Inspired by Tiny Little Office, Simon Willison used Claude Code (Opus 5.5 Extra) to build a LaTeX renderer tool that renders LaTeX source as MathJax-formatted equations or faster-latex-formatted full documents, and stores content in a URL #fragment for shareable links.
Two engineers built Stack Overflow for Agents with Codex in a few weeks; its ChatGPT plugin drove up to 10× growth in agent creation, and signups grew threefold as a result.
OpenAI's ChatGPT Chrome extension has been upgraded to directly access and act on open browser tabs. Users can target tabs with @chrome, Chat mode can summarize data across multiple tabs, and Work mode uses Computer Use to send messages, fill forms, download files, or group tabs; official examples include comparing products across tabs, summarizing articles, and comparing prices. The upgraded sidebar shows full chat history, and the extension is available on all ChatGPT plans.
OpenAI upgraded ChatGPT's Google Chrome extension: typing @chrome in the ChatGPT web or desktop app lets the model view currently open tabs. New capabilities include filling spreadsheets or forms with content from multiple tabs and comparing products or services. ChatGPT Work can also control Chrome tabs to send messages, fill forms, download files, and organize tabs into groups, and ChatGPT in the sidebar can use full conversation history within a page.
AWS released its Trust in Depth methodology, which lets agents operate safely without per-step human approval through four layers: Scope (limiting capabilities and access), Know (Agent Registry and independent identities), Bound (AgentCore Policy enforced at the Gateway, Guardrails, and the open-source sandbox Strands Box), and Observe (CloudWatch Omni tracking and evaluation).
At its first Config event in India, Figma launched Figma Specs, a Markdown editor that lets teams and agents follow a unified design language, design libraries, and codebases, and opened code layers for public testing.
A multi-agent intelligent document processing (IDP) system built on Amazon Bedrock AgentCore can automatically classify, extract, verify and learn from business documents. The solution uses Strands Agents to orchestrate 8 specialized agents, with Amazon Textract for text extraction and S3 Vectors for vector matching; new document types go through a training workflow that generates and saves extraction instructions for reuse, while known types go straight through the automated pipeline.
This AWS tutorial shows how to build an AI agent system with Amazon Bedrock AgentCore that automatically turns quarterly reports, compliance documents and market analyses into client PowerPoint presentations; in internal testing the whole process took under 90 seconds.
Anchor Browser integrates with Amazon Bedrock AgentCore payments, letting AI agents autonomously pay for paywalled pages, APIs, and MCP servers via the x402 protocol when they encounter HTTP 402 Payment Required responses, within a configured budget.
GitHub released the Copilot app for Beginners tutorial series, covering four ways to give Copilot project context, including .github/copilot-instructions.md custom instructions.
Why it matters: GitHub's official tutorial lays out four mechanisms for giving Copilot project context and when to use each, so readers can combine them as needed in their own repos.
Amazon Bedrock launched a public beta of OpenAI-powered Managed Agents and added new models including GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Luna, Claude Opus 5.5 and Kimi K3.
The AWS machine learning blog explains how Incarna uses Amazon Bedrock AgentCore payments to let agents pay BlockRun per inference for model calls via the x402 protocol, a flow already in production on the Base network (USDC).
Google announced at a Google Cloud event a unified agent for Gemini that can accept goals rather than instructions, autonomously plan tasks, use skills and tools, and connect to enterprise internal systems.
AWS demonstrated how to build automated remediation workflows using AWS Lambda Durable Functions, Amazon EventBridge, and Amazon Bedrock, connecting to the troubleshooting results from AWS DevOps Agent.
In a Latent Space interview, Kubernetes founders Craig McLuckie and Joe Beda discuss their company Stacklok and its cloud-native agent harness Mecatl, which applies Kubernetes-style thinking to running agents in the cloud.
According to Ars Technica, over the past five months Google and four other organizations have acknowledged vulnerabilities exploiting MCP: an attacker hijacks one agent inside a target network and uses chained prompt injection to spread malicious instructions to other internal agents, such as stealing databases and sensitive information.
OpenAI and Ironclad are training and evaluating AI agents on complex contract workflows to advance computer use capabilities for professional work. The partnership focuses on agent performance in real contract scenarios, helping improve AI reliability in professional software operation.
Amazon Quick resources (chat agents, action connectors, knowledge bases, flows, spaces) previously had to be manually rebuilt when promoted from development to production accounts.
The aws-ai-ml skill, delivered via the Agent Toolkit for AWS, brings optimized generative AI inference on Amazon SageMaker AI to coding agents such as Kiro, Claude Code, and Codex, injecting inference optimization and benchmarking expertise.
This AWS tutorial shows how to build a voice travel concierge for an airline app using Amazon Bedrock AgentCore, Amazon Nova 2.5 Sonic, and Amazon Bedrock Knowledge Bases, supporting seat changes, meal preference updates, policy questions, and handoffs to human agents.
The AWS machine learning blog introduces the Adjudicated Query design pattern, which lets business users ask compliance questions through the Amazon Quick chat interface while pass/fail determinations are still made by a deterministic rules engine, with the model only translating questions and narrating results.
Using Amazon Bedrock AgentCore Gateway, Claude Desktop can connect to fully managed Web Search—an MCP-compatible search capability built on Amazon's web index covering tens of billions of documents, with all query traffic staying inside AWS infrastructure and no external API keys to manage.
Earendil's agent framework Pi released Pi 1.0 and Pi Durable, both of which made the HN front page.
AWS Professional Services built a four-agent pattern based on the Strands Agents SDK and running on Amazon Bedrock AgentCore, using AgentCore Gateway with MCP tools to connect migration input and output systems.
AWS provides an end-to-end reference implementation for ambient agents on Amazon Bedrock AgentCore: an event (such as an S3 upload) triggers an agent on AgentCore Runtime to run a workflow, pausing for human input via a single ask_human tool whenever approval or clarification is needed, then resuming from where it left off.
AMD launched AMD Ross™, an agentic AI assistant covering the entire embedded development cycle, including architecture design, optimization, debugging, PCB design, schematic review, software and deployment. It connects to AMD Embedded tools via an MCP server, and bundles the AMD Knowledge Base, expert-written agent skills and runnable design examples, supporting natural-language document queries, command execution and workflow automation.
A Hugging Face team has proposed ProvenanceGuard, a source-aware factuality verification layer for MCP agents, which checks after generation whether the sources supporting each claim match the sources the answer states or implies, identifying cross-source confusion.
An official GitHub tutorial shows how to build custom workflows with canvases in the GitHub Copilot app: run the /create-canvas skill in an agent session, describe the workflow, user actions, and agent actions in natural language, and the agent generates boards, checklists, dashboards, and other interfaces that open in the side panel.
Why it matters: The tutorial covers the three elements of /create-canvas and its two-way collaboration mechanism, so readers can turn their own workflows into reusable canvases.
Antonio Morales of GitHub Security Lab has released Fuzzing Taskflow, an autonomous fuzzing pipeline for C/C++ projects built on the Taskflow Agent — you only specify a GitHub repository, and it automatically identifies entry points, analyzes the build system, writes harnesses, runs AFL++, and triages crashes.
Why it matters: The author explains the design of the automated fuzzing pipeline, showing how LLM agents can take over manual steps like coverage analysis and crash triage.
The GitHub Podcast breaks down five common AI hot takes one by one. Key conclusions: AI-generated code still needs review scaled to risk; Skills and MCP solve different problems, with MCP providing a standard for tool and data access while Skills package team workflows and best practices in Markdown, making them complementary; RAG is not dead—retrieval brings models closer to answers and can coexist with agents, MCP, and Skills in the same workflow.
Mistral has launched Studio, a unified system of record for enterprise Prompts and Skills, enabling versioning, clear ownership and traceability.
Mistral released the Apache-2.0 open-source model Leanstral 1.5, with 119B total parameters and 6B activated parameters, trained via mid-training, supervised fine-tuning and CISPO reinforcement learning.
Why it matters: The official post discloses the full training pipeline, benchmark figures and real code verification cases, letting readers gauge how practical formal verification models are for mathematical proofs and open-source bug finding.
Mistral AI has rolled out several new capabilities for Connectors: enhanced admin controls (GA) let organizations set connector access per workspace or org and toggle tools individually, while API keys with connector scopes (GA) prevent identity misuse in automated workloads.
Chrome released an agent-ready toolkit for developers, and Lighthouse gains a new Agentic browsing audit category from M150, checking three metrics: accessibility tree, CLS visual stability, and WebMCP integration.
Why it matters: The article details the specific checks in Lighthouse's new Agentic browsing audit and Chrome DevTools debugging methods, so developers can directly improve how agent-friendly their sites are.
Chrome officially launched third-party developer tools for Chrome DevTools for agents, letting libraries and frameworks expose runtime internal state, such as component hierarchy and server-side state, to AI agents via an event-based JavaScript API.
Chrome announced the WebMCP origin trial in Chrome 149, letting developers build structured tools for web apps that declare the purpose of buttons, input fields, and other UI elements and manage page state, so agents can complete tasks without guessing.
Why it matters: With the official WebMCP origin trial open, developers can let agents operate web forms and debugging flows via declared tools and submit API feedback.
Mistral AI released the public preview of Search Toolkit, an open-source framework for building production-grade search pipelines for AI applications, unifying ingestion, retrieval and evaluation in a single shared-interface framework.
Why it matters: The original details modules, evaluation metrics and enterprise case studies, helping readers judge whether it can replace their existing retrieval infrastructure.
Mistral released Connectors in public preview for Studio; both built-in connectors and custom MCPs can be used via API/SDK with all models and agent calls. New features include direct tool calls, human-in-the-loop approval flows, and programmatic management of connectors. Once centrally registered, connectors can be reused in LeChat and AI Studio, making it easy to connect to enterprise systems like CRMs and knowledge bases.
Mistral released Leanstral-120B-A6B (6B activated parameters), its first open-source coding agent for Lean 4 formal proof, with weights under the Apache 2.0 license and accessible via Mistral Vibe and the free labs-leanstral-2603 API endpoint.
Mistral AI launched 20+ secure MCP-powered connectors (beta) for Le Chat, covering tools such as Databricks, Snowflake, GitHub, Atlassian, Box, Stripe, and Zapier, enabling search, summarization, and actions, with support for connecting any remote MCP server and deployment on-premises, in your own cloud, or on Mistral Cloud.