#Draw Things
452 related articles
Product Reviews·4 min
Manus Hands-On Review: Testing a General-Purpose AI Agent Across Three Real-World Scenarios
Hands-on testing of Manus general AI Agent across history report generation, Tesla stock analysis, and GAIA benchmarks. Compares vertical vs general agents with scoring data and limitation analysis.
Read more →
Product Reviews·5 min
Nano AI Agent Hands-On Review: Real Experience and In-Depth Evaluation of Free MCP Tools
In-depth hands-on review of Nano AI agent with Guizhou travel guide and Pop Mart business analysis tasks. Free MCP tools, zero setup, 10-min reports with detailed pros/cons analysis.
Read more →
Deep Dives·3 min
Harness Engineering: The Core Engineering Methodology for Taking AI Agents from Demo to Production
Deep dive into Harness Engineering: its definition, six core components, and production practices. Learn why Prompt and Context Engineering aren't enough for production-grade AI Agent systems.
Read more →
Deep Dives·4 min
Codex Is More Than Code: A Complete Analysis of How OpenAI's Agent Is Reshaping Knowledge Work
OpenAI Codex has evolved from a coding tool into a general-purpose AI agent covering project management, information synthesis, and personal automation. Deep dive into real usage, /goal mode, enterprise security, and tips.
Read more →
Research·4 min
Skills-Oriented Programming: Domain Knowledge Engineering for Efficient Code Generation by Code Agents
Alibaba Mama's Skills-Oriented Programming methodology uses three-layer Skill structures, progressive disclosure, and four-layer anti-corruption systems to achieve 90%+ code generation accuracy for Code Agents in complex enterprise codebases.
Read more →
Tutorials·4 min
Anthropic's Official Agent Building Guide: A Complete Breakdown of Workflows vs. Agents
Deep dive into Anthropic's Building effective agents guide: workflow vs. agent distinctions, the technical selection pyramid, and framework pitfalls for building efficient LLM agents.
Read more →
Product Reviews·4 min
Get Shit Done: Full Breakdown of the 60K-Star Claude Code Meta-Prompting & Spec-Driven Development System
Deep dive into Get Shit Done (GSD), a 62K-star GitHub project built for Claude Code. Covers meta-prompting, context engineering & spec-driven development.
Read more →
Tutorials·4 min
Manus AI Tutorial: The Three-Layer Expression Method to Triple Your Efficiency (With 19 Real-World Scenarios)
A detailed guide to Manus AI Agent's core capabilities and usage techniques, using the Three-Layer Expression Method to issue precise instructions across 19 real-world scenarios including workplace reporting, data analysis, and side income.
Read more →
Tutorials·3 min
Andrew Ng's 2026 New Course: 4 Core Techniques to Go from AI Prompting Beginner to Expert
Andrew Ng's 2026 AI prompting course: master 4 core principles from context-giving and deep thinking to overcoming sycophancy and iterative workflows.
Read more →
Deep Dives·3 min
Two Root Causes of Agent Context Rot: Distraction vs. Poisoning Explained
AI Agent getting dumber over time? Context Rot has two root causes: Distraction (attention dilution) and Poisoning (causal chain contamination). Learn symptoms, mechanisms, and remediation strategies.
Read more →
Tutorials·4 min
Hermes Agent in Practice: Building a Memory-Persistent AI Assistant with a Four-Layer Memory System
Deep dive into Hermes Agent's four-layer memory system architecture, covering Harness Engineering principles, Lark integration, persistent memory configuration, and autonomous Skill evolution for building AI assistants that never forget.
Read more →
Tutorials·3 min
Ollama + OpenCode Local AI Coding: A Complete Zero-Cost Alternative to Cursor
Tutorial: Deploy Qwen3 Coder locally via Ollama with OpenCode for zero-cost AI coding. Covers setup, code generation, auto-debugging, and hardware recommendations.
Read more →
Product Reviews·3 min
Open Design: A Local-First Open Source Alternative to Claude Design with 40K+ GitHub Stars
Open Design is a local-first open source AI design tool with 40K+ GitHub Stars, featuring 19 design skills, 71 brand-grade design systems, and compatibility with 9+ AI tools including Claude Code and Cursor.
Read more →
Product Reviews·3 min
How to Use Gemini 3.1 Pro in China? 5 Solutions Tested and Compared
A detailed comparison of 5 ways to use Gemini 3.1 Pro from China: Google AI Studio, Gemini official site, 2233.ai relay, API relay, and POE — analyzed by network requirements, cost, and features.
Read more →
Tutorials·4 min
Avoiding Pitfalls in Agent Skill Maintenance: A Practical Guide to Defending Against Perplexity's "Action at a Distance" and Building Evaluation Systems
Deep dive into Perplexity's "Action at a Distance" risk in Agent Skill maintenance, covering precise fixes for three failure types, the Gotcha flywheel, and a four-layer evaluation system.
Read more →
Product Reviews·3 min
Claude Code 2.0 Review: Rewind Rollback, Usage Monitoring, and Other Practical New Features
In-depth review of Claude Code 2.0's three core features: Usage monitoring, Rewind code rollback, and Ctrl+R prompt search, plus Sonnet 4.5 model and VS Code extension insights.
Read more →
Product Reviews·3 min
Claude Haiku 4.5 In-Depth Review: Twice the Speed, But Can It Replace Sonnet?
Independent developer benchmarks Claude Haiku 4.5 vs Sonnet in agentic coding using a multi-agent monitoring system, revealing speed gains, precision gaps, and the optimal model hierarchy strategy.
Read more →
Product Reviews·2 min
Claude Haiku 4.5 In-Depth Review: One-Third the Cost, Coding Performance Rivaling Sonnet 4
Anthropic releases Claude Haiku 4.5: coding rivaling Sonnet 4 at 1/3 the cost and 2x speed. A dev built browser-based macOS for just 28 cents, redefining small AI model capabilities.
Read more →
Expert Opinions·3 min
Vibe Coding Crashes and Burns After Seven Months: 234 Commits Archived, Rewriting Everything from Scratch
A developer Vibe Coded with AI for 7 months, made 234 commits and 1,690 lines of code, then the project collapsed. Five hard lessons reveal AI's true limits: it builds features, not architecture.
Read more →
Tutorials·3 min
Conversation as Development: Rapidly Building an EHS Safety Management Platform with AI Agents
Learn how AI application generation Agents use natural language to rapidly build a complete EHS safety management platform with nine core modules, compressing development from months to hours.
Read more →