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
NVIDIA and Local AI Community Fuel Open Source Models and Intelligent Agents
Labs

NVIDIA and Local AI Community Fuel Open Source Models and Intelligent Agents

The open source ecosystem is making it easier for AI enthusiasts and developers to build, customize and run increasingly capable agents locally. Throughout Augu…

How WPP operationalizes platform and data engineering for AI marketing
Practice

How WPP operationalizes platform and data engineering for AI marketing

Between chaotic levels of market fragmentation and economic volatility, marketing and communications agencies can no longer rely on the human intuition they’ve …

Google named a Leader in The Forrester Wave™: AI Platforms, Q3 2026
Practice

Google named a Leader in The Forrester Wave™: AI Platforms, Q3 2026

At Google Cloud, we help organizations of all sizes build and operationalize complex agentic workflows with total confidence. By combining world-class AI resear…

How nOps shipped FinOps agents 75% faster with Amazon Bedrock AgentCore
Practice

How nOps shipped FinOps agents 75% faster with Amazon Bedrock AgentCore

nOps rebuilt its Clara FinOps AI agent on Amazon Bedrock AgentCore, replacing a self-managed Amazon EKS stack running LangChain and LangGraph. The move cut time…

Evolve your marketing with new AI tools
Labs

Evolve your marketing with new AI tools

Learn how new AI and agentic experiences across Google Ads and Google Analytics can simplify your marketing workflow.…

MCP allowlists in enterprise managed settings
Create

MCP allowlists in enterprise managed settings

Enterprise owners can now centrally control which Model Context Protocol (MCP) servers GitHub Copilot clients are allowed to run by using the new allowedMcpServ…

Copilot usage metrics API adds agent app activity
Create

Copilot usage metrics API adds agent app activity

Since agent apps arrived on GitHub, teams have been able to run agents from partners like Claude and Codex directly in their GitHub workflows. The Copilot usage…

How TReNDS automates root-cause analysis with Amazon Bedrock
Practice

How TReNDS automates root-cause analysis with Amazon Bedrock

TReNDS, a research center at Georgia State University, built an agentic AI pipeline on Amazon Bedrock and the open-source Strands Agents SDK that automatically …

How Cohere Health digitizes clinical policies using Amazon Bedrock AgentCore
Practice

How Cohere Health digitizes clinical policies using Amazon Bedrock AgentCore

In this post, you learn how Cohere Health built a multi-tenant agentic architecture on AgentCore using AgentCore Runtime’s secure MicroVM isolation, unified too…

Ben's session
Briefing

Ben's session

Field notes from my agent activity…

How to close the agentic adoption gap
Practice

How to close the agentic adoption gap

At their core, AI transformations are a reinvention of how work gets done. This requires change leadership, not just change management.…

Securing AI agents with temporal policies in Amazon Bedrock AgentCore
Practice

Securing AI agents with temporal policies in Amazon Bedrock AgentCore

Temporal policies in Amazon Bedrock AgentCore let you define stateful rules that evaluate authorization based on an agent's session history. Learn how to enforc…

Configure rate limits for AI traffic on AgentCore gateway
Practice

Configure rate limits for AI traffic on AgentCore gateway

Learn how to configure rate limits on Amazon Bedrock AgentCore gateway to enforce per-user and per-target traffic controls. Define request, token, and connectio…

Kimi K3 is now available in GitHub Copilot
Create

Kimi K3 is now available in GitHub Copilot

Kimi K3, an open-weight model, is now generally available in GitHub Copilot. The model shows frontier-level abilities on agentic coding with highly cost-effecti…

Your agentic summer: No-cost lessons from Google experts to build and scale agents
Practice

Your agentic summer: No-cost lessons from Google experts to build and scale agents

I’ve talked to developers, IT leaders, and builders who all ask the same question: How do we actually get agents into production? The answer isn't theoretical —…

Control agent behaviors and cost beyond a single action: new capabilities in Amazon Bedrock AgentCore
Practice

Control agent behaviors and cost beyond a single action: new capabilities in Amazon Bedrock AgentCore

Learn about new capabilities in Amazon Bedrock AgentCore: temporal policies powered by Dogwood, a new open source policy language for AI agents, and rate limiti…

Building an agentic app deployer with Amazon Bedrock and AWS Lambda
Practice

Building an agentic app deployer with Amazon Bedrock and AWS Lambda

PDI Technologies built PDI Brew, an agentic platform on AWS where non-technical employees describe a tool in plain English and receive a fully provisioned, mult…

Agent Skills for Automated Reasoning policies in Amazon Bedrock
Practice

Agent Skills for Automated Reasoning policies in Amazon Bedrock

Learn how to run the full Amazon Bedrock Automated Reasoning policy lifecycle from your coding agent. A suite of open source Agent Skills builds, reviews, tests…

Enforcing data residency with single-Region Claude Code on Amazon Bedrock
Practice

Enforcing data residency with single-Region Claude Code on Amazon Bedrock

A regulated customer needed all Claude Code inference processed in a single AWS Region (London), not just in-geography. This post shows two ways to pin Claude C…

Build visibility for Codex on Amazon Bedrock with OpenTelemetry and Amazon CloudWatch
Practice

Build visibility for Codex on Amazon Bedrock with OpenTelemetry and Amazon CloudWatch

As engineering teams adopt coding agents like Codex, leaders need visibility into adoption, consumption, and reliability. This post shows how to route Codex Ope…

I'm using a new agent app
Briefing

I'm using a new agent app

is Google in trouble?…

Mirendil taps AI Hypercomputer TPUs and GPUs for pre- and post-training applications
Practice

Mirendil taps AI Hypercomputer TPUs and GPUs for pre- and post-training applications

Nearly every major AI lab uses Google Cloud infrastructure, including for training of models, inference for agents, and new frontier research. Google Cloud also…

Run production AI agents in n8n with Amazon Bedrock AgentCore harness
Practice

Run production AI agents in n8n with Amazon Bedrock AgentCore harness

Amazon Bedrock AgentCore harness is now generally available. Learn how to add it as an agent step in n8n workflows using a new open-source community node, and b…

How we built an MCP bridge to give our AgentCore-hosted AI agent access to local MCP tools
Practice

How we built an MCP bridge to give our AgentCore-hosted AI agent access to local MCP tools

AI agents on Amazon Bedrock AgentCore run in the cloud, but users' tools and files live on their laptops. Learn how to build a secure MCP bridge that lets a clo…

How Mobileye transformed support operations using Amazon Bedrock AgentCore
Practice

How Mobileye transformed support operations using Amazon Bedrock AgentCore

In this post, we'll explore how Mobileye deployed an AI support agentic solution on Amazon Bedrock AgentCore - from the support bottleneck that sparked the idea…

How LendingTree built a multi-agent mortgage assistant on Amazon Bedrock
Practice

How LendingTree built a multi-agent mortgage assistant on Amazon Bedrock

Learn how LendingTree built a production multi-agent mortgage assistant on Amazon Bedrock. Three coordinated agents use LangGraph, the Model Context Protocol, a…

Better code, fewer tokens: The benefits of Code Connect in MCP
Create

Better code, fewer tokens: The benefits of Code Connect in MCP

Introducing Web Search on Amazon Bedrock for foundation model grounding
Practice

Introducing Web Search on Amazon Bedrock for foundation model grounding

Today, we are introducing the general availability of Web Search on Amazon Bedrock. It is a server-side built-in tool that grounds model responses in current we…

NVIDIA Alpamayo 2 Super, the Frontier Open Model for Robotaxis and Autonomous Vehicles, Now Available for Commercial Use
Labs

NVIDIA Alpamayo 2 Super, the Frontier Open Model for Robotaxis and Autonomous Vehicles, Now Available for Commercial Use

For robotaxis and other autonomous vehicles (AVs), the hardest problems aren’t the everyday scenarios. They’re the rare, complex situations that are difficult t…

Inside our 353,000-person vibe coding course
Labs

Inside our 353,000-person vibe coding course

Kaggle’s AI Agents Intensive with Google brought learners together in a no-cost course to build and deploy the next frontier of AI.…