Almost Timely News: How to Do Feature Engineering With AI  🔗 **Source:** [Almost Timely News: How to Do Feature Engineering With AI](https://www.christopherspenn.com/2026/07/almost-timely-news-%f0%9f%97%9e%ef%b8%8f-how-to-do-feature-engineering-with-ai-2026-07-12/) 📄 **Full text:** [[Full Document Contents/Articles/Almost Timely News How to Do Feature Engineering With AI.md|Almost Timely News: How to Do Feature Engineering With AI by Christopher S. Penn]] ## Highlights - * Year * Month * Day * Week of year * Day of year * Weekend or weekday * Day of week * Day of month * Week of month * Day of quarter * Week of quarter * Month of quarter * Quarter of year ([View Highlight](https://read.readwise.io/read/01kxb9p3pzhpsht8bxkp3c3z93)) - Note: A single datestamp decomposes into 13 derived features — the article's clearest concrete example. - Tags: atom/literature/h2 - One of the most important reasons you need to know feature engineering for surveys is because every question you ask someone in a survey reduces the completion rate. The more questions you ask, the less participation you get. Thus, if we want high completion rates AND good quality data, we have to think about what we can feature engineer from the data we have. Never ask questions for information you can extract on your own. ([View Highlight](https://read.readwise.io/read/01kxb9p2agjrqksmj0x66tkpnj)) - Note: Every survey question reduces completion rate — the case for inventory-first survey design. - Tags: atom/literature/h1 - I always recommend that people approach this in a three phase process – define the requirements in a requirements document (PRD, product requirements document in software engineering lingo) first. That’s the why. Next, you define the technical specifications of the software, the what. Finally, you define the workplan for implementing the software, the how. AI can build all that for you as long as you have rich, detailed explanations of what you want. ([View Highlight](https://read.readwise.io/read/01kxb9p7hkyzgxy9j30cswa5ha)) - Note: PRD → spec → workplan sequence before any code gets written. - Tags: atom/literature/h2 - This is the model you must use for all records in the datasets as it is private and local; we never use cloud models when handling PII/SPI/PHI (personally identifying information/sensitive protected information/protected health information). Feel free to use LiteLLM or similar libraries so you don’t have to reinvent the wheel here. You’ll process one row at a time; be sure to structure your prompts to maximize prompt caching and efficiency. ([View Highlight](https://read.readwise.io/read/01kxb9p5z93pv4v0z7xnxaz8fd)) - Note: PII/SPI/PHI must be routed to a local model, never a cloud API — enforcement not demonstrated, only asserted. - Tags: atom/literature/h1