Author

Linyb Geek Road

Tech notes

181

Articles

Likes

1.1k

Views

Comments

Latest from Linyb Geek Road

100 recent articles max

Linyb Geek Road

Jul 15, 2026 · Artificial Intelligence

From ReAct to Harness: Building Production‑Ready Agent Architectures

The article outlines the five‑stage evolution of AI agents—from the basic ReAct loop to self‑driving, self‑optimizing systems—and presents six engineering pillars (verification, stop, state, recovery, isolation, observability) that together form a Harness framework for deploying reliable, production‑grade agents.

AI AgentsObservabilityagent architecture

0 likes · 8 min read

From ReAct to Harness: Building Production‑Ready Agent Architectures

Linyb Geek Road

Jul 14, 2026 · Artificial Intelligence

Understanding MCP, Skill, Harness, and Loop: A Deep Dive into the Four‑Layer AI Agent Architecture

The article breaks down the four‑layer AI Agent stack—MCP protocol, Agent Skill, Harness runtime, and Loop engineering—showing how each layer solves distinct problems, presenting benchmark data (e.g., a 25.7 pp SWE‑bench gain from Harness changes), security analyses, design trade‑offs, and a production checklist.

AI Agent ArchitectureAgent HarnessAgent Skill

0 likes · 26 min read

Understanding MCP, Skill, Harness, and Loop: A Deep Dive into the Four‑Layer AI Agent Architecture

Linyb Geek Road

Jul 13, 2026 · Artificial Intelligence

Why AI Agents Crash and How Harness & Loop Engineering Make Them Run Autonomously

The article explains why AI agents frequently fail in production, identifies four core runtime failure modes, and shows how a two‑layer architecture—Harness for stability and Loop engineering for autonomous scheduling—combined with concrete configurations, memory tiering, and verification loops can keep agents running reliably.

AI AgentHarnessLoop Engineering

0 likes · 18 min read

Why AI Agents Crash and How Harness & Loop Engineering Make Them Run Autonomously

Linyb Geek Road

Jul 12, 2026 · Operations

Designing a High‑Availability Architecture: Core Principles and Practices

This article outlines the essential principles for building a high‑availability system, covering cluster and distributed designs, fault‑tolerance, reliable hardware, disaster recovery, monitoring, security, capacity planning, and automated scaling to achieve optimal performance and resilience.

Capacity Planningautomationcluster architecture

0 likes · 6 min read

Designing a High‑Availability Architecture: Core Principles and Practices

Linyb Geek Road

Jul 11, 2026 · Artificial Intelligence

Why Are AI Agent Bills Soaring? Token‑Saving Techniques to Cut Costs

The article explains that most token cost comes from system‑added context rather than the user query, breaks down cost components, and offers a hierarchy of optimizations—from usage habits and prompt caching to model routing, tool management, and output compression—to dramatically reduce AI coding agent expenses.

AI AgentPrompt Cachecontext compression

0 likes · 23 min read

Why Are AI Agent Bills Soaring? Token‑Saving Techniques to Cut Costs

Linyb Geek Road

Jul 11, 2026 · Artificial Intelligence

How to Slash Token Costs When Using AI Agents

The article analyzes why AI agents quickly consume token quotas and presents seven practical strategies—shortening sessions, avoiding parallel sub‑agents, giving concise prompts, providing precise context, pre‑defining rules, automating mechanical tasks, and investing in clear prompts—to dramatically reduce token usage and lower operational costs.

AI AgentsPrompt Engineeringautomation

0 likes · 10 min read

How to Slash Token Costs When Using AI Agents

Linyb Geek Road

Jul 10, 2026 · Artificial Intelligence

Unlock AI Coding Superpowers with Spec‑Driven Development

The article explains how writing clear specification documents—detailing required features, prohibitions, and acceptance criteria—guides AI code generators to produce reliable, secure code, avoiding guesswork and over‑implementation, and shows how this disciplined approach becomes a programmer’s most valuable skill in the age of AI.

AI code generationPrompt EngineeringSpec-Driven Development

0 likes · 13 min read

Unlock AI Coding Superpowers with Spec‑Driven Development

Linyb Geek Road

Jul 10, 2026 · Artificial Intelligence

Why Writing Specs Is Just Writing Code Again – The Double‑Watch Dilemma

The article argues that detailed specification documents for AI agents end up being as verbose and bug‑prone as actual code, turning a single spec into two code‑like artifacts and exposing a "precision conservation" law that makes AI‑generated code unreliable.

AI code generationPrompt Engineeringautomation

0 likes · 16 min read

Why Writing Specs Is Just Writing Code Again – The Double‑Watch Dilemma

Linyb Geek Road

Jul 9, 2026 · Artificial Intelligence

Implementing AI Agents with Andrew Ng’s Loop Engineering: A Practical Guide

The article explains Andrew Ng’s Loop Engineering framework—three nested feedback loops that transform AI‑assisted coding from manual babysitting into an automated pipeline, and provides concrete steps, tool recommendations, and evaluation‑standard guidelines for building reliable AI agents.

AI AgentsAI developmentLoop Engineering

0 likes · 10 min read

Implementing AI Agents with Andrew Ng’s Loop Engineering: A Practical Guide

Linyb Geek Road

Jul 8, 2026 · Industry Insights

Is Spec‑Driven Development a Savior or a Burden in the Age of AI‑Generated Code?

The article analyses how AI‑generated code creates massive technical debt, explains Spec‑Driven Development (SDD) and its three maturity levels, evaluates three real‑world tools—Kiro, spec‑kit and Tessl—through concrete metrics and expert commentary, and finally advises when SDD is worthwhile and when it becomes a heavyweight process.

AI code generationKiroSpec-Driven Development

0 likes · 17 min read

Is Spec‑Driven Development a Savior or a Burden in the Age of AI‑Generated Code?