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.
This article explains how OpenClaw controls the side‑effects of AI‑driven tool calls by splitting them into three guardrails—sandbox, tool policy, and elevated—plus a dynamic exec‑approval step, detailing configuration keys, practical troubleshooting tips, and a minimal baseline setup for secure deployment.
The article explains how OpenClaw tackles common multi‑agent messaging problems by treating sessionKey as a partition key, redefining DM scope for multi‑source inputs, employing a dual‑layer queue with per‑session serialization and global lane throttling, and exposing configurable knobs for micro‑batching, backpressure, and observability.
Boris Tane, former founder of Baselime and Cloudflare Workers observability lead, shares a disciplined eight‑step workflow that lets architects harness Claude Code while preventing costly system‑breaking AI‑generated code, by making every AI contribution explicit, reviewed, and anchored to documented architectural decisions.
The article explains how OpenClaw’s control plane guarantees reliable, idempotent, and observable agent execution by enforcing a two‑phase protocol, strict handshake, role‑based authorization, layered deduplication, gap‑recovery mechanisms, and schema‑driven validation, turning a simple message flow into a production‑grade job system.
OpenClaw treats agents as infrastructure by introducing explicit queues, session boundaries, tool permissions, and persistence layers, ensuring that multi‑channel AI assistants run predictably without chaotic side effects, and the article walks through its architecture, concurrency model, session management, context handling, tool sandboxing, and fail‑over strategies.
This article explains how the Agent Loop—an engineered while‑loop that repeatedly calls an LLM, decides when to use tools, executes them, and feeds results back—creates persistence, style, memory, judgment, and safety boundaries that together make an AI agent feel like it has its own personality.
This article distills a viral thread by Eyad Khrais into six actionable principles and a reusable workflow for Claude Code, covering planning mode, project‑specific CLAUDE.md files, context management, interface‑style requirements, handling stuck conversations, and automating high‑frequency actions into a sustainable engineering system.
This article breaks down Anthropic’s 33‑page guide on building Claude Skills, explaining the two‑layer MCP/Skill architecture, progressive disclosure design, file‑naming rules, reusable patterns, testing methods, and distribution options for creating stable, reusable AI workflows.
The article analyzes why autonomous LLM agents become expensive, breaks down their cost components, and presents concrete engineering strategies—memory management, tool‑call optimization, and planning constraints—to dramatically reduce token usage and improve reliability while maintaining performance.
WebMCP is a new browser‑native API that lets webpages expose structured tools for AI agents to call directly, solving the fragility of UI‑based automation by moving interaction from the presentation layer to a semantic, contract‑driven layer.
