Prompt engineering for product teams

Prompting written for teams that ship, not for demos. How to structure prompts you'll still be maintaining in six months, how to evaluate prompt changes against a real dataset, and how to keep prompt iterations from silently breaking the features you already have working.

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

Article14 APR 2026

Should you still write PRDs when building AI features?

The programming language is plain English. The prompt IS the spec, so why is the PM three handoffs away? Why "evals are the new PRDs" makes things worse, and what PM-owned AI development actually looks like.

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

We tested the viral prompt tricks. Most of them do nothing.

Threatening the model, all caps, high-stakes framing — we ran the viral prompt techniques across nine models on real extraction tasks. Structure and clarity beat hacks every time.

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

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

Building an expense-policy AI agent: what we learned reverse-engineering Ramp

Three prompts, six models, 126 runs. What we learned trying to reverse-engineer Ramp's expense-policy AI agent — including why a more detailed prompt actually made GPT-5 worse.

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

Article15 JAN 2026

Infinite personalization without the AI slop

AI lets you personalize content infinitely — and slip into generic slop just as easily. The two failure modes to watch for, and why feeding the model your real data is the difference between insight and filler.

Madalina Turlea

Article09 JAN 2026

Prompt Engineering Techniques: Part 4

From craft to system: how to test prompts rigorously, compare approaches on real data, and build repeatable processes for prompts running inside a product or workflow.

Maria-Fontica Marinescu

Article07 JAN 2026

Prompt Engineering Techniques: Part 3

Validation-side techniques for verifying AI outputs before you act on them: role prompting for perspective-shifting, self-consistency checks, and critical analysis prompts.

Maria-Fontica Marinescu

Article06 JAN 2026

Prompt Engineering Techniques: Part 2

Two intermediate techniques that raise output quality on harder tasks: few-shot learning with worked examples, and chain-of-thought reasoning for multi-step problems.

Maria-Fontica Marinescu

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

Masterclass04 DEC 2025

Myth busters edition - prompting techniques

Let's test out some popular beliefs about prompting AI.

Catalina Turlea

Article15 OCT 2025

3 mistakes PMs make when they let engineers own the AI prompt

Engineers build infrastructure. Domain experts build quality. Here are three costly mistakes that happen when PMs hand prompt ownership to engineering.

Madalina Turlea

Article15 OCT 2025

The 3 prompt testing mistakes most teams don't know they're making

Most teams test prompts wrong without realizing it. Here are three specific mistakes that silently kill AI feature quality — and how to fix each one.

Madalina Turlea

← Back to all resources