#AI Agent
1105 related articles
MCP Security Primer: OWASP Top 10 Risks and the Lethal Trifecta Defense
A systematic breakdown of MCP security risks: from the Postmark backdoor to the OWASP MCP Top 10, how the Lethal Trifecta reveals AI Agent fragility, plus shadow servers and missing audits.
Claude Duet Unveiled: Anthropic Launches a Proactive Personal Assistant
Anthropic launches Claude Duet, a proactive personal assistant seen as a response to Muses, Bots, and Dots. This analysis covers its positioning, competition, technical barriers, and market impact.
Behind the QQ Agent Hype: Ecosystem Chaos and Pitfall-Avoidance Guide as Newcomers Flood In
After QQ Agent's explosive growth, community numbers surged. Bilibili creator Bai Lu complains about common newcomer issues: API configuration errors, model selection confusion, account conflicts, incomplete error screenshots. This article sorts out the technical essence of these high-frequency problems and offers Agent tool pitfall-avoidance advice and a must-read guide for newcomers.
The Most Comprehensive AI Agent Tutorial on Bilibili: From Zero to Practice in Seven Days
Comprehensive analysis of Bilibili's AI Agent tutorial: from ReAct framework, planning & reasoning, memory mechanisms in the cognition part to LangChain & AutoGen practice in advanced part, and enterprise project implementation. Is the seven-day learning path reliable? Who is it for? This article breaks down the course structure and design philosophy.
748-Episode AI Agent Development Course: A Complete Guide to Enterprise-Level Intelligent Agent Practice
In-depth analysis of Bilibili's 748-episode AI Agent development course: from basic environment setup, prompt engineering, RAG knowledge bases to enterprise-level practical projects and job interview guidance, evaluating its course structure and learning value for Agent development learners.
WorkBuddy Practical Guide: Build Your AI Office Automation Agent from Zero
WorkBuddy hands-on tutorial: from installation to application, explaining the essential difference between desktop AI Agents and chatbots, comparing WorkBuddy vs CodeX on barriers, ecosystem, and cost, and breaking down file management, data processing, and collaborative office scenarios to help zero-basis office workers shift from AI questioners to AI managers.
Grok Bot from Scratch: Installation & Login, Building an AI Team, and Cloud Agent Security Settings
A from-scratch Grok Bot tutorial: official download and login, subscription access checks, your first assistant with a test, researcher and planner Bot teamwork, cloud Agent install, API credential security, Auto Review rules, and cost control.
Master WorkBuddy in Ten Lessons: From Chat AI to an Automated Digital Colleague
A complete breakdown of the ten-lesson WorkBuddy tutorial on Bilibili: installation, the three working modes, the six elements of task descriptions, Skills, expert teams, MCP connectors, mini programs and IM assistants, external API access, and the five elements and six screening questions for scheduled Agent tasks—all in one article to understand how AI agents go from chat tools to digital colleagues that work for you.
I Handed My Plants Over to an AI Agent: A Practical Guide to Automated Watering from Sensors to Pump
A Bilibili creator uses ESP32-S3, SHT40, light and soil sensors, ESP32-CAM, and Doubao Work to build an AI Agent that senses plant status, makes judgments, and controls a water pump.
Hermes Agent Advanced Guide: 10 Configurations to Build a Super Assistant
Don't just chat after installing Hermes Agent. This article breaks down 10 core configurations tested on Bilibili: Camoufox stealth scraping, Soul.md persona injection, primary/secondary model cost reduction, three-layer memory, Docker sandbox isolation, Swarm multi-Agent collaboration, and automated skill evolution—helping you transform your initial Agent into a full-stack digital employee.
Agent Scraper Mines Taoguba Hot Money Data: A Practical Review and Zero-Basics Deployment Tutorial
Bilibili creator shares Taoguba scraper Agent: scraping hot money discussions to generate pre-market plans, 11.72% daily return, zero-basics deployment tutorial, rule-based trading logic, and reverse validation table design, analyzing AI Agent's practical application and boundaries in short-term trading.
Mouse-1: An Efficient Decision Model Built for AI Agents, 163x Cheaper
Mouse-1 is a lightweight decision model for AI Agent frameworks, reportedly 163x cheaper and 65x faster than GPT-6 Sol. Learn how it works, its cost advantages, and use cases.
Don't Rush to Deploy AI Agents: A Complete Design Guide to Tool Use and Function Calling
A systematic guide to AI agent tool design: JSON Schema, execution loops, parameter validation, error feedback, least privilege, human approval, and production practices.
AI Agent Launches a Product Business in One Day: Hands-On with Alibaba's AI Product Sourcing and Sampling
Hands-on test of Alibaba.com's AI Mode: an AI Agent completes sourcing, design, branding, and orders a real sample in one day — but final decisions still need a human.
Cursor Engineer Open-Sources Pstack: A Six-Phase AI Coding Workflow Breakdown
Cursor engineer Lauren Tan open-sources Pstack, splitting AI coding into six phases: planning, design, building, testing, deployment, and maintenance. This article breaks down the multi-model arena design, TDD and cleanup diff skills, end-to-end verification and swarm testing, plus coding principles like attack the premise, with a Bilibili creator's hands-on commentary.
Vercel Drives Officially Launches: The Era of Stateful AI Agent Hosting Begins
Vercel Drives is now generally available, letting developers run stateful AI Agents on Vercel. This analysis covers how it solves session persistence, long-task continuity, and tool-calling context passing, plus its impact on AI app development and the Agent hosting competitive landscape.
MemCurrent: Designing Persistent Memory Systems for Production-Grade Agents
MemCurrent explores persistent memory design for production-grade AI Agents: why context windows aren't memory, and solutions to four engineering challenges: writing, retrieval, updating, and isolation.
ToDo.is: Hand Your To-Dos to an AI Agent That Actually Does the Work
ToDo.is is an always-on AI agent to-do tool: write a task and it executes—research with sources, generate files and images, scheduled briefings and price alerts. Works on web, Android, WhatsApp, and Telegram, and asks before paid, send, or delete actions.
MCP Protocol Deep Dive: A Standardized Connection Solution for AI Agents
A deep dive into the Model Context Protocol (MCP): its Host/Client/Server architecture, JSON-RPC messaging, STDIO and Streamable HTTP transports, Tools/Resources/Prompts primitives, and security best practices—helping AI developers systematically understand this standardized agent connection protocol.
Give Your AI Agent a Shelf: MCP + x402 Lets Agents Shop Autonomously
A real experiment: give an AI Agent a secondhand shelf, expose search, lookup, and purchase-intent tools via MCP, and return payment challenges with x402—but eBay still closes the deal. Exploring agent-readable e-commerce.