What shipped & dropped across AI labs, today.
Today
Wed · Aug 5 · 2 postsScaling AI Agent Infrastructure with the MCP Stateless updates
The 2026-07-28 Model Context Protocol (MCP) specification replaces legacy stateful constraints with a fully stateless core, enabling cloud-native horizontal scaling, serverless deployments, and standard round-robin load balancing. This architectural shift introduces standardized HTTP headers for efficient routing without deep packet inspection, caching controls, and Multi Round-Trip Requests (MRTR) to handle interactive and long-running tasks without blocking connections. Developers can immediately begin migrating their agentic applications to this highly scalable infrastructure using the newly available beta SDKs for Python, TypeScript, Go, and C#.
Inference hooks: inline data loss prevention for Claude Enterprise
Inference hooks lets your compliance team inspect and enforce policy on every prompt and tool call response before they reach Claude — across Claude Enterprise surfaces including chat, Claude Code, Claude Cowork, and more.
Yesterday
Tue · Aug 4 · 4 postsA guide to cost visibility and control in Claude
How IT admins can see and manage Claude costs, including spend caps, model controls, usage analytics, and API features like prompt caching and batch processing.
Retiring the Copilot Billing Preview app
We’ve retired the GitHub Copilot Billing Preview app, and it’s no longer available. You can review and manage your Copilot spend directly in your GitHub billing settings. The app helped…
Mariano-Florentino (Tino) Cuéllar to join Anthropic as Chief Global Affairs Officer
A unified API for AI model routing
Google Cloud API Gateway now offers a model routing feature in Public Preview, allowing developers to dynamically route traffic to models like Gemini, Claude, or OpenAI OSS-GPT without hardcoding endpoints or managing open-source proxies. Developers can easily configure these routing rules directly within their OpenAPI 3.x specifications by mapping virtual model names to specific backend targets on a shared host. Once deployed, the Gateway acts as a serverless ingress layer that accepts standard OpenAI-compatible requests, automatically transcodes the payload to the native schema of the target model, and routes the traffic on the fly.
Monday
Mon · Aug 3 · 5 postsTrigger Copilot automations with comments
You can now create Copilot cloud agent automations that run when an issue comment or pull request comment is created. Common use cases include: Generate documentation: Comment on a pull…
Enterprise team specialization for managed settings
Enterprise administrators can now customize managed settings by targeting enterprise teams with itemized configuration files. Large enterprises can scale governance without bottlenecking every configuration change through central administrators or one-size-fits-all…
Customize the reasoning level for Copilot cloud agent
When you delegate a task to GitHub Copilot cloud agent, you can now set the reasoning level for models that support it. This allows you to control how much the…
Google Workspace Plugins
Cursor can now read, write, and act across your Google Workspace. New plugins give coding agents direct access to Gmail, Google Drive, and Calendar, so you can pull context, draft and update files, and manage your inbox and calendar without leaving Cursor. Install plugins to connect: Google Drive: search files and folders, open and download content, create and organize files Gmail: search and read mail, draft and send messages, apply labels and manage threads Google Calendar: read schedules, create and update events, find free time Browse the new plugins in the Cursor Marketplace or install them from the Customize page in Cursor. Learn more in our docs.
Scaling real-time AI agents with session-aware load balancing
Real-time AI agents break traditional request-response load balancing paradigms because they rely on long-lived, stateful bidirectional streams that obscure true server capacity. To solve this, developers must implement application-level session tracking directly within the runtime to accurately measure the committed concurrent workload of active conversations. By feeding these precise session counts alongside standard CPU utilization metrics into a hybrid routing algorithm, infrastructure can effectively distribute stateful AI traffic and prevent individual backend bottlenecks.
Friday
Fri · Jul 31 · 6 postsUpcoming August 2026 model deprecations in GitHub Copilot
We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions), on September 1st, 2026: Model Deprecation date…
Imagine Video 1.5 with References
Our best video model, now with text, image, and voice references — generating up to 1080p.
Gemini 2.5 Pro and Gemini 3 Flash deprecated
As of today, July 31, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Model…
Enterprise teams model policy targeting in public preview
You can now take advantage of user-based model policy targeting for GitHub Enterprise customers with Copilot Business or Copilot Enterprise licenses. This feature empowers AI administrators to set a baseline…
Agent and Model Evaluations in Gemini Enterprise Agent Platform are now GA
Agent Platform's evaluation service is now generally available, providing developers with a unified engine to measure agent quality consistently across local development experiments and live production traffic. You can evaluate agents using over 20 pre-built metrics, DeepMind-backed adaptive rubrics, or custom code-based and LLM-as-a-judge metrics stored in a centralized, versioned registry. The service integrates directly into existing workflows via the Agent Platform SDK, agents-cli, and ADK, offering built-in user and environment simulators to automate complex multi-turn testing and streamline CI pipelines.
Enable on-demand expertise with Agent Skills in Genkit Go
To prevent context window bloat and reduce token consumption, Genkit Go introduces Agent Skills based on a progressive disclosure architecture. Developers can package specialized instructions, scripts, and references into modular SKILL.md bundles where only the frontmatter metadata is initially exposed to the agent's system prompt. When a task matches the skill's description, Genkit's middleware dynamically loads the full instruction body and associated assets, ensuring the model accesses precise workflows exactly when needed.
Thursday
Thu · Jul 30 · 3 postsInvestigating three real-world incidents in our cybersecurity evaluations
GitHub Copilot in Visual Studio Code, July 2026 releases
This changelog covers VS Code v1.127 through v1.131, shipped throughout July 2026. These releases improve how you work with agents, review changes, use chat, and navigate VS Code. They also…
Limit remote control to managed devices
Enterprises and organizations can now restrict which devices are eligible to host remotely controlled Copilot sessions, giving administrators fine-grained control over where remote control access is permitted. The new remoteControl…