Tagged articles
agent design
38 articles · Page 1 of 1
The author uses an AI agent to auto-generate daily WeChat articles, showing how it adapts when APIs fail, documents its reasoning, and delivers editable drafts — unlike rigid scripts that break on unexpected errors. To make AI a reliable colleague, three requirements are essential: data visibility, operational boundaries, and audit trails.
AI agentsLLM Applicationsagent design
0 likes · 7 min read

This lesson distills five design principles, five over‑engineering signals, a decision‑matrix, and a ten‑point checklist for building effective Harness agents, illustrating each with concrete examples, trade‑offs, and practical guidance on when to use or avoid specific components.
AI agentsContext ManagementDecision Matrix
0 likes · 30 min read

The article examines recursive self‑improvement in AI, arguing that a well‑designed harness—responsible for workflow orchestration, context management, and tool integration—is as crucial as model intelligence, and outlines design patterns, meta‑engineering approaches, evolutionary search methods, and the remaining challenges for truly autonomous AI systems.
AI self‑improvementEvolutionary SearchHarness Engineering
0 likes · 17 min read

The article analyzes the growing “Skill Hell” problem in AI agent engineering—where excessive rules and redundant skills overload context—and presents Matt Pocock’s step‑by‑step methodology for classifying triggers, streamlining skill documents, using concise leading words, splitting tasks, and applying a deletion test to create lean, reliable agent skills.
AI agentContext ManagementSkill Hell
0 likes · 12 min read

The article outlines a four‑layer architecture for a data analysis agent—intent recognition, data acquisition via NL2SQL, analysis execution, and result presentation—while detailing practical methods to boost NL2SQL accuracy and illustrating real‑world e‑commerce, operations, and finance use cases.
NL2SQLSQL Safetyagent design
0 likes · 5 min read

By 2026, AI product managers must shift from merely using models to delivering stable, valuable results, mastering seven core abilities—demand judgment, evaluation-driven iteration, context design, RAG strategy, agent orchestration, solution planning, and rapid Vibe Coding—to close the loop between business needs and AI capabilities.
AI Product ManagementProduct solutionRAG
0 likes · 13 min read

The article analyzes how extending the context window of large language models leads to rapid forgetting, outlines seven concrete failure modes, examines cognitive‑science‑based memory architectures, and walks through practical layers—from Python lists to markdown files to vector retrieval—highlighting why simple context expansion alone cannot solve the problem.
LLM memoryagent designcognitive architecture
0 likes · 10 min read

The article analyzes why memory extraction in LLM‑driven agents incurs cost, compares four frameworks—Claude Code, Generative Agents, MemGPT, and Mem0—detailing their trigger mechanisms, concurrency handling, and trade‑offs, and offers practical guidance for choosing the right strategy in real‑time, social, or batch‑processing scenarios.
AI EngineeringLLMagent design
0 likes · 18 min read


AntDataApr 17, 2026 · Industry Insights
This article shares the practical lessons learned from building Dataphin‑MCP, an AI‑enabled data‑development platform, by outlining five concrete "silver" rules, illustrating each with real‑world cases, and discussing deeper considerations for building robust AI‑first tools and harnesses.
AI PlatformConcept modelingContext Management
0 likes · 13 min read

This tutorial explains the three-stage evolution from Prompt Engineering to Context Engineering and finally Harness Engineering, detailing their motivations, core components, practical implementations, and why stable, end‑to‑end AI agents require a full harness to manage tasks, context, tools, execution, state, and error recovery.
AI systemsHarness Engineeringagent design
0 likes · 31 min read


JavaGuideApr 14, 2026 · Artificial Intelligence
The article explains how industrial‑grade AI agents require structured prompt engineering, chain‑of‑thought reasoning, task decomposition, and a three‑layer defense (sandbox, prompt isolation, and human approval) to prevent prompt‑injection attacks, while also covering context engineering, retrieval‑augmented generation, and tool design best practices.
LLM securityagent designchain-of-thought
0 likes · 23 min read

The article dissects twelve concrete harness design patterns uncovered in the leaked Claude Code source, organized into four categories—memory & context, workflow & orchestration, tools & permissions, and automation—detailing their use cases, trade‑offs, and implementation costs for building production‑grade AI agents.
Claude CodeTool Permissionsagent design
0 likes · 14 min read

The article explains why routing every request to the most powerful LLM hurts cost, speed, and throughput, and presents a three‑layer task decomposition that assigns execution‑level tasks to cheap small models, intermediate tasks to mid‑size models, and high‑risk judgment tasks to large models, with concrete examples and a minimal routing strategy.
Cost OptimizationLLMagent design
0 likes · 8 min read


Qborfy AIMar 31, 2026 · Artificial Intelligence
The article introduces the Plan-and-Solve design pattern for AI agents, explaining how separating planning and execution improves handling of complex tasks, compares it with ReAct, provides detailed workflow diagrams, concrete examples such as weekly report generation, and offers a full Python implementation with dynamic replanning and result aggregation.
AI agentsLLMPlan-and-Solve
0 likes · 14 min read

The article analyzes the emerging concept of Harness Engineering—combining AI models with structured environments, standards, and feedback loops—to enable agents that can work continuously, illustrated by OpenAI and Anthropic case studies, practical design guidelines, and a three‑week adoption plan.
AI EngineeringHarness Engineeringagent design
0 likes · 10 min read

Anthropic’s new Auto Mode for Claude Code inserts a middle ground between manual approvals and unrestricted execution by letting the model approve low‑risk actions while blocking potentially dangerous ones, using a two‑stage classifier that evaluates intent and real‑world impact with concrete safety metrics.
AI safetyAuto ModeClassification
0 likes · 12 min read

The article analyzes Anthropic's guidance on building effective AI agents, contrasts workflow and agent architectures, outlines criteria for choosing agents, presents six incremental design patterns, and shares practical principles such as simplicity, transparency, and robust tool interfaces.
AI agentsLLM memoryagent design
0 likes · 9 min read

A sudden wave of OpenClaw uninstall services in 2026 revealed severe AI agent security risks, including default open‑network configurations, persistent OAuth tokens, malicious plugins, runaway costs, and stability crashes, prompting a deep analysis of design flaws and recommended safeguards for future intelligent agents.
AI agentsAI safetyOpenClaw
0 likes · 10 min read

The author explains why Claude Code became too bloated, outlines the minimal, controllable requirements for a code‑assistant, details pi-mono’s four‑package architecture, shares design anti‑patterns, and presents benchmark results showing its simple approach outperforms heavier agents.
Claude OpusLLM Agentsagent design
0 likes · 13 min read

The article explains how large‑model AI can quickly generate seemingly functional code but still lacks product logic, boundary awareness, and security, forcing engineers to act as “post‑processing engineers” who proofread, refactor, and polish AI‑generated artifacts into reliable, production‑ready software.
agent designcode generationpost-processing
0 likes · 8 min read

This article explains how to build a controllable, editable, and cost‑effective long‑term memory system for AI agents by categorizing memory types, structuring a three‑stage pipeline of capture, AI‑driven compression, and smart retrieval, and choosing appropriate storage back‑ends such as files, knowledge bases, or databases.
Long-term Memoryagent designartificial intelligence
0 likes · 18 min read

The article systematically defines and compares the seven key AI programming abstractions—Rules, Commands, Subagents, MCP, Skills, Modes, and Hooks—detailing their core characteristics, typical use cases, implementation patterns, and best‑practice guidelines while highlighting common misunderstand‑ings and design trade‑offs.
AI programmingModesRules
0 likes · 18 min read

Gas Town, a multi‑agent orchestration system introduced by former Google engineer Steve Yegge, coordinates 20‑30 Claude Code instances using Git‑backed hooks, beads, and a Mayor coordinator, promising parallel development, versioned state, fault tolerance, and sparking industry debate on the future of AI‑driven software engineering.
AI agentsGit persistenceagent design
0 likes · 24 min read

The article argues that the recent hype around Skills and the criticism of MCP stem from a mindset problem: developers treat MCP like a REST API wrapper, leading to poor server designs, and it offers six concrete design principles to build agent‑friendly MCP services.
AI toolingAPI DesignMCP
0 likes · 11 min read

This article explains how to build Retrieval‑Augmented Generation (RAG) for industry‑specific AI agents, covering required capabilities, metrics, data sources, indexing, hybrid retrieval, decision‑point integration, layered output, permission controls, rollout strategies, and common pitfalls to ensure reliable and secure automation.
Industry AIKnowledge RetrievalRAG
0 likes · 17 min read

This comprehensive guide explains why traditional prompt engineering is insufficient for complex AI agents, defines context engineering as the art of supplying the right information at the right time, outlines its seven core components, describes the phenomenon of context rot, and presents four practical strategies with real‑world case studies such as Claude Code and Manus.
AI agentsLLMRAG
0 likes · 21 min read

Building AI agents may seem straightforward with frameworks like LangChain, but hidden complexities in orchestration, memory management, reproducibility, and scalability turn simple demos into fragile systems, requiring systematic engineering, observability, and robust design to achieve reliable, production‑grade intelligent agents.
AI agentsLangChainRAG
0 likes · 21 min read

This article distills Anthropic’s “Effective Context Engineering for AI Agents” into key insights, explaining why context engineering matters, how it differs from prompt engineering, what constitutes good practice, and practical techniques—system prompts, tool design, few‑shot prompting, compaction, structured note‑taking, and sub‑agent architectures—to mitigate context overload in large language model agents.
AI agentsLLM Optimizationagent design
0 likes · 10 min read

This article examines the context explosion problem in AI agents and compares three distinct compression approaches—Manus's never‑lose philosophy, Claude Code's aggressive 92% threshold with eight‑section summaries, and Gemini CLI's balanced 70% trigger with curated history—highlighting their trade‑offs in performance, cost, and reliability.
AILLMagent design
0 likes · 19 min read

Context engineering, the emerging discipline of structuring and managing input information for large language models, goes beyond simple prompt design by addressing issues such as context poisoning, overload, and conflict, offering strategies like intelligent retrieval, isolation, pruning, and compression to build reliable, high‑performing AI agents.
AI Productivityagent designcontext engineering
0 likes · 19 min read

This comprehensive guide explores the core implementation paths for large language model (LLM) applications, focusing on agent design, workflow orchestration, tool integration, memory management, multi‑agent architectures, and future trends, providing actionable methodologies and real‑world examples for practitioners.
AI agentLLMagent design
0 likes · 25 min read

Fred’s practical guide expands Anthropic’s “Build effective agents” by offering a technical selection framework, clear definitions of agents versus workflows, a suite of reusable design patterns such as prompt‑chain routing and orchestrator‑worker loops, real‑world case studies, and concrete implementation tips that emphasize simplicity, transparency, and effective tool‑prompt engineering.
AI agentsLLM workflowsagent design
0 likes · 25 min read

The article evaluates the Manus agent’s current strengths in information‑gathering tasks, contrasts collaborative versus fully‑delegated agent models, identifies structural and context limitations that hinder professional‑grade outputs, and speculates on how future agents might bridge this gap.
AIGeneral Agentagent design
0 likes · 5 min read

This article details the end‑to‑end design of Vivo’s custom log‑collection agent, covering file discovery with inotify, unique file identification using inode and content hash, real‑time reading via RandomAccessFile, checkpointing, Kafka integration, offline HDFS ingestion, resource throttling, and platform‑wide management, while comparing it with open‑source alternatives.
KafkaLog Collectionagent design
0 likes · 26 min read

This article presents the design principles, core techniques, and practical solutions of Vivo's self‑developed Bees log collection agent, covering file discovery, unique identification, real‑time and offline ingestion, checkpointing, resource control, platform management, and a comparison with open‑source alternatives.
JavaKafkaLog Collection
0 likes · 25 min read

Vivo’s Bees‑agent is a custom, lightweight log‑collection service that discovers rotating files via inotify, uniquely identifies them with inode and hash signatures, supports real‑time and offline ingestion to Kafka and HDFS, offers checkpoint‑resume, resource isolation, rich metrics, and a centralized management platform, outperforming open‑source collectors in latency, memory usage, and scalability.
HDFSJavaKafka
0 likes · 24 min read

This article analyses the shortcomings of traditional log‑collection agents, compares Flume and Filebeat based on low‑cost, stability, efficiency and lightweight criteria, and presents practical solutions for file discovery, offset tracking, multi‑line handling and performance tuning in modern logging pipelines.
FlumeLog CollectionOperations
0 likes · 13 min read

This article explains the evolution of logging, the role of log‑collection agents, industry solutions, and step‑by‑step techniques for building a reliable push‑mode log collector on Linux, covering file discovery, offset management, file identification, update detection, and safe resource release.
File MonitoringLinuxLog Collection
0 likes · 17 min read
