Tagged “Engineering”

• RAG vs Long Context: Which Approach Fits Your AI App?

  Compare retrieval-augmented generation with simply pasting documents into a long context window: cost, accuracy, freshness, citations and when each one fits.

  Oct 12, 20261 min readAIEngineeringEvaluation

• AI Code Review: What It Catches, Misses and How to Use It

  Where AI-assisted code review helps (edge cases, tests, consistency) and where humans must decide (design, security, product intent). A practical team workflow.

  Oct 5, 20261 min readAICoding agentsEngineering

• Structured Output From LLMs: Reliable JSON Without Surprises

  How to get dependable JSON from language models: define a schema, validate every response, retry with the error, keep prompts small and handle missing fields.

  Sep 28, 20261 min readAIEngineeringPrompting

• AI API Costs: How Tokens Work and How to Spend Less

  Understand token-based AI pricing, why long conversations cost more than they seem, and how to cut spend with caching, smaller models and tighter context.

  Sep 17, 20262 min readAICostEngineering

• Shipping an AI Feature to Production: Pre-Launch Checklist

  A pre-launch checklist for AI features: narrow scope, evaluation, fallbacks, privacy, monitoring and honest user communication. Go from demo to production.

  Sep 10, 20262 min readAIEngineeringProduct