality is mindblowing! Agentic search works exceptionally well. The subagents run in parallel. ChatGPT’s deep research is no match! https://x.com/omarsar0/status/1978235329237668214
skills/document-skills at main · anthropics/skills https://github.com/anthropics/skills/tree/main/document-skills
