#AI Agent
1113 related articles
Cayu: An Open-Source Python Framework for Building Long-Horizon Domain-Specific Agents
Cayu is an open-source Python framework for building domain-specific, long-horizon AI agents. It lets developers assemble a harness of tools, knowledge, and business rules, backed by an integrated durable runtime handling sessions, state, recovery, approvals, and observability.
AI Agent Development: A 4-Stage Learning Roadmap from Beginner to Enterprise-Level Practice
A complete AI Agent learning roadmap from zero to enterprise-level: covering ReAct, multi-agent collaboration, Prompt tuning, RAG, MCP, and real-world projects.
A New DeepSeek Harness Experiment: Agent Supervising Agent for Self-Evolution
A developer built an "Agent supervising Agent" self-evolution system using DeepSeek Harness, with a ledger mechanism enabling near-unattended overnight software iteration.
From Solo to Team Player: The Journey of an AI/LLM Self-Learner
A CSE student with LLM, RAG, AI Agent, MCP, and LangChain skills seeks mentorship and team experience. Exploring how AI self-learners can transition from solo to collaborative engineering.
AI Agent Practical Guide: A Technical Roadmap from RAG to Intelligent Agents
From prompt engineering to RAG to AI Agents: a practical breakdown of LLM engineer skill sets, four stages of commercial deployment, and the four main Agent categories. Covers LangChain and LangGraph.
Enterprise AI Agent Full-Stack Development: A Complete Learning Path to Building Production-Ready Agents from Scratch
A breakdown of an enterprise AI Agent full-stack development course: covering why to learn Agents, target audience, LangChain & CrewAI learning paths, and single-to-multi-agent project walkthroughs.
DeepSeek Harness Explained: Three Core Design Questions at the Heart of AI Agents
What is DeepSeek Harness? This article breaks down the AI Agent core design through three key questions: Harness engineering, plugin architecture, and building highly available Agent systems.
A 5-Level Roadmap for Learning AI Agents: Don't Rush Into Frameworks
A 5-level roadmap for learning AI Agent development: LLM fundamentals, production APIs, context management, RAG, and Agent orchestration — each with a hands-on project.
LangGraph Beginner's Guide: The Complete OS for AI Agents
LangGraph is called the OS for AI Agents. This guide covers its relationship with LangChain, State/Node/Edge fundamentals, checkpoints, human-in-the-loop, and subgraphs.
Andrew Ng on Agentic AI: Cutting Through the Hype to Find the Core Skills That Actually Matter
Andrew Ng's Agentic AI course cuts through industry hype to reveal the real skills that matter: systematic evals and error analysis for building reliable agent workflows.
AI Agent Whistleblower Hotline Goes Live: Intelligent Agents Can Now "Snitch"
AI Contact Hotline introduces a whistleblower-style reporting channel for AI Agents, letting them flag misconduct in multi-agent systems. We break down how it works, its value, and the governance debates it raises.
Deconstructing Claude Code's Architecture: An Advanced AI Agent Development Guide for Frontend Engineers
Break down Claude Code's Agent Loop, Tool system, Skills, and Memory modules. A hands-on guide for frontend engineers to build a minimal coding agent with TypeScript.
Graph Engineering: The AI Workflow Design Method That Goes Beyond Prompts
Graph Engineering is the next evolution beyond prompt engineering. Learn how to break complex AI tasks into planners, parallel researchers, skeptics, and merge steps — with a practical 3-level implementation path from manual to LangGraph automation.
OpenAI Agents API Decoded: The Monetization Logic Behind Open-Source Codex
OpenAI launches Agents API, packaging open-source Codex Harness as a cloud agent service. Explore its three premium features and the Open Core business model behind it.
What Is an AI Agent? From Chatbots to Digital Employees — How It Actually Works in Practice
What is an AI Agent? It's a digital employee that reads data, calls APIs, breaks down tasks, and self-corrects. Learn how Agents differ from chatbots and where they're being deployed in real enterprises.
Sierra Multimodal Agents: A Customer Service AI That Seamlessly Switches Between Voice, Text, and Vision
Sierra's Multimodal Agents automatically switches between voice, text, and vision within a single conversation, built for enterprise customer success scenarios.
Portable Computer Comes to Windows: Run AI Agents Locally with RTX GPUs
Portable Computer now supports Windows PCs with NVIDIA RTX GPUs, enabling local AI agents, harnesses, and models to run on-device without cloud uploads, with optional frontier cloud model access.
LabAgent: Building Reproducible AI Agent Systems for Research Laboratories
A new arXiv paper introduces LabAgent, an AI agent system for research labs that uses executable skill verification and experience logging to outperform generalist agents across life science domains.
Adaptive Physical AI Exploration: Can LLM Agents Handle Long-Horizon Physical Tasks?
New arXiv paper explores whether LLM agents can manage long-horizon physical tasks. A multi-agent framework combining planning, tool calling, observation, and verification is tested in agricultural settings, showing LLMs outperform RL agents in shifted environments.
SOP-Bench: A New Benchmark for Evaluating AI Agents on Real Business Procedures
SOP-Bench is a new extendable benchmark for evaluating AI agents on complete real-world business procedures, going beyond isolated proxy tasks to measure true end-to-end capability.