SIGNAL
Tracking the global AI frontier — labs · research · agents · policy
Frontier Signal

Agents

The agentic stack, tracked daily: MCP and A2A protocols, LangChain/LangGraph, Claude Code, OpenAI Agents SDK, agent frameworks, benchmarks and orchestration patterns.

The agentic stack, tracked daily: MCP and A2A protocols, LangChain/LangGraph, Claude Code, OpenAI Agents SDK, agent frameworks, benchmarks and orchestration patterns.

Latest in Agents

30 stories
Market surveillance agent with LangGraph and Strands on AgentCore
Practice

Market surveillance agent with LangGraph and Strands on AgentCore

Learn how to architect and deploy a production-ready multi-agent AI system using LangGraph for workflow orchestration and Strands for agent reasoning on Amazon …

Scientific computing in the age of agentic AI
Labs

Scientific computing in the age of agentic AI

A new field report shows how scientists use AI coding agents to modernize scientific computing, accelerating software development and discovery in genomics and …

Gemini API Managed Agents: 3.6 Flash, hooks, and more
Labs

Gemini API Managed Agents: 3.6 Flash, hooks, and more

We’re announcing even more new capabilities in Managed Agents in Gemini API so developers can build reliable, production-ready agents.…

GitHub Copilot for JetBrains adds improved OpenTelemetry configuration and model management
Create

GitHub Copilot for JetBrains adds improved OpenTelemetry configuration and model management

This update brings more control and clarity to your GitHub Copilot for JetBrains workflows. You can now connect MCP servers and custom agents in Claude agent fl…

Enterprise managed settings in the GitHub Copilot app and Copilot cloud agent
Create

Enterprise managed settings in the GitHub Copilot app and Copilot cloud agent

You can now govern the GitHub Copilot app and Copilot cloud agent with enterprise managed settings, the same centrally managed policies you use to control Copil…

Building the enterprise environment for agentic AI
Research

Building the enterprise environment for agentic AI

For the enterprise, the promise of agentic AI is much more than just a better chatbot. It is software agents that execute business tasks end-to-end across peopl…

Rewired takes: How AI is unlocking creativity and heralding the rise of the agent manager
Practice

Rewired takes: How AI is unlocking creativity and heralding the rise of the agent manager

Companies are reassessing how they work, their team structures, and what it means to be a manager in this bracing new era.…

Introducing Claude Opus 5 on AWS: Anthropic’s most capable Opus model
Practice

Introducing Claude Opus 5 on AWS: Anthropic’s most capable Opus model

This post covers Opus 5’s improvements and practical guidance for AI engineers integrating the model into agentic systems and production inference workloads on …

Get started with OpenAI GPT-5.6 Sol, Terra, and Luna on Amazon Bedrock
Practice

Get started with OpenAI GPT-5.6 Sol, Terra, and Luna on Amazon Bedrock

OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock. Learn how to select a model, run inference through the Responses API on the b…

Claude Opus 5 is now available in GitHub Copilot
Create

Claude Opus 5 is now available in GitHub Copilot

Claude Opus 5, Anthropic’s newest Opus model, is now available in GitHub Copilot. It is designed for complex, long-running coding tasks that require caref…

How AI agents can help FP&A better steer the business
Practice

How AI agents can help FP&A better steer the business

AI makes continuous financial planning practical at scale. Organizations can identify risks sooner, evaluate trade-offs faster, and intervene before performance…

Announcing Fugu-Ultra v1.1 and Claude Code interface for Fugu
Labs

Announcing Fugu-Ultra v1.1 and Claude Code interface for Fugu

How Figma stays ahead of vulnerabilities with agents
Create

How Figma stays ahead of vulnerabilities with agents

Copilot cloud agent for Linear is now generally available
Create

Copilot cloud agent for Linear is now generally available

You can now assign issues in Linear to Copilot cloud agent, our asynchronous, autonomous background agent. When you assign a Linear issue to Copilot, it will: A…

GitHub MCP Server supports the next MCP specification
Create

GitHub MCP Server supports the next MCP specification

The MCP protocol is going stateless on 28th July 2026, and the GitHub MCP Server supports the latest spec ahead of the official release. What’s changing T…

Agent automation controls in GitHub Issues in public preview
Create

Agent automation controls in GitHub Issues in public preview

Agent automations increasingly label, type, assign, and close issues for you. GitHub Issues now shows the reason behind each change and lets you review them bef…

Agentic retrieval for Amazon Bedrock Managed Knowledge Base
Practice

Agentic retrieval for Amazon Bedrock Managed Knowledge Base

This post focuses on why classic retrieval falls short on multi-part questions, how the AgenticRetrieveStream API works (including request construction and trac…

Detecting silent agent failures with Amazon Bedrock AgentCore optimization
Practice

Detecting silent agent failures with Amazon Bedrock AgentCore optimization

Amazon Bedrock AgentCore optimization surfaces silent behavioral failures in production AI agents: the ones that pass every health check but still deliver wrong…

Building trade assistant: How Jefferies optimized front office trading operations with AI
Practice

Building trade assistant: How Jefferies optimized front office trading operations with AI

In this post, we explore how Jefferies overcame these challenges with a solution built on Strands Agents, an agent harness SDK for building AI agents that can r…

Evaluating AI Agents: A production blueprint with Strands and AgentCore
Practice

Evaluating AI Agents: A production blueprint with Strands and AgentCore

Together, Motorway and AWS built an end-to-end evaluation pipeline that reduced incorrect results from 1 in 8 queries to 1 in 50 and cut issue detection time fr…

AI Teammates: how monday.com runs production AI agents on Amazon Bedrock
Practice

AI Teammates: how monday.com runs production AI agents on Amazon Bedrock

AI Teammates are agentic AI on Amazon Bedrock, and few engineering organizations run them in production at the scale that monday.com does. Nine in ten Builders …

Introducing OpenAI Presence
Labs

Introducing OpenAI Presence

Introducing OpenAI Presence, a proven enterprise AI agent platform that helps organizations deploy trusted voice and chat agents for customer and internal workf…

Powering supply chain with agentic AI
Practice

Powering supply chain with agentic AI

Agentic AI could fundamentally reshape supply chain operations, but realizing its potential will require companies to move beyond isolated use cases and orchest…

Now in preview: Find and fix software vulnerabilities with CodeMender
Practice

Now in preview: Find and fix software vulnerabilities with CodeMender

As adversarial AI threats accelerate attacks on code, security teams must counter them with machine-speed defenses that can automate code remediation and fight …

Gemini 3.6 Flash is now available in GitHub Copilot
Create

Gemini 3.6 Flash is now available in GitHub Copilot

Gemini 3.6 Flash, Google’s latest Flash model, is now rolling out in GitHub Copilot. It is designed for web and app development, coding, and longer-horizo…

Built for Vera Rubin, NVIDIA Spectrum-6 Arrives in Gigascale AI Factories
Labs

Built for Vera Rubin, NVIDIA Spectrum-6 Arrives in Gigascale AI Factories

AI has entered the gigascale era. The world’s most advanced AI factories are bringing together hundreds of thousands of GPUs and CPUs to train frontier models, …

Introducing Fugu-Cyber: our new orchestration model that achieves state-of-the-art performance on real-world cybersecurity benchmarks
Labs

Introducing Fugu-Cyber: our new orchestration model that achieves state-of-the-art performance on real-world cybersecurity benchmarks

Evolving from legacy BI to agentic AI at Tradeshift with Amazon Quick
Practice

Evolving from legacy BI to agentic AI at Tradeshift with Amazon Quick

In this post, we describe how Tradeshift deployed Amazon Quick with agentic AI capabilities to replace our legacy BI tool, resulting in query response times up …

Build specialized agent workflows for your business with Amazon Quick and NVIDIA NeMo Agent Toolkit
Practice

Build specialized agent workflows for your business with Amazon Quick and NVIDIA NeMo Agent Toolkit

In this post, we show how Amazon Quick can serve as the business-user front door for specialized agent workflows. We use the NVIDIA NeMo Agent Toolkit to build …

At SIGGRAPH, NVIDIA Advances Graphics and Simulation With Agentic and Physical AI
Labs

At SIGGRAPH, NVIDIA Advances Graphics and Simulation With Agentic and Physical AI

From open models to real-time simulation, AI and graphics breakthroughs are transforming media, content creation and robotics.…