LLM fundamentals for product teams

What actually happens when you build AI into a product: tokens, context windows, temperature and sampling settings, model APIs, and why the same prompt costs different amounts across models. Written for the PM or founder who needs the mental model without a PhD.

Newsletter28 APR 2026

The death of the prompt box: what A16Z's 2026 prediction means for your AI features

What A16Z's 2026 Prediction Means for Your AI Features.

Madalina Turlea

Article15 JAN 2026

Your AI always returns an answer. That's why you can't trust it.

AI features never throw errors — they just quietly get things wrong. Here's how product managers catch silent failures before users lose trust.

Madalina Turlea

Article15 JAN 2026

Using AI at scale is not the same as using ChatGPT

Using AI in a chat box is solving one problem. Building AI into a product is solving one problem many times — with the same instructions, for inputs you do not control.

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

AI always returns something, and that is the problem

AI never fails completely — it just returns plausible answers, sometimes wrong. Why ship-and-hope traps teams, and what real iteration on a prompt actually looks like.

Madalina Turlea

Article15 JAN 2026

Markdown, XML, or JSON: how to format a prompt so the model understands it

The format you put your prompt in changes accuracy more than you would expect. When to use Markdown, when to reach for XML tags, and when JSON is the right tool.

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

Temperature, max tokens, and streaming: the LLM settings that quietly change your output

The API parameters you send with every prompt change how the model behaves. What temperature, max tokens, top-P, reasoning settings, and streaming actually do — and when they matter.

Madalina Turlea

Article15 JAN 2026

Why ChatGPT gets dumber the longer you talk to it

Long chats degrade for a concrete reason: the context window. The model is not remembering — it is being re-sent the whole conversation every turn, and there is a hard limit.

Madalina Turlea

Article15 JAN 2026

Does the AI know what day it is? Cutoff dates, web search, and why models differ

Models do not know the current date and stop knowing the world at their cutoff. What the cutoff is, why web search is expensive, and the three dimensions that actually make models different.

Madalina Turlea

Article02 JAN 2026

Prompt Engineering Techniques: Part 1

Three foundational techniques that improve any AI interaction: writing specific instructions, providing context, and specifying the output format you actually want.

Maria-Fontica Marinescu

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

Masterclass28 NOV 2025

Demystify popular AI features with us - part 1

Breaking down how popular AI features work under the hood.

Catalina Turlea

← Back to all resources