Building in Public: AI and the Art of Prompt Engineering
· Meaningful Blog
Building in Public: AI and the Art of Prompt Engineering
Google is famous not only for holding 90% of the internet search market, but also for heavily investing in R&D ($55.6 billion in 2025 alone, a 15.12% increase compared to the previous year). In short: to stay relevant, you must always invest in yourself and others.
Being one of the leading voices in AI, Google regularly releases tons of documentation, courses, and videos, including the "Prompt Engineering" series, now in v7.
The Key Insight
From Google's introduction:
"When thinking about a large language model input and output, a text prompt is the input the model uses to predict a specific output. You don't need to be a data scientist or a machine learning engineer — everyone can write a prompt. However, crafting the most effective prompt can be complicated. Many aspects of your prompt affect its efficacy: the model you use, the model's training data, the model configurations, your word-choice, style and tone, structure, and context all matter. Therefore, prompt engineering is an iterative process. Inadequate prompts can lead to ambiguous, inaccurate responses, and can hinder the model's ability to provide meaningful output."
The Moral
Quality data in, quality data out — from AI to personal relations.
Naturally, we also use AI and from our experience, Gemini is great but Windsurf 🏄 with Opus 4.5 is another ballgame! This is how we manage to iterate so fast with a minuscule small team — 99 commits in 2 months.