AI Agent News from Official Blogs and Changelogs
Announcements about AI agents and coding tools from the blogs and changelogs of AI labs and tool makers.
-
Building an evidence-grounded agentic security operations harness on Cloudflare
Cloudflare Managed Defense uses specialized AI agents on Workers to analyze security alerts with grounded recommendations based on network telemetry and evidence collection.
-
Beyond hours saved: Building the business case for agentic automation
AWS provides a framework for calculating the full business value of agentic automation, including time savings, exception handling, decision quality, and maintenance costs.
-
Automate remediation post AWS DevOps Agent investigation
AWS DevOps Agent investigation summaries can be converted into pre-validated remediation fixes using Lambda Durable Functions, EventBridge, and Bedrock.
-
How Cornerstone OnDemand cut database diagnosis by 78% with Amazon Bedrock
Cornerstone OnDemand built Orion AI, a multi-agent system using Amazon Bedrock and Strands Agents, reducing database diagnosis time from 45 minutes to 10 minutes.
-
Update your IDE to restore agent activity in Copilot usage metrics
GitHub is rolling out a fix to restore agent activity metrics in Copilot usage tracking after a bug caused agent metrics to appear lower than actual usage.
-
Building Git infrastructure for agent-scale development
GitHub describes infrastructure improvements to handle increased write volume from agent-scale development.
-
Building a context-aware AI assistant on AgentCore and OpenClaw
Tutorial on building a context-aware AI assistant using OpenClaw on Amazon Bedrock AgentCore, with persistent memory across conversations.
-
Advancing computer use with Ironclad
OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use capabilities.
-
Mistral Large 4 now available on AI Gateway
Mistral Large 4, an open-weight multimodal model, is now available on Vercel's AI Gateway and accessible via the AI SDK.
-
Remote control for local agents
Cursor iOS app now allows users to see and control local agents running on their computer remotely.
-
Secret scanning adds detectors for Lovable, Supabase, and more
GitHub secret scanning now detects secrets from Lovable Labs, Pydantic Services, and Supabase.
-
Supercharge regulated workloads with Claude Code and Amazon Bedrock
Claude Opus 5.5 and Sonnet 5.5 are now available on Amazon Bedrock in GovCloud regions for use with Claude Code on regulated workloads.
-
New agent skill: Amazon SageMaker optimized generative AI inference for your coding agent
Amazon SageMaker introduces an aws-ai-ml skill for coding agents like Kiro and Claude Code to optimize generative AI inference.
-
ReviewBench: An open benchmark for AI code review
GitHub launched ReviewBench, an open benchmark for evaluating code review agents using real pull requests and production-aligned metrics.
-
Agentic retrieval with LangChain and Amazon Bedrock Knowledge Bases
AWS published guidance on building agentic retrieval applications with LangChain and Amazon Bedrock Knowledge Bases for multi-part questions.
-
Evaluating multi-agent systems for explainability and helpfulness with Amazon Bedrock AgentCore
AWS documented evaluating multi-agent systems using Amazon Bedrock AgentCore with built-in and custom evaluators for supply chain decisioning.
-
The Agent Said It Was Done. The Database Disagreed.
-
Selected models in GitHub Copilot deprecated
GitHub Copilot deprecated selected models across all experiences including chat, inline edits, and agent modes as of October 2, 2026.
-
A model guide for the GPT-6 family
OpenAI published a guide for choosing GPT-6 models, tuning reasoning, improving prompts, coordinating tools, and preparing workflows for production.
-
Fine-tune a search agent with multi-turn RL on Amazon SageMaker AI
AWS demonstrated fine-tuning a search agent with multi-turn reinforcement learning on SageMaker AI to improve retrieval quality and reliability.
-
GitHub Copilot weekly releases — September 28
This week, put Copilot to work with new models, reusable workflows and desktop app automation, plus Azure canvases and VS Code improvements. GitHub Copilot Claude Sonnet 5.5 is available to… The…
-
AutoSynthData: Generating Training Data for Enterprise Agents
-
How Rogo ships agent-written code to production in 5 minutes on Vercel
Rogo deployed agent-written code to production in 5 minutes on Vercel, running 73,000+ deployments monthly with six production AI agents.
-
Scaling cloud migrations with agentic AI on Amazon Bedrock AgentCore
Learn how AWS Professional Services uses a multi-agent framework built on Amazon Bedrock AgentCore to automate enterprise cloud migrations end to end. Purpose-built AI agents handle discovery…
-
Build agent memory with NVIDIA NeMo Agent Toolkit and Amazon S3 Vectors
Learn how to use Amazon S3 Vectors as the persistent memory layer within the NVIDIA NeMo Agent Toolkit (NAT), deployed on Amazon Elastic Kubernetes Service (Amazon EKS). This post shows how NAT's…
-
Building ambient agents with Amazon Bedrock AgentCore: From event-driven signals to human-in-the-loop workflows
Ambient agents respond to events such as an Amazon S3 upload, a schedule, or an alert instead of waiting for a chat prompt. This post walks through building framework-agnostic ambient agents on…
-
Cloudflare OS: your company’s agent workspace, managed for you
Cloudflare OS gives everyone in your organization an agent workspace that knows how your company works and connects to its data and systems. We’re opening the waitlist for fully managed deployments…
-
The Den frees up 10-15 hours a week to grow with ChatGPT Work
As it opens a new location, the social club prepares grant applications in 2 hours instead of 3 days and liquor-license materials in 3 hours instead of 4 days.
-
Vercel Agent now installs private packages from npm and custom registries
Vercel Agent can install private dependencies from npm and custom registries using credentials stored as shared environment variables on Vercel. npm , pnpm , and classic Yarn running in Agent…
-
You can now top up your n8n Assistant credits
On n8n Cloud, you can now buy extra Assistant credits when you run out - manually or with auto top-up. Here's how it works.
-
Gemini 4 Argon: our next era of frontier intelligence
-
Build a multi-agent music production pipeline on Amazon Bedrock AgentCore Runtime Instances
Amazon Bedrock AgentCore Runtime Instances gives multi-agent workflows AWS managed EC2 infrastructure with GPUs, persistent volumes, and multi-day sessions. In this post, we deploy a three-agent…
-
Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents
-
DevDay 2026 Recap
Explore more than 20 announcements from OpenAI DevDay 2026, including GPT-6 Astra, ChatGPT, Codex, APIs, security, and new tools for builders.
-
Introducing GPT-6.1 Sol
Meet GPT-6.1 Sol: near-Astra intelligence for coding, computer use, and professional work at one-fifth of Astra’s standard API input and output token prices.
-
GPT-6.1 Sol now available on AI Gateway
GPT-6.1 Sol from OpenAI is now available on AI Gateway. It improves on GPT-6 Sol for coding, computer use, and professional work, including reading complex documents and carrying out multi-step…
-
How we found 24 Android vulnerabilities using our open source AI security agent
A look at the targeted AI taskflows behind these findings, the critical Android bugs they uncovered, and how to run the same open-source agent on your own app. The post How we found 24 Android…
-
Holo4: powering generalist computer-use agents
-
Basis completes a tax workbook 2x faster with GPT-6 Astra
GPT-6 Astra completed a 50-tab tax workbook twice as fast as GPT-5.6 Sol, and its stronger understanding of user intent gives Basis more confidence in real-world use.
-
Are you a Codex Original?
We’re collecting real stories of builders, tinkerers, researchers, and creators who are using Codex to do incredible things. If you want to be a part of the next chapter of the Codex Originals…
