Sign in Subscribe

Topic

AI Engineering

A collection of 20 issues

Evals: The Single Highest-Leverage Discipline in AI Engineering

Part 4 of the AI Engineer Series. Evals are the single highest-leverage discipline in AI engineering. Deterministic assertions, LLM-as-judge with calibration, pairwise versus pointwise scoring, and the discipline that separates teams who ship from teams who hope.

Structured Outputs and Fallback Chains: How to Stop LLMs From Breaking Your Parser

Part 3 of the AI Engineer Series. Structured outputs are how you stop the model from breaking your downstream code. JSON mode, tool calling, constrained decoding, and the fallback chain pattern that holds when models misbehave.

Context Engineering: Why Retrieval Quality Decides Almost Everything About Your RAG System

Part 2 of the AI Engineer Series. Naive RAG pipelines fail at retrieval roughly 40% of the time. Chunking, hybrid search, reranking, and query rewriting determine quality more than any prompt change.

Harness Engineering: The Code Around Your LLM Calls That Keeps Production Alive

Part 1 of the AI Engineer Series. Prompt engineering gets the spotlight, but in production, most reliability comes from the system around the prompt. This is the harness layer, and most teams underbuild it.

The Complete AI Engineer Roadmap: A 13-Week Plan to Go From Curious to Production-Ready

A structured, week-by-week learning plan covering everything from harness engineering and RAG to inference internals, fine-tuning, and production guardrails — with real code, real libraries, and real tradeoffs.

The Production Reality — Governance, Security, and ROI for RAG Systems in 2026

Part 5 of the RAG Series: The unglamorous work that keeps RAG alive in production. EU AI Act obligations, RBAC at the retrieval layer, provenance tracking, and an ROI framework that makes the business case concrete.

Agentic RAG — From Passive Retrieval to Active Reasoning with LangGraph

Part 4 of the RAG Series: The jump from passive retrieval to active reasoning. Build LangGraph agents that decompose questions, iterate over retrieval loops, use SQL tools and MCP servers, and hand off between specialised agents.

Architectures of Choice — Adaptive, Corrective, and Modular RAG with LangGraph

Part 3 of the RAG Series: Stop building RAG systems that do the same thing for every query. Adaptive RAG, Corrective RAG, and Modular RAG — built with LangGraph state machines — give you systems that route, self-correct, and stay composable.

The Retrieval Multiverse — Vectors, Graphs, and Why Hybrid Is the Only Way to Go

Part 2 of the RAG Series: Production RAG in 2026 is never vector-only. Learn why hybrid search, GraphRAG, and late chunking each solve problems that pure vector search cannot — with LangChain and LangGraph code throughout.

Why 80% of RAG Demos Die in Production (And How to Fix It at the Source)

Part 1 of the RAG Series: Why 80% of RAG prototypes fail in production — and how shifting your mindset from "vector search + prompt" to a Knowledge Runtime fixes it at the source.