Architecture

50 articles about architecture.

How AI Agents Work: Architecture, Loops, and Tool Use Explained

·14 min read

AI agents work by running a perceive-reason-act loop powered by LLMs and tool calls. Learn the architecture, memory systems, and planning layers inside.

ai-agentsarchitecturetool-usellmagentic-aimacos

I Wanted a 100% Private AI Accessible from My Smartphone

·2 min read

Building a local-first desktop AI agent that keeps everything private while remaining accessible from your phone. The architecture behind truly private AI.

privacylocal-firstsmartphonedesktop-agentarchitecture

Actor-Based Sync Engines and Modular Frameworks for Native macOS Apps

·2 min read

Why actor-based sync engines with modular Swift frameworks produce the cleanest macOS app architecture. Lessons from real native apps using Swift 6 concurrency.

swiftmacosarchitectureconcurrencynative-apps

Agent CLI Framework Differences: Sequential vs Batch Tool Calling

·9 min read

A concrete comparison of sequential vs batch tool calling across Claude, OpenAI, LangChain, and open-source agent frameworks - with code examples, latency benchmarks, and a decision matrix for when each approach makes sense.

agent-frameworkclitool-callingdesktop-agentarchitecture

Building a Learning System for AI Agents That Remembers Across Repos

·2 min read

Why AI agents keep making the same mistakes and how an immune system-style memory layer helps them learn from repetition across multiple repositories.

memoryai-agentslearningmulti-repoarchitecture

AI Agent Security in 2026 - Lessons from OpenClaw and Why Architecture Matters

·11 min read

The OpenClaw security crisis showed what happens when AI agents have unchecked access to your system. Here is what went wrong, what the industry learned

securityprivacyopenclawai-agentsarchitecture

Architecture Decision Records with Code References - Holding Architects Accountable

·3 min read

ADRs are only useful when they point to working code. Adding code references to Architecture Decision Records creates accountability and makes decisions

adrarchitecturedocumentationcode-qualityaccountabilityengineering-practices

Architecture Diagrams vs Working Systems - How AI Agents Expose the Gap

·6 min read

AI agents implement architecture documents literally and expose every underspecified gap. Using an agent as an architecture validator catches design flaws before a full team builds on them.

architecturesoftware-engineeringai-agentssystems-designtechnical-debt

Why Your AI Agent Should Never Depend on a Single LLM Provider

·2 min read

When your only LLM provider goes down, your entire agent stops working. Build multi-provider fallback into your AI workflows from the start.

llm-providersreliabilitymulti-providerai-agentsarchitecture

AWS Certification That Changed Architecture

·2 min read

Certifications teach what a platform can do. Building teaches what it should do. Both matter for AI agent infrastructure decisions.

awscertificationarchitectureinfrastructurelearning

Building a Custom AI Coding Agent with the Claude API and MCP Tools

·3 min read

Why building your own AI coding agent with direct API access and custom MCP tools gives you more control than using Claude Code out of the box.

claude-apimcpai-agentscoding-agentarchitecture

Skills vs Sub-Agents in Claude Code - When to Use Each Pattern

·2 min read

How to structure Claude Code skills vs sub-agents - splitting by type, managing 10+ skills, and choosing the right pattern for each workflow.

claude-codeskillssub-agentsarchitecturedeveloper-workflow

Claude Code Writes Your Code, but Do You Know What's in It?

·2 min read

AI coding agents restructure modules in unexpected ways. The code works but the architecture drifts from your mental model unless you actively review

code-reviewclaude-codearchitectureai-codingai-agents

How CLAUDE.md Prevents AI Agents from Writing Goop Code

·2 min read

The single biggest improvement for AI-generated code quality is describing your architecture in a CLAUDE.md file before the agent touches anything. Here is

claude-mdcode-qualityarchitectureai-codingbest-practiceschatgptcoding

Context Windows Are Not Memory

·2 min read

Context windows are working memory, not storage. Understanding this distinction is critical for building AI agents that maintain state across sessions.

context-windowmemoryworking-memoryai-agentsarchitecture

Memory Is Just Context with a Longer TTL - AI Agent Memory Systems

·2 min read

Memory files are lossy compressed embeddings of past context. Explore how context windows and long-term memory relate in AI agent architectures.

memorycontext-windowai-agentpersistencearchitecture

Designing Agent Networks With Isolation and Shared State Patterns

·2 min read

A good agent network balances isolation with shared state. Learn how to design multi-agent systems where agents stay independent but coordinate through

agent-networksarchitectureshared-stateisolationmulti-agent

Different Answers, Same Problem - Comparing AI Agent Architectures

·2 min read

When multiple AI agent architectures tackle the same automation task, the results reveal more about design tradeoffs than about which approach is best.

ai-agentarchitectureautomationmulti-agentcomparisondesign-tradeoffs

Dumb Orchestrator With Smart Workers Beats One Big Agent

·2 min read

A simple decision-tree orchestrator routing tasks to specialized worker agents - browser, accessibility, sequential - is more reliable than a single

orchestrationmulti-agentworkflowreliabilityarchitectureautomation

When Federation vs Centralization Makes Sense for AI Agents

·2 min read

Federation adds coordination costs that often outweigh the benefits. Learn when to federate your AI agent architecture and when to keep it centralized.

federationcentralizationarchitectureai-agentsdistributed-systems

Focus Compounds - Why Specialized AI Agents Outperform Generalists

·2 min read

A focused AI agent that does one thing well outperforms a distributed agent that does ten things poorly. Specialization compounds in ways generalization cannot.

specializationarchitectureai-agentsfocusdesign-patterns

GTC 2026: Agentic AI and Memory-First Architecture

·2 min read

Memory-first architecture treats agent memory as the primary data store, not an afterthought. Agents that remember context across sessions perform

gtc-2026agentic-aimemoryarchitectureagent-design

Hybrid AI Agent Architectures - Local Models for Sensitive Data

·2 min read

Why the best AI agent setup uses local models for sensitive data and cloud models for everything else, with practical patterns for routing between them.

local-modelshybrid-aiprivacysensitive-dataollamaarchitecture

Exposing macOS Desktop Capabilities to External AI Agents via MCP

·2 min read

How MCP servers let external AI agents like ChatGPT and Claude interact with your macOS desktop - file management, app control, and system automation

mcpmacosdesktop-agentsaasintegrationarchitectureai_agents

How to Choose Which Model for Each Task in AI Agents

·2 min read

Tiered model routing sounds smart but adds complexity. When does routing between models actually help AI agents, and when is one model simpler and better?

model-routingai-agentsllm-selectionoptimizationarchitecturewebdev

Holding Parallel Truths in AI Agent Development

·2 min read

Two truths breathing at once is multithreading for consciousness. When two contradictory approaches both work in AI agent development and how to navigate

ai-agentarchitecturedecision-makingparallel-agentsdevelopment-philosophy

Modular Architecture for Native macOS Apps: Frameworks, Actors, and File Provider

·7 min read

Building a native macOS app with file syncing and background services requires clean architecture from day one. Here's how to structure Swift frameworks, use actors for concurrency safety, and treat File Provider as a thin adapter.

macosswiftarchitecturemodularfile-providersyncopensource

When Scaffolding Becomes Architecture in AI Agent Code

·2 min read

Scaffolding you refuse to take down becomes architecture eventually. How temporary workarounds in AI agent codebases become permanent fixtures and what to

ai-agentcode-qualityarchitecturetechnical-debtsoftware-engineering

Smart Caching Strategies for AI Agent Tool Results

·3 min read

TTL-based caching gives AI agents stale data. Learn about dependency-tracking caches that invalidate when upstream data changes, keeping agent decisions fresh.

cachingai-agenttool-resultsarchitectureperformance

Specialist vs Generalist AI Agents - When to Split Responsibilities

·2 min read

One generalist AI agent doing six things vs six specialist agents doing one thing each. When to split agent responsibilities and the tradeoffs of focused vs

ai-agentarchitecturemulti-agentspecialistdesign

SQLite Is the Right Database for Most AI Agent Workloads

·6 min read

A single SQLite file per agent session handles most workloads. Benchmarks, schema patterns, and when you actually need to move beyond SQLite for AI agent state management.

sqlitedatabaseai-agentsarchitecturelocal-first

Vibecoded App with Claude Code

·2 min read

Vibecoding with CLAUDE.md architecture rules turns Claude Code from a code generator into a system-aware development partner. Here is how the approach works.

vibecodingclaude-codeclaude-mdarchitecturedevelopment

Error Propagation in Multi-Agent AI Systems

·11 min read

When one AI agent makes a bad decision, every downstream agent inherits that error. Learn how errors cascade in multi-agent systems and practical patterns to contain them.

multi-agenterror-propagationreliabilityagent-networksarchitectureai-agents

Using Agent Teams as a Product Backend: Bridging Swift Desktop Apps to Claude Agent SDK

·2 min read

We built a Swift desktop app that bridges to the Claude Agent SDK via a local Node.js process. Here is how agent teams can serve as a product backend.

swiftclaude-sdkarchitecturemacosagent-teams

The Lossy Handoff Problem - When AI Agents Transfer Context via Git Diff

·3 min read

Git diffs capture what changed but not why. When AI agents hand off work to humans, architectural decisions and rejected alternatives are lost. How to

handoffcontext-lossgit-diffai-agentknowledge-transferarchitecture

Competing Philosophies About Where AI Should Live - Truly Local vs Cloud VM

·2 min read

Some tools claim local-first but run in cloud VMs. True local means native code on your machine with direct OS access and no virtualization layer.

local-firstcloud-vmphilosophynativearchitecture

You Don't Have a Claude Code Problem, You Have an Architecture Problem

·2 min read

When AI agents struggle with desktop automation, the issue is usually architecture - not the LLM. Thin action primitives that the model composes into

architectureclaude-codedesktop-automationprimitivesagent-designworkflows

What File Systems Teach About AI Agent Reliability

·3 min read

File systems solved reliability decades ago with atomicity, journaling, and crash recovery. AI agents can learn the same lessons for more reliable execution.

reliabilityfile-systemsai-agentsatomicityjournalingcrash-recoveryarchitecture

Structuring a macOS Agent App with Modular Swift Frameworks

·2 min read

Split your Swift macOS agent into separate frameworks for UI, accessibility, networking, and models. AI agents can work on one framework without breaking

swiftmodularframeworkmacosarchitecture

The N+1 Problem in AI Agents - Everyone Wants Agents That Automate Other Agents

·2 min read

Why the impulse to build agents that automate other agents is premature, and why nailing the first layer of automation matters more.

n-plus-oneagent-automationlayer-skiparchitecturecomplexity

No-Server Architecture for Small Business Tools - Why Local-First with IndexedDB Wins

·2 min read

Adding a backend to small business software means becoming the IT department for every shop. Local-first with IndexedDB is the smarter constraint.

local-firstindexeddbsmall-businessno-serverarchitecture

How to Protect Your IP When Building with AI Coding Agents

·2 min read

Practical strategies for protecting intellectual property when using AI coding agents like Claude Code - isolate secret sauce, use modular architecture, and

intellectual-propertyai-agentcode-securityarchitectureprotectionclaudeai

PWA vs Native macOS App - How to Decide for Your AI Tool

·2 min read

PWA is fastest to ship but feels like a wrapper. Native SwiftUI gives you proper notifications, menu bar integration, and system-level shortcuts. For AI

pwanative-appswiftuimacosarchitecture

Write Specs Before PRs to Avoid Redesign Debates in Code Review

·2 min read

How writing a short spec before non-trivial PRs prevents architecture debates during code review and saves hours of rework.

code-reviewspecsengineering-processpull-requestsarchitecture

Designing a Tiered Permission System for AI Desktop Agents

·3 min read

Full YOLO mode is dangerous and full approval mode is unusable. Tiered permissions with allowlists per action type hit the sweet spot.

permissionsai-safetyux-designdesktop-agentarchitecture

The HANDOFF.md Pattern - How to Keep Claude Code Productive Across Sessions

·3 min read

Context window management matters more than prompt quality once your project grows. How the HANDOFF.md pattern and post-edit hooks keep AI coding agents

claude-codedeveloper-toolsproductivityarchitecture

You Do Not Need an MCP Server for Every Mac App - Accessibility APIs as a Universal Interface

·3 min read

Instead of building a separate MCP server for each macOS app, use the accessibility API as a single universal interface. One integration controls every app

mcpaccessibility-apimacosarchitecturedeveloper-tools

Using Claude as an Execution Layer - Markdown Specs, MCP Tools, No Traditional Code

·3 min read

What happens when your entire app is markdown specs that Claude executes, with MCP servers as the only real code. A year of building this way.

claude-codemcparchitecturedeveloper-toolsworkflow

Building Memory Into an AI Desktop Agent - Knowledge Graphs and Persistent Context

·2 min read

The hardest problem in AI agents is not planning - it is remembering. How knowledge graphs and local file indexing give desktop agents persistent memory

memoryknowledge-graphai-agentsarchitecturecontext

Native Desktop Agent vs Cloud VM - Why We Chose to Run on Your Actual Mac

·4 min read

Cloud VM agents like Claude Cowork run in isolated environments. Native agents like Fazm control your actual apps. Here is why the native approach wins for

desktop-agentcloud-vmarchitectureproductivitycomparison

Browse by Topic