90 related articles

LLM thought visualization is emerging as a key breakthrough in AI explainability. This article explores the value, technical approaches, and challenges of visualizing Chain-of-Thought reasoning.

Why can't companies find qualified AI engineers? Discover the 4 core competencies every high-value LLM application engineer needs: task decomposition, tool calling, observability, and production readiness.

An in-depth analysis of the open-source LLM control plane tool Otari—covering unified multi-model access, cost observability, and security compliance governance to help teams build manageable, production-grade AI infrastructure.

Microsoft Foundry integrates Anthropic Claude models, enabling Azure customers to access Claude Opus 4.8 and Haiku 4.5 with unified authentication, billing, and commitment spend drawdown.

Microsoft Foundry integrates Anthropic Claude models. Azure customers can now access Claude Opus 4.8 and Haiku 4.5 with unified identity auth, billing, and commitment credit deduction.

A deep dive into Agentic AI: core components (planning, tool calling, memory), engineering challenges (reliability, cost, safety), and practical development recommendations for production deployment.

Can AI really replace programmers? This article explains Harness Engineering principles and its three evolutionary stages, revealing real pain points of enterprise AI programming.
Morph Reflexes: Building Real-Time Beh…
Morph Reflexes is an open-source AI agent monitoring tool that uses multi-head classifiers for real-time trace classification — enabling safety guardrails, quality scoring, and training data filtering.

Why do enterprise RAG knowledge bases dazzle in demos but fail in production? This article dissects five critical engineering pitfalls with real-world case studies from million-doc platforms and ops agents.

In-depth analysis of OpenAI Codex's four usage forms, comparing Codex, Claude Code, and Cursor across price, stability, and frontend/backend fit to help developers choose the right AI programming tool.

A developer built Manifest Studio to automate the full pipeline from AI code generation to app deployment, using a Skill mechanism for one-sentence publishing.

A detailed four-stage competency model for AI Agent development: from Python/RAG basics (15K) to workflow orchestration (20K), inference optimization (30K), and Agent cluster governance (40K RMB).

Deep dive into Agent Loop mechanics: the think-act cycle, how agents differ from LLMs, termination conditions, and design principles for building autonomous AI Agent systems.

In-depth comparison of five AI Agent code execution sandbox solutions—E2B, Daytona, Modal, Cloudflare Sandbox, and Vercel Sandbox—across isolation, cold start latency, state management, and pricing.

A deep dive into AI Agent architecture and engineering practices, covering tool design, ReAct execution patterns, Vercel deployment, and production considerations to bridge the prototype-to-production gap.

Deep dive into Dify, the open-source LLM app development platform featuring visual workflow engine, RAG knowledge base, Agent capabilities, hundreds of model integrations, Docker deployment, and comparisons with LangChain, Coze, and FastGPT.

A detailed 7-step guide to building commercial AI Agents, covering requirements, platform selection (Coze/Dify/FastGPT), prompt engineering, databases, UI, testing, and deployment.

Deep dive into Agent Skills: how they solve React Agent pain points through on-demand loading and capability modularization, improving decision precision for production-ready enterprise AI Agents.

AI Engineer is evolving from a vague concept into a fast-growing career track. This article analyzes the role's core skills—Prompt Engineering, RAG, Agent development—and industry trends from the AI Engineer Conference.

PilotDeck is an open-source local Agent console from a Tsinghua-affiliated team that solves multi-task chaos with workspace isolation, white-box memory management, and smart model routing.