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: At a high level, the best analogy I've heard for Skills is something like Neo learning Kung Fu in seconds in the Matrix.

We're "loading in" specialized knowledge to our general agents at runtime.

We’re running a “Built with Claude Sonnet 4.5” challenge.

We want to see the coolest things you can build with 4.5 in the next week.

Four winners will receive one year of Claude Max 20x and $1k in Claude API credits. We will select four winners:

“Keep Coding” Award - most technically impressive implementation

“Keep Researching” Award - most compelling exploration of a topic

“Keep Learning” Award – best educational application

“Keep Creating” Award – most artistic use-

We’ve rolled out another update to Claude Code to help customize your workflows: Hooks. Hooks are user-defined shell commands that execute at various points in Claude Code’s agent loop.

They give you deterministic control over Claude Code’s behavior to ensure certain actions always happen at certain times.

We've simplified local MCP usage by creating something new we call Desktop Extensions (.dxt files).

These package your local server, handle dependencies, and provide secure configuration so you can one-click share and install local servers on Claude Desktop and other apps. dxt's are zip archives containing the local MCP server as well as a manifest.json, which describes everything Claude Desktop and other apps supporting desktop extensions need to know.

Multi-agents systems are the next frontier of AI applications. At Anthropic, we found that multi-agents beat single agents by up to 90%+ on some complex tasks.

We wrote a blog post detailing practical tips for building multi-agent systems based on our own experiences: Let's start with some context:

This post is based on our learnings from developing claude dot ai's Research feature. We define a multi-agent system to be multiple agents (LLMs autonomously using tools in a loop) working together.

We’ve added four new features to the Anthropic API today:
- Code execution tool
- MCP connector
- Files API
- Extended prompt caching

Let’s dive in: The code execution tool allows Claude to run python code that it generates in a secure sandboxed container.

This is a big boost for any tasks involving data analysis or math.

Introducing Claude Opus 4 and Claude Sonnet 4.

Our best models yet. The Claude 4 family is here. Let's start with Opus 4. It’s finally back and it's better than ever.

This model picks up on the subtlest nuances in conversation. Every interaction I’ve had with it feels more natural and intuitive than with any other model I’ve used.

We wrote up what we've learned about using Claude Code internally at Anthropic.

Here are the most effective patterns we've found (many apply to coding with LLMs generally): 1/ CLAUDE md files are the main hidden gem. Simple markdown files that give Claude context about your project - bash commands, code style, testing patterns. Claude loads them automatically and you can add to them with # key

I used Claude Code to make an agentic march madness bracket picker in <20 minutes.

Here's the final four that Claude picked: Here's the full bracket, Claude's a bit more on the conservative side when it comes to upsets

We’ve completely overhauled the design of the Anthropic Console to make it the one-stop-shop for all things prompt engineering.

Here’s a few of my favorite features: The workbench is our prompt playground. Iterate on your prompts and test features like tool use, extended thinking, and much more.

One of the things we've been most impressed by internally at Anthropic is Claude 3.7 Sonnet's one-shot code generation ability.

Here are a few of my favorite examples I've seen on here over the past day: Racing games

https://twitter.com/2786431437/status/1894238330138812616

Introducing Claude 3.7 Sonnet.

Our most intelligent model to date and the first generally available hybrid reasoning model in the world. We developed Claude 3.7 Sonnet with a different philosophy than other reasoning models out there. Rather than making a separate model, we integrated reasoning as one of many capabilities in a single frontier model.

We've rolled out Citations in the Anthropic API.

Citations allows Claude to ground its answers in user-provided information and provide precise references to the sentences and passages used in its responses.

Here's how it works: Under the hood, Claude is trained to cite sources. With Citations, we are exposing this ability to devs.

To use Citations, users can pass a new "citations: {enabled:true}" parameter on any document type they send through the API.

Quality of life update today for devs. Four features are moving out of beta to become generally available on the Anthropic API:
- Prompt caching
- Message Batches API (with expanded batches)
- Token counting
- PDF support Prompt caching is now:
- Generally available on the Anthropic API
- In preview on Google Cloud’s Vertex AI
- In preview in Amazon Bedrock

https://twitter.com/1380719534970040322/status/1823751966893465630

It's only been a day since we've released MCP and folks are already starting to build tons of stuff on top of it.

The future of MCP is truly going to be community-led and not controlled by any single entity.

Here are some of the highlights I'm seeing from across the industry: Replit is looking into adding MCP support to Agents

https://twitter.com/19888273/status/1861084103556366665

I just connected Claude to an internet search engine using MCP.

Here's how you can do it too in under 5 minutes: First, you will need to download the latest version of our Claude desktop app here: claude.ai/download

Introducing the Model Context Protocol (MCP)

An open standard we've been working on at Anthropic that solves a core challenge with LLM apps - connecting them to your data.

No more building custom integrations for every data source. MCP provides one protocol to connect them all: Here's a quick demo using the Claude desktop app, where we've configured MCP:

Watch Claude connect directly to GitHub, create a new repo, and make a PR through a simple MCP integration.

Once MCP was set up in Claude desktop, building this integration took less than an hour.

We've added a Claude-powered prompt improver to the Anthropic Console.

Take any prompt, run it through the improver, and get an optimized prompt in return.

Here's how it works: To start, you enter a prompt and specify what aspects of the prompt you would like to improve.

Once you hit enter, a six-step prompt improvement process begins.

We held our first Builder's Day in partnership with @MenloVentures this past weekend!

It was a great event with tons of extremely talented devs in attendance.

Here's a recap of the day: We kicked the day off with a @DarioAmodei fireside chat.

Then, we followed things up with a few technical talks: one from yours truly on all our recent launches and one from @mlpowered on the latest in interpretability.

Claude 3.5 Haiku is now available on the Anthropic API, Amazon Bedrock, and Google Cloud's Vertex AI.

Claude 3.5 Haiku is our fastest and most intelligent cost-efficient model to date. Here's what makes it special: 3.5 Haiku surpasses all previous Claude models (except the new 3.5 Sonnet) on coding and agentic tasks, while being significantly more affordable -- a fraction of the cost of Sonnet and Opus.

It's a big day for Claude's PDF capabilities.

We're rolling out visual PDF support across claude dot ai and the Anthropic API.

Let me explain:
Up until today, when you attached a PDF in claude dot ai, we would use a text extraction service to grab the text and send that to Claude in the prompt.

Now, Claude can actually see the PDF visually alongside the text.