Topic
347 articles found
Version 0.14.2 added a MongoDBSession backend; here's a working multi-agent customer-support demo that uses it, and the documents it leaves behind. The OpenAI Agents SDK has shipped session backends for SQLite, SQLAlchemy, Redis, and Dapr for a while now. With 0.14.2 (April 2026), MongoDBSession joi
As enterprises race to wire AI into their operations, the infrastructure bottleneck has shifted from model capability to data access — and the enterprises winning the race are those treating real-time data pipelines as a first-class architectural concern. Agents are only as intelligent as their unde
Google is bringing back its 5-Day AI Agents Intensive Course with Kaggle and registration is open.
The phone could go in mass production in 2028, an analyst says.
Nothing New Under the Sun ☀️ Started by scrutinizing how things actually work under the hood. When you dig into the pipeline, you realize that a modern AI agent is essentially just a marriage between a regular chatbot and a pre-trained model. Wrapped all together, they gave it the name "AI Agent": V
Public web pages are actively hijacking enterprise AI agents via indirect prompt injections, Google researchers warn. Security teams scanning the Common Crawl repository (a massive database of billions of public web pages) have uncovered a growing trend of digital booby traps. Website administrators
Many developers use OpenClaw for a long time without truly grasping the boundary between Tools and Skills. If you want to move from a "casual tinkerer" to a professional AI Agent architect, you must understand the underlying design philosophy. To a Linux veteran, this is as fundamental as the distin
Most "AI agent" tutorials show you how to build a chatbot with memory. That's not an agent. That's a stateful chatbot with a good PR team. A real agent makes decisions, calls tools, recovers from failures, and produces outputs your users actually care about. The gap between demo and production is wh
The surprise in building KubeStellar Console with coding agents was not the extent of the model’s capabilities, but the heavy The post Beyond prompting: How KubeStellar reached 81% PR acceptance with AI agents appeared first on The New Stack.
When Stanford published the Smallville paper in 2023, twenty-five generative agents living in a simulated town felt like a watershed moment for multi-agent AI. That was twenty-five. Last week we put two hundred and twenty-one AI agents in a single group chat — not a sandbox, but our actual platform
This is a submission for the Google Cloud NEXT Writing Challenge Everyone Is Building AI Agents After Google Cloud NEXT ‘26 — Here’s Why Most of Them Will Fail At Google Cloud NEXT ‘26, one message was impossible to miss: We are entering the era of AI agents. With announcements around agent-to-agent
This is a submission for the Google Cloud NEXT Writing Challenge AI Agents Need a Constitution: The Missing Control Layer Google Cloud NEXT ‘26 Didn’t Solve At Google Cloud NEXT ‘26, one thing became clear: We are no longer building software. We are building autonomous systems. With announcements ar
Anthropic created a secret AI marketplace where agents sold and bought physical goods on behalf of its employees.
This is a submission for the OpenClaw Challenge: Wealth of Knowledge. The 3 AM Problem It's 3 AM in rural Kenya. A clinic the only one within 50 kilometers looses power. Inside, a neonatal ward goes dark. The solar inverter that powered the clinic has failed, but nobody knows why. The nearest techni
Alchemy CEO Nikil Viswanathan argues the global financial system was designed for humans, but the next wave of commerce will be driven by AI agents that operate natively in crypto.
Model Output Is Not Authority: Action Assurance for AI Agents AI agent security is not only about making the model safer. That statement may sound obvious, but it becomes important once an AI system can do more than generate text. When an AI agent can call tools, access internal systems, update reco
This is a submission for the Google Cloud NEXT Writing Challenge Las Vegas, April 22, 2026. The lights are bright. The room holds thousands of developers. And up on stage, Google is about to change the way we think about software forever. I woke up at 6:30 AM just to watch a keynote. That sentence a
A company called Reco converted JSONata from JavaScript to Go in 7 hours using AI. Seven. Hours. Not seven sprints. Not seven engineers over seven weeks. Seven hours. And the internet immediately argued about the wrong thing. Everyone wanted to talk about which model they used, which agent framework
Pollak, who will be speaking at Consensus Miami 2026 next month, also sees the open-source protocol x402 as a key part of that wave.
The Model Context Protocol (MCP) standard is becoming the default way to expose tools to LLMs in 2026. Anthropic, OpenAI, and every major editor vendor — Cursor, Cline, Continue, Windsurf — now ship with MCP support. If you have any API or scraper, MCP-ifying it is a free distribution channel into e
