The latest AI news, in focus.

Agents Are Going Async

Async subagents let an agent stay responsive while background workers run long tasks. How the orchestrator, notifications and approvals work in Deep Agents.

Quoting Ben Hylak

every product i use should just be a headless mcp, that feeds into an agent, where i never have to think about anything underneath.

How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents

Most proactive agents run on a simple cron. Learn what scheduled runs unlock, from memory to smart triage, and how to add them to Managed Deep Agents.

How to build evidence-grounded agent memory with OpenWiki and Graphs

LangChain used OpenWiki, its open-source wiki compiler, and an evidence graph to build a persistent memory layer that preserves knowledge for agents to reuse across tasks. Learn how.

How LangChain grew self-serve analytics questions 40x by giving its AI agent layered context

LangChain gave its Hex agent layered context, turning self-serve analytics questions from occasional to routine.

How We Built Our Design Agent

How LangChain built Content Studio, an open-source design agent in Slack that makes on-brand videos, graphics and decks, and the harness that powers it.

SAP advances its autonomous enterprise push with smarter, governed Joule agents

SAP SE today announced a set of artificial intelligence innovations at its annual TechEd conference for developers, enhancing its Joule assistant solutions and Business AI Platform, including tabular data foundation models. New capabilities in Joule Work will help AI agents become more efficient and interoperate with open protocols. In this case, the Model Context Protocol […] The post SAP advances its autonomous enterprise push with smarter, governed Joule agents appeared first on SiliconANGLE.

Groundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock

Every time an agent takes a step, it re-reads its entire context before acting. Here is how prompt caching for OpenAI models on Amazon Bedrock lets your agent remember, cutting input cost and latency without resending the same tools, instructions, and history every turn.

Context Engineering (Agent Memory) for AI Agents Starts with Retrieval

Agents waste time and context on clumsy searches, oversized results and stale data. Learn the retrieval techniques LangChain's Deep Agents harness uses to get the right context in.

Context Engineering with Deep Agents: How To Remember Without Keeping Everything In Context

Long-running agents degrade as context piles up. Learn how offloading, summarization, skills, subagents, and memory keep your agent's context window focused.

How DocuSign cut analytics engineering time in half by pairing Claude Code with dbt v2, dbt MCP, and agent skills

DocuSign wired Claude Code, dbt Agent Skills, dbt MCP, and dbt v2 into one workflow and measured a 50% productivity gain.

How to solve dashboard debugging in six minutes with an MCP-connected AI agent

An AI agent used dbt lineage from inside the BI layer to answer three data mysteries in the time it takes to get coffee.

LangChain releases the five core components of its “Enterprise-Level Agent Framework”

On October 25, 2026, LangChain published a blog post systematically outlining the five universal architectural principles it has distilled from deploying AI agents (GTM Agent, OpenSWE, Content Studio) within its marketing, sales, and engineering teams: native integration with the work environment (Slack), a dynamic identity model (OBO + fixed credentials), a two-tiered memory mechanism (global/user-level), sandboxed code execution, and a high proportion of scheduled operations (not manually triggered). All agents are built on the Managed Deep Agents platform.

Why it mattersThis information originates from the official LangChain blog, published on 2026-10-25T18:06:32.000Z—earlier than the current system time of 2026-10-25T23:01:18.857Z. The content focuses on implemented internal agent practices, with specific details such as Slack thread isolation, GitHub account attribution logic, and tiered permissions for Notion/Twitter, without including unverified predictions or external claims, thus meeting requirements for timeliness and factual accuracy.

Microsoft open-sources Agensh: a decentralized framework that supports 1024 autonomous, collaboratively operating AI coding agents.

On October 25, 2026, Microsoft Research open-sourced Agensh, a multi-agent runtime framework that operates without a central coordinator, enabling 1 to 1,024 LLM-powered coding agents to self-organize and collaborate on ProgramBench. The system achieves decentralized coordination through shared dashboards inspired by Gitea, Mattermost, and DeLM, with all agents following the same prompt-driven five-step loop; its scalability has been validated in a Linux + Docker environment.

Why it mattersThis achievement represents a significant evolution in multi-agent system architectures—abandoning the traditional “master‑agent” paradigm and enabling large‑scale self‑organization through prompt engineering and lightweight service composition. Empirical results on ProgramBench (e.g., 128 agents achieving a 49% improvement in task load balancing across five tasks) establish a new benchmark for distributed AI engineering. Released under the MIT License and compatible with mainstream single‑agent tools such as Copilot CLI, it offers valuable guidance for practical development.

Anthropic open-sources the OS-level sandbox sandbox-runtime: providing container-free file and network isolation for AI agents.

On October 24, 2026, Anthropic open-sourced sandbox-runtime (srt), an OS-level sandboxing tool that operates without containers, designed to restrict file read/write and network access permissions for AI agents, MCP servers, and CLI tools. It supports macOS (Seatbelt), Linux (bubblewrap), and Windows (alpha), with npm package version 0.0.81 under the Apache-2.0 license.

Why it mattersThis tool represents a significant advancement in AI security infrastructure—achieving fine-grained, full-process-tree coverage through the operating system’s native isolation mechanisms, directly addressing the risks of prompt injection and privilege escalation, and has already been deployed for internal validation within Claude Code.

Bayer Crop Science has built the multi-agent decision-making engine ADE based on Amazon Bedrock AgentCore.

Bayer Crop Science has built the Agentic Decision Engine (ADE) on Amazon Bedrock AgentCore—a natural-language multi-agent platform for breeding experts, analysts, and researchers—as an enhancement layer rather than a replacement for its existing Connected Decision Engine (CDE). The system is now live in production, serving over 100 R&D users and enabling approximately 80% of issues to be resolved independently through 22 domain-specific agents and about 20 API tools.

Donating Agent Skills to the Agentic AI Foundation

Donating Agent Skills to the Agentic AI Foundation News today from Anthropic: We’re committed to keeping Agent Skills open, community-driven, and vendor-neutral. Today, we are donating the standard to the Agentic AI Foundation (AAIF) under the Linux Foundation, which we co-founded with Block and OpenAI last year, and to which we donated the Model Context Protocol (MCP). I'm pleased to note I called this one last December, when Anthropic first declared skills to be an "open standard": I wouldn't be surprised to see this end up in the AAIF, recently the new home of the MCP specification. Fun side note: since my blog content is available to Claude via the datasette-mcp plugin I found that post by prompting Claude to "Use simonwillison.net MCP to find if I ever talked about how I want skills t

A Multi-Layered Approach to AI Agent Hallucination Detection: A Practical Framework for Production Environments

This paper systematically categorizes four typical types of hallucinations exhibited by AI agents in real-world workflows—factual, contextual, fictional, and self-contradictory—and proposes that detection should rely on a multi-dimensional approach, incorporating credibility checks, source verification, self-consistency assessment, semantic entropy analysis, and human–machine collaboration thresholds, rather than on a single scoring metric. It underscores that such detection must be embedded within the workflow’s closed loop and deeply integrated with observability, error handling, and human review pathways.

Deep Insight: How AWS’s Open-Source Multi-Agent System Addresses Five Major Production-Grade Challenges

AWS Solutions Architecture Team has launched Deep Insight, an open-source multi-agent system designed for automated CSV data analysis and natural-language report generation. It systematically addresses five common challenges in production environments—agent orchestration, role-based model selection, stable operation, secure code execution, and observability—and has been validated in real-world scenarios such as LG Electronics and the re:Invent 2025 TechRecon.

AWS releases the Adaptive Agent Framework (AAIF): a hierarchical AI task scheduling solution that enables edge-cloud collaboration based on Strands Agents.

AWS has introduced the Adaptive Agentic Intelligence Framework (AAIF), which leverages Strands Agents to build a hierarchical agent architecture. It dynamically routes tasks via local small language models (SLMs): routine IoT telemetry and visual analytics are executed at the edge, while complex reasoning is offloaded to Amazon Bedrock’s large cloud-based models. The framework supports hybrid deployment, keeps costs under control, and incorporates responsible AI governance recommendations; however, it currently exists as a proof-of-concept implementation and does not yet provide third-party validation or commercial deployment data.