Amazon SageMaker AI launched the aws-ai-ml skill through Agent Toolkit for AWS, giving MCP-enabled coding agents such as Kiro, Claude Code, and Codex inference-optimization and benchmarking capabilities. They can benchmark endpoints, recommend deployment configurations, compare performance, and generate executable SageMaker Python SDK v3 code.
Cross-account resource migration in Amazon Quick can be automated with an MCP server deployed on Amazon Bedrock AgentCore. It supports one-click migration of chat agents, action connectors, knowledge bases, flows, and spaces from a development account to a production account.
The Microsoft Copilot Studio team and Hugging Face jointly released ThinkingBox. It runs agents in isolated MCP tool sessions and then performs executable checks on final backend state and side effects, rather than judging only the final reply or whether tool calls were allowed.
Why it matters: The agent benchmark from Microsoft and Hugging Face uses 507 stateful workflows and 20 repeated runs, shifting the focus from tool calls to the final database state.
Anthropic released Mods for Claude Code, a middleware layer that runs inside the tool. Developers can use JavaScript or TypeScript functions to hook into events such as tool calls, user prompts, and UI rendering, adding custom panels, intercepting tool calls, or connecting new commands.
Why it matters: Anthropic added plugin-style Mods middleware to Claude Code, showing how it changes extensibility and permission risks in coding tools.
Amazon Bedrock AgentCore Gateway can connect Claude Desktop to web search backed by Amazon's web index. Query traffic stays within AWS end to end, with no external API key required.
AWS proposed the Adjudicated Query design pattern, in which business users ask compliance questions in the Amazon Quick chat interface while a deterministic rules engine makes the actual decision. An integrity receipt ensures that the sum of compliant, noncompliant, ambiguous, and unreadable records equals the total scanned, preventing records from being silently skipped. The pattern applies to high-risk cases such as lease compliance, sanctions screening, and insurance claims.
Airbnb CTO Ahmad Al-Dahle described the company's shift to becoming AI-native: AI now writes 60% of its code, feature delivery has grown nearly 80% year over year, engineering PR throughput per person is about 1.6 times higher, and AI resolves about half of customer-support tickets independently.
Earendil released Pi 1.0 and Pi Durable, both of which reached the Hacker News front page. Pi 1.0 adds native MCP, Jev, and image-model support in Codemode; virtual-model extensions; lazy tool loading; Anthropic model-cache warming; system messages in the middle of conversations; a new TUI theme; and full-screen mode by default.
AWS Professional Services uses a four-agent pattern to reduce infrastructure-as-code development per application from three to four weeks to minutes. Built with the Strands Agents SDK and running on Amazon Bedrock AgentCore, the pattern connects source and target systems through MCP tools exposed by AgentCore Gateway.
Amazon Bedrock AgentCore supports building 'ambient agents' that listen to event streams such as Amazon S3 event notifications, EventBridge rules, and Lambda triggers and perform tasks automatically. When needed, they pause for human approval through a single ask_human tool and resume from where they stopped.
Josh Woodward shares Stitch’s CLI announcement, describing it as a way to get design ideas on demand. @stitchbygoogle introduces the @google/stitch CLI, which connects to local coding agents, generates screens and design systems, and sends local dev server snapshots to Stitch. Users can access it from the terminal or ask a harness such as @antigravity.
MCP is making a strong comeback! You can now use them to connect your data to https://hf.co/chat?mode=ml-intern
Airbnb launched AI search in its fall update this week. CEO Brian Chesky says chatbots are not suited to e-commerce, and the company will explore multiplayer AI interfaces over the next three to six months. He believes the industry lacks an operating system truly built for AI: AI should run at the kernel level. Airbnb plans to make its app more agentic and connect it to other agents through MCP.
After OpenAI DevDay, Latent Space interviewed Ari Weinstein, who leads computer-use product and engineering, and Nikunj Handa, head of API product.
An AWS blog post provides a full tutorial for deploying a multi-agent music-production pipeline on Amazon Bedrock AgentCore Runtime Instances. Three agents handle composition, delivery, and compliance, sharing a session through the same runtimeSessionId and colocating on one GPU instance.
Amazon Bedrock Knowledge Bases added the AgenticRetrieveStream API, which breaks claims questions into subqueries, retrieves information over multiple rounds, and returns cited answers.
GenFlow 1.0, launched jointly by Baidu Wenku and Baidu Netdisk, has been given the Chinese name Kuku AI and released as a standalone product. It enters tasks such as writing papers, making presentations, and generating industry reports as a general-purpose AI agent. The enterprise version has attracted 3,000 trial companies shortly after launch, with faster adoption among small and midsize businesses. Its international version has been refreshed as Kooko by Oreate AI and surpassed 10 million overseas users within a year.
Leiphone compared OpenClaw 2.0 (v2026.8.1), released August 31, with version 1.x, v2026.7.1-2. Both ran the same research, report, and visual webpage task on the same server with the same GLM 5.3 base model.
Stanford's HomeBody project connects GPT-6 Astra to a Unitree G1 in a kitchen, where it follows language instructions to gather coffee bags, throw away a carton, and get medicine from a drawer to hand to a person. The system works in three stages: it first explores the kitchen and saves camera images, lidar, and joint poses as spatial memory; then reconstructs a digital kitchen in Isaac Sim; finally Astra uses images, maps, and memory to call navigation, grasping, placing, and drawer-opening skills.
Manus, which announced a return to independent operations on September 1, released its first major update since returning: Manus 2.0, including a new agent foundation, a creative workspace, and Cue, a new personal agent app.
Why it matters: This is Manus's first major update since becoming independent again, showing its product approach to giving personal agents an identity and enabling group collaboration.
Doubao announced support for several travel services. Users can book flights and train tickets, hail a ride, and get route directions through natural-language chat without switching between apps. The update adds travel to existing hotel and restaurant bookings. Flight and train tickets are provided by Flight Master and High-Speed Rail Butler, ride-hailing connects to services such as Cao Cao Mobility, and Baidu Maps and others support navigation. A dedicated 'Travel with Doubao' entry point is now available.
Anthropic released Claude Sonnet 5.5. API prices are unchanged and generation is faster, while its scores rose substantially on agent benchmarks such as Terminal-Bench and CursorBench.
OpenAI announced expanded ChatGPT extension capabilities at DevDay. Developers can create dedicated entry points for apps in ChatGPT’s sidebar and build interactive panels that let users operate tools directly in a conversation. Panels can also include file viewers for formats supported by the product.
At DevDay 2026 in San Francisco, OpenAI announced 25 updates spanning ChatGPT, Codex, GPT-6 models, and the API.
Why it matters: The overview explains how Dots, GPT-6.1 Sol, Codex, and the Agents API fit together among OpenAI’s agent products.
OpenAI announced a series of ChatGPT updates at DevDay, including the Plugin Extensions system, shared ChatGPT Space workspaces, collaborative Pages, Slack and Microsoft Teams integrations, automated workflows, new pricing tiers, and the enterprise-focused OpenAI Marketplace.
Why it matters: OpenAI’s rollout of extensions, collaboration spaces, and an enterprise marketplace indicates ChatGPT’s shift from chatbot to platform.
Wabi, founded by Replika creator Eugenia Kuyda, announced this week that it is pivoting to an AI messaging app with Wabi 2.0, described as a “personal agent that can do things for you and instantly build the interface you need.” After a user gives it a task, the agent can generate interfaces on demand for calorie tracking, weightlifting logs, children’s activity calendars, and other uses, placing each in a relevant thread such as health or family. Wabi 2.0 is currently available by invitation codes distributed on X.
At DevDay 2026, OpenAI launched always-on agent Dots, which can autonomously handle tasks such as fixing bugs reported in Slack and sending forgotten invoices. It also introduced the cheaper GPT-6.1 Sol; its higher-end GPT-6.1 Astra was held back over safety concerns.
Why it matters: OpenAI introduced always-on agent Dots at DevDay 2026 and gave comparisons with Meta Muse and details on staged availability.
Perplexity introduced Automations in Perplexity Computer, a feature for ongoing work that can take action in response to event-based triggers or on a schedule. Perplexity says Automations work with your memory, skills, and connected apps including Slack, Gmail, Outlook, and Linear.
Prompt engineering determines how well Amazon Quick's AI features respond to natural-language requests, spanning custom agents, automated workflows, and conversational data analysis. The article presents general principles and the structured CRISPE framework, emphasizing specificity, business context, and examples. It uses enterprise scenarios such as customer-service efficiency analysis to show how to reduce iteration and improve first-pass accuracy.
AWS breaks down prompt-writing approaches for Amazon Quick components: Quick Research needs a clear objective, audience, and focus area, with sub-questions decomposed and data sources constrained; Quick Flows should specify timing, data sources, calculations, and delivery goals, using numbered steps for complex logic and conversational iteration for revisions; Quick Sight queries should state the business question, metrics, dimensions, and visualization preferences.
Hugging Face has published the ProvenanceGuard paper, describing a post-generation verification layer for MCP agents that preserves the identity of tool-output sources and detects cross-source confusion—claims that are true but attributed to the wrong source. On 281 real medical-agent traces, it blocked 138 of 139 claims experts said should be blocked, achieved about 86% source-identification accuracy, and scored highest among four comparison checkers.
Tencent's operating-system-level personal AI butler Marvis announced a repositioning four months after launch, shifting from “find an app” to “find a service” and explicitly taking on the role of managing users' digital assets over time. A new “Butler Team” appears in the sidebar; its PC Butler, co-developed with Tencent's Enterprise IT “8000” team, offers a Skill catalog covering 27 real-world operations scenarios across four categories.
Anthropic's Thariq Shihipar discusses the next phase of Claude Code on the Latent Space podcast, including Ask User Question, artifacts as persistent generative interfaces, multi-agent collaboration through Claude Tag and Projects, and Claude Mods for customizing the harness.
H Company has released the Holo4 agent-model family, with a 27B dense model and a 35B-A3B MoE model. Both are available through the H Models API, and weights are open on Hugging Face in BF16, FP8, NVFP4, and 4-bit GGUF formats.
Why it matters: Holo4 opens both its weights and complete evaluation traces, giving readers a basis to assess the cost and capability limits of general-purpose computer-use agents.
A canvas extension in the GitHub Copilot app is a customizable interface. Users can type the `/create-canvas` skill in an agent session and describe what they want in natural language to generate an interface such as a kanban board, launch checklist, or dashboard, without writing code.
The GitHub Copilot app has introduced canvas, a full-stack mini-app that runs inside the app without a browser shell, can communicate in both directions with the Copilot agent, and can call third-party APIs or run code locally. The company argues that chat is a general-purpose fallback, while a canvas can be a better fit when users have a specific task. For example, a SQLite canvas can operate on a database directly instead of having an agent repeatedly spend tokens on actions such as “stage and commit.”
GitHub Security Lab has released Fuzzing Taskflow, an autonomous fuzzing pipeline for C/C++ projects. Given a GitHub repository URL, it identifies entry points, analyzes the build system, writes a harness, runs AFL++, reads coverage reports and improves the harness, triages crashes, and produces vulnerability reports.
Why it matters: GitHub Security Lab hands harness writing, coverage analysis, and crash triage to an LLM agent, and has published the full implementation and instructions for running it.
Now Gemini can connect with 13 new apps like @adobe, @squarespace, @onepeloton, and more. Instead of switching between tabs, you can now grow your business, design assets, and plan your workouts all in Gemini. 🧵
Simon Willison has released the `llm-typesafe` plugin, version 0.1a0, adding support for TypeSafe AI's new Jev model. Install it with `llm install llm-typesafe` and configure an API key.
Kimi has renamed Kimi WebBridge to Kimi Browser Extension. Users can chat with Kimi in the browser sidebar and ask it to browse pages or fill out forms. For repetitive tasks, they can record a sequence of actions once and save it as a skill for Kimi to run later. The extension is available at kimi.ai/products/kimi-browser-extension and the Chrome Web Store.
