The engineering discipline around AI features: prompt and context design, retrieval pipelines, streaming interfaces, evaluation harnesses, cost and latency budgets, failure handling, and the architecture decisions that separate a demo from a production system.
3 articles2 contributors6 topics
RAG solves a knowledge problem; agents solve an action problem. Where each architecture belongs, how they combine, and why their failure modes barely overlap.
When a change can be drafted by a process that runs your tests, the constraint moves from writing code to reviewing it. What that shift breaks and rewards.
The layers between a working AI demo and a system people depend on: call boundaries, budgets, tenant isolation, evaluation, observability, degradation.
Sections that sit closest to AI Development in the Tech Agents taxonomy.
AI Development currently holds three pieces: one explainer, one tutorial and one comparison. It is written by M. Oyelaran and A. Rahman.
Subjects that recur across the section include Evaluation, AI Agents, Architecture and Python. The earliest piece was published on January 21, 2026 and the most recent on June 24, 2026.
Coverage here is filed against ai development, ai engineering, building with llms and rag. The sections sitting closest to it in the Tech Agents taxonomy are AI Agents, Artificial Intelligence and AI Tools, which is where neighbouring material is published.
Topics in this section