Extend and Improve: The Design You Already Have Is the Job
New code is cheap to draft. The lasting move is older: add to a design someone still understands, or tidy that design until the next change is easy.
18 min read
← All topics
Architecture
A topic hub collecting every article tagged Architecture. Use it to explore related posts and follow this theme across the site.
29 articles
Explore More Topics
What Is an AI-Native App? A Working Definition, Architecture, and Practical Test
AI-native apps are not ChatGPT wrappers. They are systems where model inference, retrieval, memory, orchestration, tools, and evaluation are core infrastructure. Here is a working definition, the reference architecture, and a test you can apply to your own product.
21 min read
Modern Algorithms Every Programmer Should Know: From Matching Markets to HNSW and ARC
A deep systems engineering guide to the essential algorithms behind modern infrastructure — matching markets, rolling hashes, network flows, cache replacement, probabilistic sketches, and vector search.
42 min read
How to Build the Fastest, Lightest Autonomous Agent Platform with Kubernetes, ArgoCD, Ante, and Frontier LLMs
A systems architecture guide for building a high-throughput, low-memory autonomous agent platform in 2026: combining Ante's 15MB Rust micro-kernel, Kubernetes KEDA scaling, ArgoCD GitOps, and dynamic speed-quality Pareto routing across Gemini 3.7 Flash, GPT-5.6 Sol, and Claude Opus 5.
25 min read
Forward Deployed Engineers: Who Owns the Last Mile of AI?
Forward Deployed Engineers turn AI capabilities into production outcomes. Learn what FDEs own, when the model works, where it breaks, and how to evaluate the role.
21 min read
Building Google Translate: Before LLMs and With Modern AI
How Google Translate evolved from rules and statistical phrase models to neural MT and today’s Translation LLM — and how to build a translation app in 2026 with the right mix of NMT, multilingual models, and LLMs.
19 min read
Hermes Agent AI Agents RAG Agent Harness Architecture Nous Research OpenClaw Agno CrewAI n8n AI Engineering
Hermes Agent: Is It the Ideal RAG App? Architecture Lessons for Engineers
A source-backed review of Nous Research's Hermes Agent — what it is, how its memory and retrieval layers work, why it is not a classic RAG app, and which architecture decisions are worth borrowing.
31 min read
Graph RAG Apps: A Production Deep Dive and Recommended Stack
How to design a production Graph RAG app with graph construction, hybrid retrieval, durable hand-offs, evaluation gates, and a practical recommended stack for engineers and PMs.
22 min read
How to Make App Data Public and Production-Ready with MCP and RAG
A practical guide for engineers and PMs who want to expose public app data safely through MCP and RAG — with allowlists, caching, cost controls, and a production checklist.
17 min read
Horizontal Agents vs Vertical Agents: Designing Loop Engineering
A practical guide for engineers and PMs on when to build general-purpose horizontal agents, when to invest in domain-specific vertical agents, and how loop engineering differs for each—including hybrid architectures that route across both.
21 min read
Winning Ambiguous Problems: How to Explore Alternatives, Capture Unknowns, and Still Decide
A practical playbook for engineers and PMs facing messy problems with many possible answers, hidden risks, and no obvious best path.
16 min read
Migrating an Existing App to Heimdall + OpenFGA, One Route at a Time
Part 2: a strangler-fig adoption path for moving a live app to a Zero-Trust gateway and OpenFGA, starting with a single route in shadow mode and expanding without a big-bang rewrite.
15 min read
The Zero-Trust Auth Stack Architects Nod At: Heimdall + OpenFGA
How the gateway forwardAuth to external authorizer to internal JWT to thin services pattern works, built with Heimdall as the PEP and OpenFGA as the Zanzibar-style PDP.
19 min read
Architecture Governance for AI Code Generation
A practical guide for engineers and PMs who want AI coding agents to move fast without breaking architecture decisions, module boundaries, ownership, and long-term system quality.
20 min read
Autonomous Workflows in Practice: n8n, CrewAI, Cloudflare Agents, LangGraph, and Agno
A source-audited guide to modern autonomous workflows: when to use n8n, CrewAI, Cloudflare Agents, LangGraph, or Agno, where teams stumble, and why this is practical now.
24 min read
Recommendation Engines for AI Agent Apps: From Zero to Production Ready
A source-backed deep dive for engineers and PMs on building recommendation engines inside AI-agent products, from MVP heuristics to retrieval, ranking, evaluation, safety, observability, and production launch.
22 min read
The Pieces of Modern, Effective Software Design
A practical ladder for growing a software system from one app and one database into observable, event-driven, permission-aware, AI-ready architecture.
18 min read
OpenFGA for Granular Permissions in Modern Apps, MCP, and Agent Workflows
A practical guide to using OpenFGA for fine-grained authorization in SaaS apps, MCP servers, workflow agents, and agent orchestrators.
32 min read
What `ghcr.io` Is, and How to Use It with Helm and Argo CD for a FastAPI App
A practical, source-backed guide to GitHub Container Registry, OCI Helm charts, Argo CD, and a clean local/dev/prod flow for a simple FastAPI service.
27 min read
Agno/AgentOS + FastAPI vs LangChain/LangGraph + FastAPI
A source-audited, side-by-side guide to choosing between Agno/AgentOS + FastAPI and LangChain/LangGraph + FastAPI for production Python agent backends.
26 min read
Astro Cloudflare D1 Cloudflare Containers Agno AgentOS Architecture Blog Platform AI Agents Cloudflare Workers
How to Build a Modern Blog App with Astro, Cloudflare D1, and Cloudflare Containers for Agno Agents
A practical guide for engineers and architects designing an Astro blog platform with draft/publish workflows in D1, a lightweight markdown editor, and a Cloudflare Containers deployment for an Agno/AgentOS research service.
26 min read
12-Factor Agents in Practice: LangChain/LangGraph and Agno/AgentOS
A source-audited translation of HumanLayer's 12-factor agent principles into practical LangGraph and Agno/AgentOS architecture, with production-minded Python examples.
24 min read
Docker Compose vs Kubernetes in Production: The Claim Is Too Absolute
An evidence-driven look at the claim that Docker Compose is only for local development while production should always use Kubernetes, Helm, and Argo CD.
24 min read
Designing Subagents in the Cloud: Agno vs LangChain vs AI SDK
A practical, source-audited guide to designing subagents for real cloud workloads, with concrete patterns and tradeoffs across Agno, LangChain, and Vercel AI SDK.
14 min read
How to Stream LangChain and LangGraph into AI SDK
A source-audited, practical guide to building streaming APIs with LangChain and LangGraph, then consuming them cleanly with AI SDK from simple chat to durable agents.
19 min read
Docker GitHub Actions Helm ArgoCD Kubernetes DevOps CI/CD EKS External Secrets Hardening Architecture
From Repo to Cluster: An End-to-End Deployment Pipeline for AI SaaS
A practical service-level deployment guide for AI SaaS teams: Docker image design, GitHub Actions builds, Helm packaging, ArgoCD handoff, External Secrets, IRSA, and release hardening.
12 min read
Stateful vs Stateless Agents in Production: AI SDK, LangChain, and Agno/AgentOS
A source-audited, architecture-first guide to deciding where agent state should live in production, with code examples in Vercel AI SDK, LangChain, and Agno/AgentOS.
16 min read
Less Code, Less Hallucination: Why AI Co-Generation Demands Simpler Frontends
When an AI agent spins up tasks on a complex frontend, complexity becomes the enemy. The hypothesis: simpler codebases mean fewer bugs — and in the age of AI co-generation, fewer hallucinations too.
12 min read
Production GitOps: Terraform, Helm, and ArgoCD for Node.js APIs and Agno Agents
A deep-dive into provisioning infrastructure with Terraform, packaging apps with Helm, and continuously deploying via ArgoCD — with real config for a Node.js API and an Agno Python agent. Structured across five expertise levels from Basic to Legendary.
29 min read