DEV Community

weiwuji profile picture

weiwuji

404 bio not found

Joined Joined on 
From Loop to Graph: Our 52-Day Agent Engineering Evolution

From Loop to Graph: Our 52-Day Agent Engineering Evolution

Comments
5 min read
Self-Improving Agents Are Not a Myth: A Complete Loop from Error-Ledger to Loop Engineering

Self-Improving Agents Are Not a Myth: A Complete Loop from Error-Ledger to Loop Engineering

Comments
4 min read
数智化转型实战·第三篇:从SOP到组织免疫力——让事故变成能力

数智化转型实战·第三篇:从SOP到组织免疫力——让事故变成能力

Comments
9 min read
In Diagrams, Precision > Pretty: Why AI Technical Articles Use Code-Generated Images

In Diagrams, Precision > Pretty: Why AI Technical Articles Use Code-Generated Images

Comments
3 min read
The Choice Can't Stop at Tools: Agent Content Flywheel, Two Ways to Spin

The Choice Can't Stop at Tools: Agent Content Flywheel, Two Ways to Spin

Comments
3 min read
Practice = Technology x Scenario x Value: What Cognitive Monetization Means in the AI Era

Practice = Technology x Scenario x Value: What Cognitive Monetization Means in the AI Era

Comments
4 min read
DeepSeek Open-Sourced Its Harness: Everything Is a Plugin, But the Real Gap Is in the Details

DeepSeek Open-Sourced Its Harness: Everything Is a Plugin, But the Real Gap Is in the Details

Comments
5 min read
DeepSeek Open-Sourced Its Harness (Merged)

DeepSeek Open-Sourced Its Harness (Merged)

Comments
1 min read
From Documents to Mechanisms: Onboarding AI Agents with SOP + Checkpoints

From Documents to Mechanisms: Onboarding AI Agents with SOP + Checkpoints

Comments
9 min read
"Stop Testing Final Answers: Trajectory Evals Are the Truth About Agent Quality"

"Stop Testing Final Answers: Trajectory Evals Are the Truth About Agent Quality"

Comments
5 min read
"DeepSeek-V4 Pro: Everyone Is Benchmarking It, I'm Running It in Real Business Scenarios"

"DeepSeek-V4 Pro: Everyone Is Benchmarking It, I'm Running It in Real Business Scenarios"

Comments
5 min read
Stop Testing Final Answers: Trajectory Evals (Merged)

Stop Testing Final Answers: Trajectory Evals (Merged)

Comments
5 min read
DeepSeek-V4 Pro Just Launched: Benchmarks Near Fable5 (Merged)

DeepSeek-V4 Pro Just Launched: Benchmarks Near Fable5 (Merged)

Comments
5 min read
From One-Person Methodology to Team Assets: The 4-Step AI Materialization

From One-Person Methodology to Team Assets: The 4-Step AI Materialization

Comments
10 min read
Selling the System: From Real Scenarios to a Replicable AI Agent Business

Selling the System: From Real Scenarios to a Replicable AI Agent Business

Comments
9 min read
MCP + A2A + AG-UI: How the Three Protocols Combine — The 2026 Agent Infrastructure Panorama

MCP + A2A + AG-UI: How the Three Protocols Combine — The 2026 Agent Infrastructure Panorama

Comments
3 min read
Supervisor Architecture: When a Team of Agents Needs a Manager

Supervisor Architecture: When a Team of Agents Needs a Manager

Comments
4 min read
AG-UI: When Your Agent Stops Hiding in the Chat Box — The 2026 Evolution of the Human-Agent Layer

AG-UI: When Your Agent Stops Hiding in the Chat Box — The 2026 Evolution of the Human-Agent Layer

Comments
4 min read
A2A Protocol: When Your Agent Starts Talking to Other Agents

A2A Protocol: When Your Agent Starts Talking to Other Agents

Comments
4 min read
MCP Isn''t a New Concept — It''s the "USB Port" for AI Agents

MCP Isn''t a New Concept — It''s the "USB Port" for AI Agents

Comments
4 min read
一个人也能做A/B测试——AI驱动的自动化优化系统

一个人也能做A/B测试——AI驱动的自动化优化系统

Comments
10 min read
Which Channel Brings Your Paying Users? AI Analytics Pipeline for Content

Which Channel Brings Your Paying Users? AI Analytics Pipeline for Content

Comments
12 min read
Automate Your Blog Images: AI + SVG Architecture Diagrams (Precision > Pretty)

Automate Your Blog Images: AI + SVG Architecture Diagrams (Precision > Pretty)

Comments
7 min read
From 996 to 007: AI Agent Self-Healing Ops Stack

From 996 to 007: AI Agent Self-Healing Ops Stack

Comments
10 min read
The Last Mile of Commercial Agents: Tool Isolation and Least-Privilege Engineering

The Last Mile of Commercial Agents: Tool Isolation and Least-Privilege Engineering

Comments
5 min read
Correction Sedimentation: How AI Agents Never Repeat the Same Mistake

Correction Sedimentation: How AI Agents Never Repeat the Same Mistake

Comments
5 min read
The Observability Trio: Gate + Audit + Correction — A Feedback Loop for Commercial Agents

The Observability Trio: Gate + Audit + Correction — A Feedback Loop for Commercial Agents

Comments
5 min read
报告不是场景,是管道——Agent复合流程容器实战

报告不是场景,是管道——Agent复合流程容器实战

Comments
5 min read
Two-Layer Classification: Regex Pre-Filter + AI Semantic Routing for Agents

Two-Layer Classification: Regex Pre-Filter + AI Semantic Routing for Agents

Comments
5 min read
Four Paradigm Shifts in AI Engineering: From Prompt to Loop (2026) — Which Level Are You On?

Four Paradigm Shifts in AI Engineering: From Prompt to Loop (2026) — Which Level Are You On?

Comments
6 min read
The Sandwich Architecture: Wrapping a Probabilistic LLM in Deterministic Code

The Sandwich Architecture: Wrapping a Probabilistic LLM in Deterministic Code

Comments
7 min read
The One-Person Editorial Department: An AI Automated Content Factory

The One-Person Editorial Department: An AI Automated Content Factory

Comments
10 min read
The 4-Layer AI Agent Architecture of an OPC Operating System

The 4-Layer AI Agent Architecture of an OPC Operating System

Comments
9 min read
AI Agent Infrastructure: The $350/Year Stack Behind an OPC

AI Agent Infrastructure: The $350/Year Stack Behind an OPC

1
Comments 1
11 min read
Writing Code Isn't Enough — Self-Attack Testing Is the Hardest Test Your Agent Will Face

Writing Code Isn't Enough — Self-Attack Testing Is the Hardest Test Your Agent Will Face

Comments
9 min read
From 30 Files to 2: How I Slimmed My Agent System Down 90%

From 30 Files to 2: How I Slimmed My Agent System Down 90%

Comments
8 min read
4 AI Automation Pipelines for a Practitioner: Content, Replies, Data & Monitoring

4 AI Automation Pipelines for a Practitioner: Content, Replies, Data & Monitoring

Comments
13 min read
AI Agent DevOps: Health Checks, Alerts, Runbooks & Cost Control for a Real Business Scenario

AI Agent DevOps: Health Checks, Alerts, Runbooks & Cost Control for a Real Business Scenario

Comments
29 min read
Quality Isn't Accidental — AI Agent Maker/Checker Separation and Audit

Quality Isn't Accidental — AI Agent Maker/Checker Separation and Audit

Comments
6 min read
How Much Memory Does Your Agent Need? — A Practical Memory Store Selection Guide

How Much Memory Does Your Agent Need? — A Practical Memory Store Selection Guide

Comments
5 min read
Why Your AI Agent Forgets Everything Overnight — From Prompt to Loop Engineering

Why Your AI Agent Forgets Everything Overnight — From Prompt to Loop Engineering

1
Comments
5 min read
Why Your "All-Powerful" Agent Fails — Scene Routing That Splits One Agent into 6 Experts

Why Your "All-Powerful" Agent Fails — Scene Routing That Splits One Agent into 6 Experts

Comments
3 min read
loading...