What shipped & dropped across AI labs, today.
Today
Wed · Jul 29 · 3 postsCursor, now on iPad
Cursor for iPad is now available on all paid plans. New to both iPhone and iPad: an inbox to stay organized, and a review experience that covers the full PR. Create, review, and merge from anywhere. #Built for the bigger screen The iPad layout is rebuilt around the extra space. Sidebar chats stay pinned so you can watch several agents run at once. Split screen keeps a review open next to a chat, and file diffs render in full. Markup gets more room to work too. Attach a screenshot, then tap to drop a comment at a specific point, or draw directly on the image with Apple Pencil. #A full review surface On iPhone and iPad, the review screen now covers the full PR: comments, checks, and approvals. Add or change reviewers, read comments, and prompt the agent to resolve them. The whole path from agent output to merged PR now travels with you. #Inbox An Inbox helps you and your agents stay organized. See what's in progress, what needs your attention, and which PRs are in review. #Additional improvements for Cursor on iPhone and iPad Bitbucket and Azure DevOps SCM support Multi-PR sessions: when one chat creates multiple PRs, you can now open every one of them, not just the last. Switch between teams that you belong to directly in the app Download the Cursor App or read our docs to learn more.
Introducing Grok Voice Think Fast 2.0
Introducing our most capable speech-to-speech voice model.
Default model enablement for Copilot Business and Enterprise
We’re introducing a global default enablement policy for generally available Copilot models on Copilot Business and Copilot Enterprise plans. Instead of requiring admins to manually turn on each new model…
Yesterday
Tue · Jul 28 · 6 postsGitHub Copilot app usage metrics now expand across report rollups
Copilot app usage is now reported across much more of the Copilot usage metrics API. Individual Copilot app activity is now attributed to users in the enterprise-user and organization-user reports.…
Grok 4.5 in GitHub Copilot
Grok 4.5, our smartest coding model, is now available in GitHub Copilot.
Grok 4.5 is now available in GitHub Copilot
Grok 4.5, xAI’s latest reasoning model, is now rolling out in GitHub Copilot. It is designed for fast, agentic coding and complex multi-step workflows, with a context window of up…
Bringing MCP 2026-07-28 to Claude
The MCP 2026-07-28 spec is live, moving the Model Context Protocol to a stateless core with standardized extensions and hardened auth. Support is rolling out across Claude products soon. See what's new and how MCP is advancing in Claude.
Introducing Build Mode
Create and share websites, apps, games, and interactive dashboards. Now in Early Beta for SuperGrok Heavy subscribers on grok.com, iOS, and Android.
Cursor Start
We're introducing Cursor Start, a new ₹649 monthly plan for developers in India, making daily agentic development accessible and payment easy with local pricing and UPI. Existing Free users in India can upgrade their plan from the dashboard. New users in India can visit cursor.com/signup and select the Start plan during onboarding. Start bills monthly with auto-renewal and is available from July 28, 2026. Cursor Start includes: Generous access to Cursor models: Grok 4.5 (fixed medium effort, non-fast) and Composer (non-fast), with enough usage to build with agents every day. Always-on cloud agents that build, test, and ship code while you keep working. Cursor for iOS with remote control, so you can launch and steer agents from your phone. Plugins, MCP servers, hooks, and skills to extend Cursor across your workflows. Local pricing at ₹649 per month, tax inclusive, billed in INR with UPI or card. Learn more in our announcement and docs.
Monday
Mon · Jul 27 · 5 postsGitHub Copilot for JetBrains adds improved OpenTelemetry configuration and model management
This update brings more control and clarity to your GitHub Copilot for JetBrains workflows. You can now connect MCP servers and custom agents in Claude agent flows, tune telemetry and…
Enterprise managed settings in the GitHub Copilot app and Copilot cloud agent
You can now govern the GitHub Copilot app and Copilot cloud agent with enterprise managed settings, the same centrally managed policies you use to control Copilot across your enterprise. With…
Our position on open-weights models
Manage GitHub Copilot app access with a dedicated policy
The GitHub Copilot app now has its own policy, so you can control who has access to it at the enterprise and organization levels. Until now, access to the Copilot…
Cognizant and Anthropic expand their partnership to bring Claude to enterprise clients
Friday
Fri · Jul 24 · 6 postsGrok in Google Workspace
Use the Grok add-on for Google Workspace to work directly in Sheets, Slides, and Docs.
Claude Opus 5 is now available in GitHub Copilot
Claude Opus 5, Anthropic’s newest Opus model, is now available in GitHub Copilot. It is designed for complex, long-running coding tasks that require careful reasoning, effective tool use, and reliable…
Claude models explained: choosing the best model for your use case
How to choose the right Claude model for your workload: compare model classes, weigh cost per task vs. cost per token, and build evals that settle it.
The new rules of context engineering for Claude 5 generation models
We removed over 80% of Claude Code's system prompt for more advanced models. How to apply the lessons we learned to your own context engineering in Claude Code and with your own agents.
How the product designer who built Claude Design uses it to explore ideas before building them
Nate Parrott, a product designer at Anthropic, shares how he uses Claude Design (in beta) to explore, iterate on, and share visual ideas early, from product prototypes to slide decks and animations.
Run Ray on TPU, Part 2: Ray AI libraries
This second installment explores how Ray’s higher-level libraries—Serve, Data, and Train—abstract the complexities of running AI workloads on Google's TPU slices. Ray Serve uses a simple topology configuration to correctly gang-schedule large multi-host models, while Ray Data eliminates data-loading bottlenecks by feeding accelerators directly with native JAX batches. Finally, JaxTrainer streamlines distributed training across TPUs by automatically handling cross-slice coordination, checkpointing, and fault tolerance.