104 stories
Most AI agent platform roundups compare frameworks, builders and runtimes as if they were the same purchase. We scored ten on one question: can it safely run real work after the demo?
No single AI agent memory layer is best in 2026. The right one depends on tenant isolation, contradiction handling, where you can run it, and what a retrieval costs, all of which you can check in an afternoon.
See how Included Health used Deep Agents, LangGraph, and LangSmith to build Dot, a federated healthcare navigation agent with human handoff and clinical oversight.
Agent programs in healthcare and life sciences are being built under a different set of constraints than those in most industries. There’s plenty of upside if the constraints can be resolved.
Workflows can now start agent conversations, our MCP server can manage agents and inspect conversations, and new tools give you more control over chat content and delivery.
A practical comparison of seven leading AI agent frameworks: what each is built for, where it falls short, and how to choose.
An agent harness is the runtime layer that actually runs your agent: it drives the loop that calls the model, dispatches tool calls, executes code, and decides what an agent …
A guide on scaling agents in Europe & the Middle East to see how Schneider Electric, Vodafone, and monday.com are approaching production AI at scale, from establishing shared agent platforms and LLMOps practices to designing multi-agent architectures with stronger observability, evaluation, and…
confident-trace is our new Python and TypeScript SDK for tracing production AI applications. Here's why we're separating it from DeepEval and what that means for your stack.
Coworker AI compares 8 LangGraph alternatives for agent orchestration: CrewAI, AutoGen, Semantic Kernel, Temporal and more, with honest trade-offs.
Before you write a single line of LangGraph, CrewAI, or Python code, there is one control flow graph you must draw as part of your system design. In this video, I share a 5-question framework to help you architect reliable agents, protect irreversible actions, and decide whether you need an…
Senior Fullstack Engineer, AI Observability & Evals Platform — Boston, MA · full-time · Hybrid · $175k-$240k
Senior Backend Software Engineer, AI Observability & Evals Platform (LangSmith) — Boston, MA · full-time · Hybrid · $180k-$240k
OpenAI Agent Builder is shutting down on November 30, 2026. Learn what it did, how to migrate, and which alternative fits your workflow.
Learn how to build an AI portfolio that actually gets you hired as a Forward-Deployed Engineer (FDE). In this video, I walk through five production-grade projects from permission-aware knowledge systems to automated document approval that prove you can handle messy enterprise workflows, not just…
An agentic OS is a real layer of responsibility, not a product you can buy. Here is where the operating system metaphor holds, the four places it breaks, and the seven questions to ask any vendor claiming to be one.
LangGraph vs AutoGen in 2026 is not an even fight: AutoGen is in maintenance mode and LangGraph 1.0 is the live production choice. A straight build-vs-migrate guide.
Enterprise AI agents fail on operations, not intelligence. A practical guide to what enterprise-grade requires, why 40% of projects get canceled, and how to deploy agents you can watch, govern, and trust.
Showing 72 of 104 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
