Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: ai-architecture
Why Not Every AI Task Deserves the Biggest Model: Resource-Aware Design
Why routing, specialist models and deterministic logic can beat sending everything to one large model, with research on cost and a fraud-detection case study.
11 min read16 RAG Architectures Compared: Which Pattern Fits Which Problem
A tour of sixteen RAG patterns in four tiers, from standard and hybrid retrieval to agentic, graph and federated designs, with a month-by-month build order.
14 min readRAG from First Principles: How Retrieval-Augmented Generation Actually Works
A first-principles tour of retrieval-augmented generation: why it exists, how it compares with fine-tuning, its evolution, offline and online pipelines, and failure modes.
33 min readAI Architecture Boundaries: Probabilistic Models in Deterministic Systems
An LLM changes system design: context becomes a component, output is untrusted, a 200 can still fail, and cost is a runtime limit. Keep rules and authority in code.
8 min readBuilding Effective AI Agents: Architecture Patterns and
Architecture patterns for AI agents: core components, interfaces, tools and memory, multi-agent systems, human in the loop review and observability in prod.
21 min readPractical notes: From Pattern to Pipeline: Implementing the Agentic Cortex with
Operable walkthrough of Practical notes: From Pattern to Pipeline: Implementing the Agentic Cortex with: contracts, checks, and drop-in code slots for teams shipping this pattern.
12 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.