We're so excited to launch Claude Code on the web and iOS app today!
This has become a daily driver for many of us on the Claude Code team. Here are a few of our favorite ways to use it:
How to add Chrome DevTools MCP to Claude Code
(Bookmark this post to follow the setup later)
This lets Claude debug your web apps in a real browser... performance traces, network inspection, console errors.
Requirements:
- Node.js 22+
- Chrome browser
In the video below I show you:
- How to install the MCP server
- How to verify the DevTools tools are available
- How to use it with a real performance trace
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.
Two big updates to the Responses API today. 🖇️ Connectors — Pull context from Gmail, Google Calendar, Dropbox, and more in a single API call. 💬 Conversations — Persist chat threads for your users, without running your own database. More below:
Apple just dropped a killer open-source visualization tool for embeddings — Embedding Atlas — and it’s surprisingly powerful for anyone working with large text+metadata datasets.
This reminds me of Nomic's Atlas, but I never got around to using it 😅
We’re talking real-time search, multi-million point rendering, and automatic clustering with labels.
One of their showcase examples visualizes ~200K wine reviews using embeddings + metadata like price, country, and tasting notes. And it is lightning fast even on my browser! No separate code needed!
It nails what most LLM devs need but often hack together:
✅ UMAP projections
✅ Faceted search across metadata (e.g. “country vs. price”)
✅ Hover + tooltip on raw points
✅ Interactive filters, histograms, and cluster overlays
✅ Cross-linked scatterplot + table views
Under the hood:
• Fast rendering using WebGPU (with WebGL fallback)
• Embedding-based semantic similarity search
• Kernel density contours for spotting clusters or outliers
You just upload your .jsonl or .csv with text + vector + metadata. It handles the rest: clustering, labeling, UI layout, everything.
This feels like the LLM-native version of Tableau — but optimized for text, chat and modern data needs
If you’re building RAG evals, search tuning, clustering explainability, or even dataset audits — this could be your new favorite tool.
Cursor life hack.
Start every new chat with the following prompt:
"Do a deep-dive on the code and understand how [insert feature] works. Once you understand it, let me know, and I will provide the task I have for you."
Reduces hallucinations by 10x