What shipped & dropped across AI labs, today.
Yesterday
Wed · Sep 9 · 3 posts
Enterprise managed permissions for GitHub Copilot agent operations
If you administer GitHub Copilot Business or GitHub Copilot Enterprise, you can now centrally control which agent operations are blocked, require human approval, or can proceed without a prompt. Managed…
The Anatomy of Harness Engineering: How to Evaluate, Iterate, and Guard AI Coding Agents
While end-to-end benchmarks like SWE-bench provide broad performance scores for AI agents, they are often expensive, slow, and lack the root-cause diagnostics needed to explain exactly where an agent's logic broke down. To solve this, developers should adopt behavioral evaluations—fast, local, unit-style tests that assert on discrete intermediate actions, such as verifying specific tool calls or file modifications rather than final string equality. By building these inexpensive micro-checks alongside macro benchmarks, engineering teams can confidently iterate on system prompts and upgrade models without the risk of regressions.
Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond
Google has officially released version 1.0 of the Agent Development Kit (ADK) for Kotlin, achieving full feature parity with the Python and Java ADK cores to enable idiomatic, multi-agent AI development. Built on Kotlin Multiplatform (KMP), the framework leverages Kotlin Symbol Processing (KSP) for zero-reflection, type-safe function calling, alongside advanced orchestration capabilities like human-in-the-loop workflows and context compaction. Additionally, the release introduces a robust suite of Android-first extensions, allowing mobile developers to integrate local models via LiteRT-LM, cloud reasoning through Firebase AI, session persistence using Room, and semantic memory powered by AppSearch.
Tuesday
Tue · Sep 8 · 2 postsEnterprise-managed sandbox in Copilot for JetBrains
This update brings support for enterprise-managed sandbox policies, cross-file cursor jumps for next edit suggestions, global project context in chat, enterprise policy diagnostics, and a new connection between terminal Copilot…
Reducing cost and improving performance with Claude Platform
Tuning prompt caching, instructions, and effort can reduce Claude's cost without sacrificing application performance.
Friday
Fri · Sep 4 · 4 postsGitHub Copilot weekly releases — August 31
This week, GitHub Copilot expands model choice while VS Code adds new ways to manage agent sessions and get pull requests merge-ready.
GPT-6 Astra is generally available in GitHub Copilot
GPT-6 Astra from OpenAI is now available in GitHub Copilot. OpenAI’s latest general-purpose model, GPT-6 Astra, is designed for long-horizon, autonomous coding and agentic tasks. In our internal testing, GPT-6…
Setting Grok Bot loose on procurement
We gave Grok Bot access to vendor spend, contracts, and usage data. It found more than $100,000 in direct savings.
Driving Developer Excellence: Inside the Program Sprints
The Gemini Enterprise Developer Experience (DevEx) program conducts ongoing sprint testing of end-to-end developer workflows to identify and rapidly resolve friction points without relying on internal shortcuts. This recent sprint focused on optimizing enterprise AI governance, including refining setup prerequisites, securing extension configurations, and clarifying policy enforcement mechanics to ensure a smoother, more reliable deployment. Developers can now leverage updated documentation and standardized code samples to improve their experience with Agent Gateway and Semantic Governance configurations.
September 3
Thu · Sep 3 · 5 postsGrok Bot for Enterprise
Grok Bot is now available for enterprises. Grok and Cursor Enterprise customers have free usage for the next two weeks, and can invite their whole organization, including people without an existing seat.
Gemini 3.8 Flash is now available in GitHub Copilot
Gemini 3.8 Flash, Google’s latest Flash model, is now available in GitHub Copilot. In our early testing, Gemini 3.8 Flash performed strongly on complex terminal-based coding tasks and demonstrated rigorous…
Upcoming deprecation of selected GitHub Copilot models
We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) on October 2nd, 2026: Model Deprecation date…
Designing Grok Bot for a world of persistent agents
How we designed Grok Bot for agents that persist beyond a single session — from a chat history to a Bot roster, presence, a computer of the Bot’s own, and work that starts without a prompt.
Reopening Copilot Business and Enterprise signups
We’re gradually reopening sign-ups for Copilot Business and Copilot Enterprise customers paying by credit card or PayPal over the next couple of weeks. If you’ve been waiting to get started…
September 2
Wed · Sep 2 · 6 postsContent exclusions generally available in Copilot app and CLI
The GitHub Copilot app and Copilot CLI now respect content exclusion policies configured by enterprise, organization, and repository administrators.
Self-hosted machines
Cursor supports self-hosted machines, which let you keep tool execution entirely in your own network. Your codebase, build outputs, and secrets all stay on internal machines running in your infrastructure, while the agent handles tool calls locally. #Dynamic pool scheduling My Machines connects a single laptop or VM to your account for personal workflows. Team pools are named queues of workers for a team or enterprise. Capacity can grow as requests arrive and shrink when workers disconnect, so your self-hosted machines can scale with demand. Pools are not tied to one repository: name the pool, and any available worker can claim the request. Pools can also hibernate idle machines, then restore within a reconnect window when a follow-up arrives, so you don't keep expensive capacity warm just for the next prompt. #Run on your sandboxes Cloud agents can now execute on infrastructure you already use, including from AWS Lambda, Coder, Cloudflare, Daytona, Modal, Namespace, Vercel, and E2B. #Computer use on Linux and Mac Self-hosted workers now support computer use on Linux and Mac. With the right desktop packages, an agent can click, type, take screenshots, and drive the browser. You can watch its desktop or take control from Cursor.
Enterprise-managed settings support any default model
You can now set your preferred GitHub Copilot model as the default for new conversations through enterprise-managed settings. This lets you choose the default model that best fits your workflows.…
4 engineering patterns behind the strongest AI Agents Challenge submissions
The recent Google for Startups AI Agents Challenge revealed that the most successful multi-agent systems rely on foundational software engineering patterns rather than just raw model power. Winning architectures consistently implemented bidirectional MCP for seamless inter-agent communication, async event buses for parallel execution, strict unified validation for model fallbacks, and tiered routing to minimize expensive inference calls. By prioritizing these structural practices over simple linear prompt chains, developers can build more resilient, low-latency, and cost-effective agentic workflows.
Building commerce agents with Claude
We're launching a blueprint to help build commerce agents on Claude. It contains the harnesses, patterns, and guardrails an engineering team needs to get a commerce agent running in days.
A guide to the anatomy of effective commerce agents
The architecture, latency & cost techniques, and eval practices for agents that make it easier to buy and sell online.