BestHub
Sign in
Architecture Musings
Author

Architecture Musings

When the AI wave arrives, it feels like we've reached the frontier of technology. Here, an architect records observations and reflections on technology, industry, and the future amid the upheaval.

12
Articles
0
Likes
11
Views
0
Comments
Recent Articles

Latest from Architecture Musings

12 recent articles
Architecture Musings
Architecture Musings
May 22, 2026 · Industry Insights

Deep Dive into ThoughtWorks Tech Radar Vol. 34: Engineering Practices and Cognitive Re‑construction in the Agent Era

The article analyzes ThoughtWorks Technology Radar Vol. 34, highlighting how the rise of AI‑driven agents reshapes software engineering evaluation, introduces semantic diffusion and cognitive debt, and forces a return to classic practices while spotlighting newly adopted tools like Kafbat UI and Typer and warning about emerging anti‑patterns.

AIAgentic SystemsCognitive Debt
0 likes · 34 min read
Deep Dive into ThoughtWorks Tech Radar Vol. 34: Engineering Practices and Cognitive Re‑construction in the Agent Era
Architecture Musings
Architecture Musings
May 21, 2026 · R&D Management

Why DORA Is Being Revived in the AI Era as a Timeless R&D Efficiency Metric

The article analyzes how generative AI has boosted individual coding speed but caused a 7.2% drop in team delivery stability, explains why the classic DORA metrics are being re‑emphasized, identifies their blind spots in the AI age, and offers a concrete, multi‑stage roadmap for building a modern R&D effectiveness measurement system.

AIDORADevEx
0 likes · 24 min read
Why DORA Is Being Revived in the AI Era as a Timeless R&D Efficiency Metric
Architecture Musings
Architecture Musings
Apr 20, 2026 · Industry Insights

ThoughtWorks Technology Radar Vol. 34: Engineering Practices and Cognitive Shifts in the Agent Era

The article analyses ThoughtWorks' 34th Technology Radar, revealing how the rise of AI agents forces a reassessment of software engineering fundamentals, introduces semantic diffusion, cognitive debt, security risks, and highlights both newly adopted tools like Kafbat UI and Typer and a set of cautionary practices that demand tighter control and context engineering.

AIAgent SystemsCognitive Debt
0 likes · 34 min read
ThoughtWorks Technology Radar Vol. 34: Engineering Practices and Cognitive Shifts in the Agent Era
Architecture Musings
Architecture Musings
Apr 19, 2026 · Artificial Intelligence

My AI Adoption Journey: Lessons from the Terraform and Ghostty Creator

The author, Mitchell Hashimoto—co‑founder of HashiCorp and creator of Terraform and Ghostty—shares a step‑by‑step, candid account of adopting AI agents, detailing six phases from abandoning chatbots to continuously running agents, the concept of “harness engineering,” and practical insights on when and how to integrate AI into a developer workflow.

AI adoptionGhosttyHarness Engineering
0 likes · 16 min read
My AI Adoption Journey: Lessons from the Terraform and Ghostty Creator
Architecture Musings
Architecture Musings
Apr 17, 2026 · Artificial Intelligence

Building AI‑Native Design Docs with Architecture as Code

The article explains why traditional diagram‑as‑code approaches fall short for AI agents, introduces Architecture as Code as a structured, version‑controlled alternative, discusses the role of interface contracts and narrative documentation, and outlines the need for deterministic context engineering to make design documents truly live for both humans and machines.

AI agentsArchitecture as CodeContext Engineering
0 likes · 22 min read
Building AI‑Native Design Docs with Architecture as Code
Architecture Musings
Architecture Musings
Apr 7, 2026 · Artificial Intelligence

Why I Reject the Equation Agent = LLM + Harness

The article argues that equating an AI agent with merely an LLM plus engineering harness oversimplifies the agent’s true cognitive core—memory, planning, and tool use—and warns that such a formula risks cementing a temporary engineering compromise into a lasting ontological definition.

AI PlanningAgent ArchitectureHarness
0 likes · 10 min read
Why I Reject the Equation Agent = LLM + Harness
Architecture Musings
Architecture Musings
Apr 4, 2026 · Industry Insights

Exploring the Harness Architecture Concept: A First Look

This article examines the emerging "Harness Architecture" idea, arguing that constraints should be applied before AI code generation by leveraging stepwise refinement, modular contracts, and living design documents to improve precision, reduce token usage, and prevent architectural drift in large software projects.

AI EngineeringHarness architectureSpec-Driven Development
0 likes · 8 min read
Exploring the Harness Architecture Concept: A First Look
Architecture Musings
Architecture Musings
Apr 2, 2026 · Artificial Intelligence

Claude Code Exposed: Two Real Pitfalls That Reveal Fatal AI Agent Traps

Switching from IDE plugins to the Claude Code CLI AI agent can dramatically speed up code generation, but the author’s two real‑world incidents reveal how blind reliance creates black‑box code, context vacuums, and confident hallucinations that inflate technical debt and jeopardize maintainability.

AI agentClaude Codecode generation
0 likes · 9 min read
Claude Code Exposed: Two Real Pitfalls That Reveal Fatal AI Agent Traps
Architecture Musings
Architecture Musings
Mar 26, 2026 · Artificial Intelligence

OpenAI vs Anthropic: Two Harness Strategies for Code Agent Engineering

Both OpenAI and Anthropic published 2026 papers on AI Code Agents, but they propose opposite harness designs—OpenAI relies on strict structural constraints and linter‑driven engineering, while Anthropic uses a three‑agent evaluation loop—offering a detailed comparison of their mechanisms, trade‑offs, costs, and suitable use cases.

AI agentsAnthropicHarness Engineering
0 likes · 20 min read
OpenAI vs Anthropic: Two Harness Strategies for Code Agent Engineering