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.
The article analyzes Pi's agent harness architecture, showing how its core loop stays minimal by handling only model-tool-result cycles while pushing session management, MCP integration, Codemode orchestration, and security boundaries to the edges, enabling extensibility without complicating the main execution path.
This article argues that AI agents often mistake model output or tool calls for task completion, but real business completion requires verifiable read-back evidence, idempotency handling for timeouts, explicit acceptance criteria, and structured completion records — not just a 'final_output' signal.
This article analyzes why multi-agent handoffs often break on the second user message, comparing how OpenAI Agents SDK, LangChain, and Microsoft Agent Framework persist the current owner, transfer context, and maintain routing state across conversation turns.
This article analyzes the harness layer of 11 coding agents—including Claude Code and Codex—based on an 83-page arXiv paper, revealing how runtime systems manage tools, context, permissions, and verification beyond the model itself.
This article explains how hierarchical multi-agent architecture solves the single-supervisor bottleneck by delegating control to intermediate layers that manage local closed loops, using structured task packages downward and decision packages upward, with concrete examples from model evaluation and analysis of trade-offs like constraint dilution and retry multiplication.
This article deconstructs AI agent architecture as a stateful runtime chain—Goal→Plan→Context→Decide→Act→Observe→Verify→State→Next—distinguishing Planner, Tool, MCP, Memory, and Reflection as interconnected layers rather than parallel modules, emphasizing that reliability comes from the harness runtime handling verification, recovery, and context engineering outside the model.
This guide walks through building a Claude Code Mod from scratch using the Token Weather example, explaining the plugin structure, event hooks, state management, UI rendering, and the three hook patterns (observe, rewrite, answer), while comparing Claude Code's host-centric runtime control plane with DeepSeek Harness's plugin-first architecture.
Using a subscription billing error as a case study, this article analyzes how to systematically improve AI agents through permission separation, task-specific skill management, reproducible error tracking, rigorous evaluation design, controlled hillclimbing optimization, and deployment validation — drawing on four Claude.dev engineering articles.
The article analyzes four community-driven patterns for using Jev — semantic filtering, action selection, control-plane routing, and evidence gating — each narrowing open-ended LLM generation into a constrained judgment, with concrete examples, benchmarks, and production readiness checks.
This article compares Pi and DeepSeek Harness agent loop architectures across four control points—input attribution, tool scheduling, closure permissions, and persistent evidence—revealing how each handles mid-task user constraints, parallel tool execution, token truncation, and crash recovery through distinct runtime contracts and durable extensions.
