Optimise AI costs

How to spend less on inference without regressing the feature. Model selection with quality evidence, when a smaller model actually holds up, routing between cheap and expensive models, and how to make a cost-quality tradeoff you can defend to the person who signs the AWS bill.

Newsletter10 SEPT 2026

The AI cost trap

"Build first, optimize later" works for SaaS — and quietly bankrupts AI products. Why your most engaged users are the ones losing you the most money, and the pre-ship experimentation loop that stops you from locking in a 10x-too-expensive architecture.

Madalina Turlea

Article10 JUN 2026

How to measure AI feature ROI (when half of teams can't)

Half of product teams name unclear ROI as their #1 AI challenge, and a third track no AI metrics at all. Here's a measurable framework for the return on a single AI feature.

Madalina Turlea

Article22 MAY 2026

What document extraction actually costs across 15 models

Two numbers that shouldn't coexist: an 11× cost gap between models on the same extraction task, and a 43-point accuracy gap on the same model driven by prompt structure alone. Cost is not a proxy for accuracy.

Madalina Turlea

Article15 JAN 2026

The model selection blind spot: why the newest model is not always the best

Teams default to the newest model before checking whether it fits the task. Frontier models do not win every time — and accuracy, cost, and latency rarely peak in the same place.

Madalina Turlea

Article15 JAN 2026

Tokens, explained: what you are actually paying for when you build with LLMs

Tokens are the thing you pay for and the only number you can rely on. What a token actually is, why the same prompt costs different amounts across models, and the hidden reasoning tokens.

Madalina Turlea

Article15 JAN 2026

Start with the prompt, not RAG: giving an AI feature access to your knowledge

The instinct is to reach for RAG. The advice that works is the opposite: start by stuffing the important knowledge into the prompt, and only add complexity when the volume actually demands it.

Madalina Turlea

Masterclass19 DEC 2025

Reverse-engineering AI products: from system prompts to cost

Let's look at some of the most popular AI products and their estimated AI cost.

Catalina Turlea

Article15 OCT 2025

3 model selection mistakes that are quietly burning your AI budget

Most teams pick their AI model on reputation, not data. Here are three model selection mistakes silently inflating your costs — and how to fix them.

Madalina Turlea

← Back to all resources