Search results for Agentdesign

Designing Agentic Systems Like Distributed Systems

Agentic development is rapidly becoming one of the most talked-about paradigms in software development. The talk is not just of using AI to assist in coding but of using systems wh...

Convention over configuration reaches a new level with agent skills. I built a tiny workflow orchestrator (ambler-ts, 52...

Google's Managed Agents API promises one-call deployment at the cost of execution layer control

At Google I/O, the company unveiled Managed Agents in its Gemini API — a service that promises to collapse weeks of agent deployment work into a single API call. It's also a sign t...

NeMo Agent Toolkit With Docker Model Runner

The year 2025 has been widely recognized as the year of AI agents. With the launch of frameworks like Docker Cagent, Microsoft Agent Framework (MAF), and Google’s Agent Development...

Anthropic wants to own your agent's memory, evals, and orchestration — and that should make enterprises nervous

Just a few weeks after announcing Claude Managed Agents, Anthropic has updated the platform with three new capabilities that collapse infrastructure layers like memory, evaluation,...

The Agent Economy Is Here — Why AI Agents Need Their Own Marketplace

The Agent Economy Is Here — Why AI Agents Need Their Own Marketplace AI Agents are starting to need each other's services. But there's no standardized way for them to discover,...

Beyond n8n for Workflow Automation: Agent Graphs as Your Universal Agent Harness

Originally published March 20, 2026, on LaunchDarkly Hardcoded multi-agent orchestration is brittle: topology lives in framework-specific code, changes require redeploys, and bottl...

Designing a team of agents

I continue to experiment with AI in the context of software engineering. I’m fortunate that my team supports me in exploring different ways to improve our daily work. This week, I...

Engineering Agentic Workflows: Architecting Autonomous Multi-Agent Systems With MCP and LangGraph

The Shift From RAG to Agentic AI For the past two years, the industry has been obsessed with Retrieval-Augmented Generation (RAG). While RAG solved the "hallucination" problem by...

How to build a platform of agents

This post introduces a pattern where a user can have many agents, and an agent can be specialized in a particular domain. An agent can have tools, and even skills. Its a powerful t...

3 rules for getting AI agents to find, use—and not exploit—your devtool

Originally appeared on Evil Martians.Authors: Irina Nazarova, CEO, and Travis Turner, Tech EditorTopics: AI, Developer CommunityThe agent-led growth playbook: how to make AI agents...

Agent Script: The Control Plane for Agentic Decisions

A language built for humans and the coding agents that help them

Microsoft Agent Framework: From Zero to Multi-Agent Pipeline

I have some background with other agent frameworks like CrewAI and LangGraph, so when Microsoft released the Agent Framework, a lightweight Python package for building AI agents wi...

Anthropic、AIエージェント設計刷新　“頭脳・手・記録”を分離し、応答速度を最大90％改善

Anthropicは4月9日、長時間稼働するAIエージェントの設計課題を解決する新アーキテクチャ「Managed Agents」を発表した。

Designing Multi-Agent Systems with Gemma 4: Supervisor and Worker Pattern

Most agent implementations fail for a simple reason: They try to make one model do everything. That approach does not scale. вё» The limitation of single-agent systems When on...

Managing Anthropic Agent SDK Costs: A Post-June 15 Billing Playbook

<p>Your background agents are about to run out of money. Anthropic's new credit pool system means your automation could die</p>

AWS Agent Registry: Taming Wild Agents

Big companies are starting to use many AI agents—sometimes hundreds or thousands. This creates a problem. Think of it like a massive digital zoo where the animals (agents) are runn...

Anthropic created a test marketplace for agent-on-agent commerce

In a recent experiment, Anthropic created a classified marketplace where AI agents represented both buyers and sellers, striking real deals for real goods and real money.

FDAI、Managed Agentsを活用した企業向けAIエージェント導入支援を開始

FDAI、Managed Agentsを活用した企業向けAIエージェント導入支援を開始

I'm writing this down before I lose the thread

I'm writing this down before I lose the thread I've been sketching an architecture for agent platforms for a while, and the pieces are starting to lock together. Time to get it...

Агенты выходят на работу (часть 3)

В первой части мы говорили про оргмодель — зачем она вообще нужна и какая от нее польза.Во второй части говорили о процессах — чего не хватает в типовых BPM и как можно ситуацию ул...

Anthropic tests Conway as a persistent agent platform for Claude

Anthropic is testing its innovative Conway agent, an always-on platform that transforms Claude into a persistent, standalone autonomous environment.

LangSmith Engine closes the agent debugging loop automatically — but multi-model enterprises still need a neutral layer

Enterprises building and deploying agents have a problem: it’s taking their engineers too long to find out that an agent made a mistake, and the loop has continued to perpetuate, e...

Google ADK for Java 1.0 Introduces New App and Plugin Architecture, External Tools Support, and More

Google's Agent Development Kit for Java reached 1.0, introducing integrations with new external tools, a new app and plugin architecture, advanced context engineering, human-in-the...