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-engineering
A six-month roadmap from beginner to working AI engineer
Follow a month-by-month plan covering Python, LLM APIs, RAG, agents, evaluation, deployment and cost, with four portfolio projects that show you can ship AI systems.
10 min readAn AI Engineering Roadmap for 2026: From Python to Agents and LLMOps
A phased 2026 learning path for AI engineering, from Python and math through classical ML and deep learning to RAG, MCP, agents, evals and deployment.
14 min readAgent Harness Engineering: State, Verification and Control Around the Model
A runtime view of production agents: why prompts and context aren't enough, and how durable state, enforcement, verification and observability close the gap.
13 min readLoops vs. Graphs: Two Ways to Architect AI Agents
Loop engineering vs graph engineering for AI agents: how each architecture works, when to pick one over the other, and a checklist to use before production.
12 min readFrom Evals to Self-Improving Agents: Five Eras of Agent Evaluation
Agent evaluation now means auditing traces. See how deterministic checks, LLM and agent judges, diagnosis and a meta-harness build a safe improvement loop.
7 min readBeyond the API Wrapper: A Middleware Layer for Production LLM Integration
Direct LLM API calls break under real traffic. A middleware layer adds model abstraction, fallback routing, event-driven agents and cost-aware model choice.
6 min readGoverned AI Agents: One Policy Model, Several Runtime Enforcement Points
How to control cost, model choice, data, tools and MCP calls at runtime: a governance envelope, a neutral policy sketch, fallbacks, guardrail limits and tracing.
9 min readAGENTS.md or CLAUDE.md? What 592 Top Repositories Actually Contain
A survey of 592 top GitHub repositories shows CLAUDE.md is mostly a pointer to AGENTS.md, and that hooks, the enforcement layer, are far rarer than the docs.
7 min readPrompting, RAG or Fine-Tuning: Diagnose the Layer Before Choosing
A practical way to choose between prompting, RAG and fine-tuning in 2026, using three questions, a decision flow, cost shapes, freshness and common mistakes.
9 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.