BestHub
Sign in
Architect
Author

Architect

Professional architect sharing high‑quality architecture insights. Topics include high‑availability, high‑performance, high‑stability architectures, big data, machine learning, Java, system and distributed architecture, AI, and practical large‑scale architecture case studies. Open to ideas‑driven architects who enjoy sharing and learning.

1.4k
Articles
0
Likes
2.6k
Views
0
Comments
Recent Articles

Latest from Architect

100 recent articles max
Architect
Architect
Apr 28, 2026 · Artificial Intelligence

Agent Harness Context: Chat Log vs. Workset – How Runtime Management Shapes Long‑Running Agents

The article argues that an agent harness’s context window should be treated as a bounded workset rather than an ever‑growing transcript, and explains how pagination, compression, tool‑output limits, session isolation, and sub‑agent design together determine whether long‑running agents remain reliable and efficient.

Agent HarnessCompressionContext Management
0 likes · 24 min read
Agent Harness Context: Chat Log vs. Workset – How Runtime Management Shapes Long‑Running Agents
Architect
Architect
Apr 27, 2026 · Artificial Intelligence

Sub-Agent vs Agent Team: Designing Multi-Agent Architectures Around Context Boundaries

The article explains how to choose between Sub‑Agent and Agent Team structures for multi‑agent systems by evaluating whether sub‑tasks share context, need isolation, compression, parallelism, or continuous collaboration, and provides practical guidelines, pitfalls, and a decision framework to avoid over‑engineering.

AI ArchitectureAgent TeamContext Boundaries
0 likes · 18 min read
Sub-Agent vs Agent Team: Designing Multi-Agent Architectures Around Context Boundaries
Architect
Architect
Apr 26, 2026 · Artificial Intelligence

Designing Products for Agents: Beyond APIs and MCPs

The article argues that building products for AI agents requires more than swapping UI pages for APIs or adding MCPs; it demands reorganizing product capabilities into actions that agents can understand, invoke, be constrained by, and audit, while addressing semantics, governance, and reliability.

AI agentsAPIAgent architecture
0 likes · 26 min read
Designing Products for Agents: Beyond APIs and MCPs
Architect
Architect
Apr 25, 2026 · Artificial Intelligence

DeepSeek V4: 1M‑Token Context’s Impact on Model, Inference, Cache & Agents

The DeepSeek V4 technical report shows how a 1 million‑token context forces a redesign of attention, KV‑cache, optimizer, quantization and inference budgeting, turning long‑context capability from a costly showcase into a production‑ready feature for agents, search and Chinese professional tasks.

1M contextDeepSeekKV cache
0 likes · 28 min read
DeepSeek V4: 1M‑Token Context’s Impact on Model, Inference, Cache & Agents
Architect
Architect
Apr 24, 2026 · Artificial Intelligence

How Hermes Agents Self‑Evolve: What Should Remain After a Task?

The article examines Hermes Agent’s three‑layer memory system—facts, session retrieval, and process assets—detailing how Skills are created, stored, patched, and secured at runtime, and argues that reliable self‑evolution requires disciplined versioning, evaluation, and access controls rather than unchecked automatic skill generation.

AI SkillsHermes AgentProcess Assets
0 likes · 21 min read
How Hermes Agents Self‑Evolve: What Should Remain After a Task?
Architect
Architect
Apr 23, 2026 · Artificial Intelligence

What Exactly Belongs in a .claude/ Folder? A Beginner’s Guide

This article explains the purpose and layered structure of the .claude/ directory in Claude Code projects, detailing what files belong in CLAUDE.md, settings.json, hooks, commands, skills, and agents, and how to organize project‑level versus user‑level configurations for reliable, maintainable AI‑assisted development.

AI agentsClaude CodeSkills
0 likes · 32 min read
What Exactly Belongs in a .claude/ Folder? A Beginner’s Guide
Architect
Architect
Apr 20, 2026 · Artificial Intelligence

Why a Tiny Agent Loop Exposes the Real Engineering Hurdles of AI Agents

The article walks through building a minimal 20‑line agent loop, explains each step—from reading a task to invoking tools and feeding observations back—then shows how real systems like Claude Code, OpenClaw and Pi add layers of harness, memory, permission and validation to make the loop safe and reliable in production.

AI AgentFunction CallingHarness
0 likes · 23 min read
Why a Tiny Agent Loop Exposes the Real Engineering Hurdles of AI Agents
Architect
Architect
Apr 19, 2026 · Artificial Intelligence

Why Your AI Agent’s Success Depends on the Harness, Not Just the Model

The article explains that an Agent Harness is the complete runtime system surrounding a language model—handling the main loop, tools, context, state, permissions, and validation—and shows why this engineering layer, not the model itself, determines the stability and scalability of AI agents.

AI AgentContext ManagementHarness Engineering
0 likes · 23 min read
Why Your AI Agent’s Success Depends on the Harness, Not Just the Model
Architect
Architect
Apr 18, 2026 · Artificial Intelligence

Why Multi‑Agent Systems Need More Than Role‑Playing: 5 Coordination Patterns Explained

Anthropic’s recent analysis reveals five multi‑agent coordination patterns—Generator‑Verifier, Orchestrator‑Subagent, Agent Teams, Message Bus, and Shared State—highlighting that the real challenges lie in context boundaries, information flow, verification standards, and termination conditions rather than merely assigning roles.

AI ArchitectureAgent orchestrationCoordination Patterns
0 likes · 30 min read
Why Multi‑Agent Systems Need More Than Role‑Playing: 5 Coordination Patterns Explained