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.

1.6k
Articles
0
Likes
10.0k
Views
0
Comments
Recent Articles

Latest from Architect

100 recent articles max
Architect
Architect
Sep 6, 2026 · Artificial Intelligence

Vector Databases Aren't Dead: How Claude Code & Cursor Are Redefining RAG for Agents

The article debunks claims that vector databases are obsolete, analyzing how Claude Code and Cursor integrate retrieval into agent runtime loops rather than abandoning RAG, and proposes a five-layer architecture where vector indexes serve as retrieval projections alongside grep, semantic search, and authoritative sources.

AI AgentsAgent ArchitectureClaude Code
0 likes · 21 min read
Vector Databases Aren't Dead: How Claude Code & Cursor Are Redefining RAG for Agents
Architect
Architect
Sep 5, 2026 · Artificial Intelligence

Codex's Context Management Redesign: Four-State Architecture for Long-Running Agents

The article analyzes Codex CLI's experimental context management system (v0.153.0), which replaces monolithic compaction with four distinct state types—current working set, handoff notes, searchable history, and external facts—detailing the model-driven window-switching protocol, token budget exposure, harness fallback mechanisms, and recovery considerations for long-running coding agents.

AI AgentsCodex CLICompaction
0 likes · 30 min read
Codex's Context Management Redesign: Four-State Architecture for Long-Running Agents
Architect
Architect
Sep 4, 2026 · Artificial Intelligence

What Is a Harness? Why the Same Model Behaves Differently Across Coding Agents

The article explains why swapping the Harness — the runtime environment around an AI model — changes agent behavior even when the model weights stay identical, covering system prompts, tool definitions, agentic loops, translation layers, execution boundaries, feedback fidelity, context compression vs. immutable event logs, and architectural trade-offs illustrated by Pi, Codex, DSH, and the claudex experiment.

AI AgentsAgent RuntimeCoding Agents
0 likes · 19 min read
What Is a Harness? Why the Same Model Behaves Differently Across Coding Agents
Architect
Architect
Sep 2, 2026 · Artificial Intelligence

DeepSeek Harness: How 99% Cache Hits Validate Request Prefix Stability

This article analyzes how DeepSeek Harness achieves 99% prompt cache hit rates by enforcing deterministic request assembly, showing that cache hit rates serve as a diagnostic tool for runtime stability rather than just a cost metric.

Agent RuntimeCache Hit RateDeepSeek Harness
0 likes · 25 min read
DeepSeek Harness: How 99% Cache Hits Validate Request Prefix Stability
Architect
Architect
Aug 31, 2026 · Backend Development

How DeepSeek Harness Redesigns the Agent Runtime: Managing Capabilities, Clean Shutdowns, and Task Recovery

DeepSeek Harness (DSH) re‑architects the agent runtime by separating capability loading, clean exit handling, and task recovery into distinct boundaries, introducing Profile‑Preset configuration, a live Cordis runtime graph, a unified tool pipeline, session event logs, and dynamic Cordis for on‑the‑fly capability changes.

Agent RuntimeCordisDeepSeek Harness
0 likes · 27 min read
How DeepSeek Harness Redesigns the Agent Runtime: Managing Capabilities, Clean Shutdowns, and Task Recovery
Architect
Architect
Aug 30, 2026 · Artificial Intelligence

When Should an Agent Loop Stop? A Deep Dive into DSH vs Pi

The article dissects where an AI agent loop can pause—model stream end, tool batch return, turn completion, driver activity, and long‑term goal—by examining DeepSeek Harness and Pi implementations, their code structures, stop‑reason handling, logging, and practical trade‑offs in production scenarios.

AI architectureDeepSeek HarnessLoop Stopping
0 likes · 18 min read
When Should an Agent Loop Stop? A Deep Dive into DSH vs Pi
Architect
Architect
Aug 29, 2026 · Artificial Intelligence

Understanding the Difference Between /loop and /goal in Claude Code Agents

The article analyzes Claude Code’s /loop and /goal commands, explaining how /loop schedules recurring checks while /goal defines completion criteria, detailing their syntax, durability options, state management, failure handling, and practical use cases for automating SDK upgrades, PR creation, and CI monitoring, and discusses how agent architecture should evolve as models become more capable.

AgentClaude CodeGoal
0 likes · 17 min read
Understanding the Difference Between /loop and /goal in Claude Code Agents
Architect
Architect
Aug 27, 2026 · R&D Management

Anthropic’s AI‑Native SDLC: From Planning and Design to Secure Production

Anthropic’s AI‑Native SDLC Playbook shows how agents can accelerate coding but also expose new challenges in intent definition, specification, verification, release gating, production monitoring, and permission management, illustrated with a payment‑duplicate‑callback case and internal productivity data.

AI-Native SDLCAgentClaude
0 likes · 19 min read
Anthropic’s AI‑Native SDLC: From Planning and Design to Secure Production
Architect
Architect
Aug 23, 2026 · Artificial Intelligence

How Pi’s Rewritten Harness Verifies Long‑Running Agent Actions After 50 Hours

The article analyses Pi’s Harness v2 redesign, explaining how persistent transaction‑style recording, tool‑result pruning with spill, replay policies, and separated storage of conversation, runtime state, and usage enable an agent to survive process crashes and still prove which steps were completed.

AI AgentsPi Harnesscontext management
0 likes · 16 min read
How Pi’s Rewritten Harness Verifies Long‑Running Agent Actions After 50 Hours