# knowledge base

AI Product Development in Practice: Model Selection, Building Moats, and Paths to Commercialization

Practical strategies for AI product development: why not to train models from scratch, when to use APIs vs. fine-tuning, building product moats, and the full path from evaluation systems to commercialization.

Agent Tuning: A Complete Guide to Training LLMs with Agent Capabilities

Agent Tuning: A Complete Guide to Training LLMs with Agent Capabilities

A deep dive into Agent Tuning principles and practices, covering why Agent training is needed, the evolution from Prompt to RAG to Agent, development workflows, and cost assessment for private deployment.

Getting Started with RAG: What Is Retrieval-Augmented Generation and How Does It Solve LLM Hallucination?

Getting Started with RAG: What Is Retrieval-Augmented Generation and How Does It Solve LLM Hallucination?

RAG (Retrieval-Augmented Generation) is the core solution for LLM hallucination. Learn RAG concepts, how it works, three causes of hallucination, and the complete learning path from basics to Knowledge Graph RAG.

MCP Protocol in Practice: Building an AI Investment Analysis Agent with TradingView + Notion

MCP Protocol in Practice: Building an AI Investment Analysis Agent with TradingView + Notion

A detailed guide on MCP protocol vs Skills, integrating TradingView and Notion MCPs to build an automated investment analysis Agent with market scanning, backtesting, and report generation.

Deep Dive into How OpenClaw (Open-Source Crayfish) AI Agent Works

Deep Dives

Deep Dive into How OpenClaw (Open-Source Crayfish) AI Agent Works

Deep analysis of OpenClaw AI Agent internals: System Prompt, tool calling, SubAgents, Skill system, memory, and Context Engineering explained.

From Traditional RAG to Agentic RAG: Core Principles and Implementation Guide

From Traditional RAG to Agentic RAG: Core Principles and Implementation Guide

Deep dive into the technical differences between traditional RAG and Agentic RAG, covering offline/online pipeline principles, tool-based autonomous decision mechanisms, and a LangGraph-based Agentic RAG implementation via the ChatBox open-source project.

GPT-5.1 vs Claude Sonnet 4.5 Hands-On Comparison: Coding, Writing, and Creativity Benchmarked

Product Reviews

GPT-5.1 vs Claude Sonnet 4.5 Hands-On Comparison: Coding, Writing, and Creativity Benchmarked

Hands-on comparison of GPT-5.1 vs Claude Sonnet 4.5 across long-form writing, classical poetry, front-end coding, and UI reproduction to help you pick the right AI model.

Andrew Ng Recommends Claude Code: From Getting Started to Figma-to-Web App in Practice

Andrew Ng Recommends Claude Code: From Getting Started to Figma-to-Web App in Practice

Andrew Ng and Anthropic launch a Claude Code course covering RAG chatbots, data analysis, and Figma-to-web apps, with MCP server integration and parallel session best practices.

Enterprise RAG Project in Practice: A Complete Guide from Principles to Deployment

Enterprise RAG Project in Practice: A Complete Guide from Principles to Deployment

Complete guide to enterprise RAG projects covering principles, LangChain implementation, data processing, retrieval optimization, evaluation, and cloud deployment for AI knowledge base applications.

Getting Started with AI Agent Development: A Complete Learning Path from Concepts to Practice

Getting Started with AI Agent Development: A Complete Learning Path from Concepts to Practice

A comprehensive guide to AI Agent development for beginners, covering core concepts, market outlook, LangChain framework, RAG knowledge bases, and hands-on projects to systematically master intelligent agent development skills.

Gemini 3.5 Flash Tops the Vending Bench Cost-Efficiency Frontier

Tech Frontiers

2026年6月3日·1 min

Gemini 3.5 Flash Tops the Vending Bench Cost-Efficiency Frontier

Google Gemini 3.5 Flash achieves cost-intelligence Pareto optimality on Vending Bench. Analysis of the benchmark methodology, Pareto Frontier implications, and practical significance for AI developers.

AI Hallucinations: Why Large Language Models Inevitably "Make Things Up" and How to Deal With It

Deep Dives

2026年6月3日·4 min

AI Hallucinations: Why Large Language Models Inevitably "Make Things Up" and How to Deal With It

Deep dive into AI hallucination's three root causes: training objective flaws, exposure bias, and probabilistic generation. Covers classification and practical mitigation strategies including RAG.

Tech Frontiers

Major Firebase Update: Comprehensive A…

Major Firebase Update: Comprehensive AI Integration and Agent Skills Upgrade

Firebase announces major updates including AntiGravity integration, Android Studio Agent Mode, AI Logic security enhancements, Google Maps grounding, and hybrid AI inference support.

Ollama Getting Started Guide: The Best Tool for Locally Deploying Open-Source LLMs

Ollama Getting Started Guide: The Best Tool for Locally Deploying Open-Source LLMs

A detailed guide to Ollama's core features: free open-source local LLM management with cross-platform support, intelligent GPU/CPU scheduling, and API integration for running DeepSeek and other open-source models locally at zero cost.

AI Full-Loop Embedded Software Development: Zero-Code UART Communication in One Minute