Search
Found 15 articles
Agentic Attack Tooling Research Series: A Guide to All Fourteen Parts
When attack tooling becomes AI-agent-driven, both sides of the conflict change. This is a fourteen-part deep research series: starting from a publicly attributed real-world incident, it unpacks architecture design, coordination mechanisms, and technical principles, then returns to a checklist defenders can use immediately plus isolated research practice.
Isolated Research Practice: How to Study an Offensive Tool Safely
Studying offensive tooling is a necessary part of security work, but "researching" and "using" must be separated by technical boundaries, not willpower. Using a real isolated deployment as the example, this article covers network isolation, port binding, resource limits, tool verification, and five red lines.
The AI Coding Tools Map: Recognize the Form Factor First, Memorize Names Later
Cursor, Trae, Claude Code, Codex, OpenClaw, Hermes Agent, DeepSeek Harness, WorkBuddy and Doubao Work sorted into three categories by form factor: IDE-embedded, terminal agent, and orchestration platform. For each category: what it gives you, how much control and visibility it takes away, and how people actually mix them in practice — so you can decide which category your first tool should come from.
300-Page Annual Report to Structured JSON: The Three Statements and Segment Data
Building on the PaddleOCR field practice, this pushes 'reading out the text' to 'usable data': locating the financial-statement pages, handling cross-page tables, field mapping and unit normalization for the three statements and segment information, JSON schema design, and a complete pipeline and checklist for automated proofreading via reconciliation relationships.
SkillOpt Deep Technical Breakdown: Training Agent Skill as a Neural Network
A complete source-code-level analysis of the SkillOpt framework published by Microsoft Research. Starting from 18 Deep Learning analogies, it deeply breaks down the six-stage training loop (Rollout→Reflect→Aggregate→Select→Update→Gate), the SkillOpt-Sleep deployment engine, OpenClaw integration in practice, and the 52/52 all-win experimental results.
Skill Reporting: Breaking the AI Agent Black Box with One Line of Text - The Design Philosophy and Practice of Institutional Skills
Agent replied to you, but you have no idea which skills it used, what process it followed, or where the data came from. Every reply feels like a black box. Transparency is the third-largest barrier to enterprise adoption of AI Agents (Deloitte 2026). Skill Reporting breaks the black box with one line of text: no code required, just add one permanent rule to RULES.md. This article deeply analyzes the design philosophy, real-world effects, and indirect impacts of institutional skills.
200+ Skills, One Router: Engineering Practice of Agent Skill Routing
After installing 200+ skills, does the AI Agent actually get dumber? How category-by-stage matrix routing raises skill discovery from 35% to 90%, reduces incorrect tool usage by 80%, and lets any task automatically match the right skill combination.
PaddleOCR in Practice: Extracting Hong Kong Stock Annual Report Financial Data in 83 Seconds
A hands-on test of Baidu PaddleOCR, the open source document AI engine with 81K Stars. PP-OCRv5 with 96.5% accuracy extracted 102 text regions from a Hong Kong stock annual report P&L page, discovered a KMeans clustering bug (n_clusters=0) in the PP-StructureV3 Transformers engine, built a custom DBSCAN row and column clustering parser, and completed automatic structuring of three financial statements end to end in 83 seconds.
A Complete Tutorial for Matt Pocock Skills: The 115K Star AI Coding Engineering Discipline System, a Full Walkthrough of 15 Skills from Installation to Practice
mattpocock/skills: 35 Agent Skills released by TypeScript legend Matt Pocock from his own .claude directory, with 115K+ Stars, 2.7M+ installs, and 60K newsletter subscribers. This is not vibe coding; it is an AI coding discipline system condensing decades of software engineering experience.
A Lightweight Overhaul of MemoryHub in Practice: Cutting from 10 Databases to 5, and RAM from 6.2GB to 500MB
What happens when you delete Neo4j, Elasticsearch, and MongoDB from an AI memory system, keep only the Qdrant + FAISS + SQLite-vec trio, and replace the 9.1GB BGE-m3 with a 193MB bge-small-zh? A complete performance dissection, an embedding model comparison, and a trimming plan aimed at ordinary computers.
Polyglot Persistence in Practice: A Full-Pipeline Evaluation of a Ten-Database Memory System
From BGE-m3 vector embeddings and ten-way synchronized writes to a comparison of search quality and speed across nine backends: a complete stress test of an AI memory system. Qdrant is the king of semantics, FAISS the king of speed, and Neo4j the king of relationships.
From Zero to Launch: Agentics Website Development Retrospective and Key Lessons
A complete development retrospective on building a Next.js knowledge platform from scratch with AI Agents (our AI assistant + Claude Code): architecture design, pitfalls, key decisions, and best practices for AI-assisted development.
RAG In-Depth Principles and Practice: A Complete Guide from Chunking to Rerank
The complete tech stack for Retrieval-Augmented Generation (RAG): Embedding selection, Chunking strategies, vector database comparison, Rerank optimization, with practical code examples.
DeepSeek V4 Flash / V4 Pro API Best Practices and Performance Comparison
Complete guide to the DeepSeek V4 series models: comparing performance, pricing, and use cases of V4 Flash vs V4 Pro, with API call examples and cost estimates.
LiteLLM Proxy Multi Model Routing in Practice
Use LiteLLM Proxy to centrally manage multiple LLM backends such as DeepSeek, ModelStudio, Ollama, and more: load balancing, cost tracking, fallback configuration.