BestHub
Sign in
Architect Practice
Author

Architect Practice

Committed to sharing tech and documenting ideas.

30
Articles
0
Likes
14
Views
0
Comments
Recent Articles

Latest from Architect Practice

30 recent articles
Architect Practice
Architect Practice
Jun 1, 2026 · Artificial Intelligence

When AI Rate Limiting Goes Wrong: A Four‑Dimension Framework and Three‑Layer Gateway in Practice

A midnight alarm at a fintech AI platform revealed that traditional QPS throttling missed a runaway Agent that consumed hundreds of times more tokens, prompting a detailed analysis of four token‑based limiting dimensions, three‑layer gateway design, agent‑specific controls, semantic caching, and tool selection to prevent similar “ghost avalanche” failures.

AI rate limitingLLM operationsagent safety
0 likes · 20 min read
When AI Rate Limiting Goes Wrong: A Four‑Dimension Framework and Three‑Layer Gateway in Practice
Architect Practice
Architect Practice
May 22, 2026 · Industry Insights

Why AI That Should Make Work Easier Leaves You More Anxious

The article argues that although AI boosts individual productivity, organizations raise expectations, leading to heavier workloads, lower wages, and heightened anxiety—a pattern echoing past industrial revolutions and illustrated through historical examples and the concept of organizational benchmark reconstruction.

AIAutomationFuture of work
0 likes · 10 min read
Why AI That Should Make Work Easier Leaves You More Anxious
Architect Practice
Architect Practice
May 14, 2026 · Artificial Intelligence

Cut Your AI Coding Bill by 80% with Smart Model Routing and Prompt Caching

The author slashed a monthly AI‑coding expense from $4,200 to $312 without changing tools or delivery speed by fixing five token‑waste traps, enabling prompt caching, applying disciplined context handling, and routing tasks to the right model tier, all backed by concrete benchmarks and a 30‑day rollout plan.

AI ProgrammingClaudeKimi
0 likes · 31 min read
Cut Your AI Coding Bill by 80% with Smart Model Routing and Prompt Caching
Architect Practice
Architect Practice
Apr 30, 2026 · Artificial Intelligence

Why Business Agents Can’t Rely Solely on LLMs: Implementing Intent Recognition and Task Decomposition

The article explains that a production‑grade business agent must combine LLM‑driven intent understanding with deterministic rule‑based control, using a perception‑understanding‑planning‑execution‑feedback loop, two‑round prompting, strict JSON schemas, permission checks, and a state‑machine architecture to avoid unsafe, uncontrolled behavior.

Agent ArchitectureBusiness AgentIntent Recognition
0 likes · 23 min read
Why Business Agents Can’t Rely Solely on LLMs: Implementing Intent Recognition and Task Decomposition
Architect Practice
Architect Practice
Apr 28, 2026 · R&D Management

When the Boss Says “Let AI Do It”, Here’s the 7‑Stage SOP That Proves It’s Not a One‑Liner

The article presents a detailed 7‑stage SOP that transforms a vague “let AI handle it” request into a structured, verifiable development pipeline—covering requirement clarification, impact analysis, design, planning, TDD implementation, systematic debugging, dual‑review, and evidence‑based verification—showing why AI is not a magic wand.

AIDevOpsProcess Automation
0 likes · 22 min read
When the Boss Says “Let AI Do It”, Here’s the 7‑Stage SOP That Proves It’s Not a One‑Liner
Architect Practice
Architect Practice
Apr 12, 2026 · Artificial Intelligence

What Engineering Problems Does Claude Code’s Harness Engineering Solve?

The article dissects Claude Code’s open‑source TypeScript implementation to reveal the five‑layer Harness Engineering architecture—Query Loop, system‑prompt assembly, tool orchestration, multi‑level context compression, and multi‑Agent coordination—showing how each layer solves concrete engineering challenges for reliable AI agents.

AI AgentContext CompressionHarness Engineering
0 likes · 20 min read
What Engineering Problems Does Claude Code’s Harness Engineering Solve?
Architect Practice
Architect Practice
Apr 7, 2026 · Backend Development

The 8 Characters in a Text Message Reveal Hidden Challenges in Short‑Link System Design

This article walks through the end‑to‑end design of a lightweight short‑link service, covering why short links are needed, the choice of 302 redirects, key‑generation strategies (MurmurHash vs ID‑based base62), caching layers, security threats, scaling techniques, and practical pitfalls, all illustrated with concrete code and benchmark numbers.

base62 encodingcachingdistributed ID
0 likes · 25 min read
The 8 Characters in a Text Message Reveal Hidden Challenges in Short‑Link System Design
Architect Practice
Architect Practice
Mar 27, 2026 · Artificial Intelligence

Spec‑Driven Development: A New AI‑Era Paradigm That Stops LLMs from Guessing Your Requirements

The article critiques the chaotic "Vibe Coding" approach of prompting LLMs for code, introduces Spec‑Driven Development (SDD) as a structured, contract‑based methodology that uses a formal specification to guide AI agents through design, implementation and testing, and demonstrates its efficiency gains, maturity levels, tool ecosystem, and practical step‑by‑step workflow.

AI codingLLMSpecflow
0 likes · 21 min read
Spec‑Driven Development: A New AI‑Era Paradigm That Stops LLMs from Guessing Your Requirements