<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[my_website]]></title><description><![CDATA[Ketaki Ghatole]]></description><link>https://98ketaki.wixsite.com/ketaki-ghatole/blog</link><generator>RSS for Node</generator><lastBuildDate>Wed, 24 Jun 2026 07:38:00 GMT</lastBuildDate><atom:link href="https://blog.ketaki-ghatole.com/blog-feed.xml" rel="self" type="application/rss+xml"/><item><title><![CDATA[The copy-paste era in biotech is coming to an end]]></title><description><![CDATA[AI applications in biotech are increasing drastically. Models can predict protein structures, summarize papers, generate hypotheses, and help researchers navigate vast amounts of scientific literature. The individual capabilities are no longer the bottleneck. What remains surprisingly difficult is the work between those capabilities. It is not uncommon to be in the middle of analyzing a promising compound and fall into a familiar ritual, open ChEMBL, export a CSV, switch to UniProt to find an...]]></description><link>https://blog.ketaki-ghatole.com/post/the-copy-paste-era-in-biotech-is-coming-to-an-end</link><guid isPermaLink="false">6a2245a9367ed35011d72e8a</guid><category><![CDATA[What’s New: Biology x AI]]></category><pubDate>Fri, 05 Jun 2026 03:52:04 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/bed21e_6103773dc8604135a2f072cc887966ce~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>ketaki ghatole</dc:creator></item><item><title><![CDATA[Why Pydantic Works Well for Scientific Data]]></title><description><![CDATA[If you’ve come across Pydantic recently, it was probably in the context of LLM agents. Pydantic didn’t suddenly become useful because of agents. It's been solving data validation problems in Python for years. It can efficiently solve data problems that I was hacking around for years with if-else loops as a bioinformatician. It's one of the most powerful tools for handling the messy, complex data that dominates our field.  At its core, Pydantic is a Python library for data validation. You...]]></description><link>https://blog.ketaki-ghatole.com/post/beyond-agents-why-pydantic-works-well-for-scientific-data</link><guid isPermaLink="false">697d8c93ccf6db790cb48659</guid><category><![CDATA[Back to Basics]]></category><pubDate>Sat, 31 Jan 2026 06:52:54 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/bed21e_ddbd496053df45f58fac98235123e202~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>ketaki ghatole</dc:creator></item><item><title><![CDATA[Build for Scientists, Not Around Them]]></title><description><![CDATA[I have watched scientists spend time fighting with a tool that was built to save time. But, finally, abandoning it and going back to Excel or something similar. And slowly, they stop using the tool. This happens more than you think. Most scientific tools don't fail because the tool was wrong or slow. They fail for a simpler, more painful reason, it was never built for how scientists actually think or work. I started my product journey, like many others, by reading Inspired by Marty Cagan. My...]]></description><link>https://blog.ketaki-ghatole.com/post/build-for-scientists-not-around-them</link><guid isPermaLink="false">697d651eccf6db790cb43e71</guid><category><![CDATA[Thinking in Products]]></category><pubDate>Sat, 31 Jan 2026 02:40:38 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/bed21e_c06c058e310f4c46a94c421050cee711~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>ketaki ghatole</dc:creator></item><item><title><![CDATA[How to Talk to AI? A Biologist's Prompting Guide]]></title><description><![CDATA[You’re several minutes into a back-and-forth with an LLM chatbot (ChatGPT, Claude etc.), trying to get a clear answer about interpreting some results. But, it keeps circling back to the same generic explanation. The AI seems confused and continues to apologize and you're frustrated! I've been there. We've all been there. These tools don't work like Google. When you type a question into Google, it finds all relevant existing information. It retrieves information and you can choose what you are...]]></description><link>https://blog.ketaki-ghatole.com/post/how-to-talk-to-ai-a-biologist-s-prompting-guide</link><guid isPermaLink="false">691999f90dbc57ddd09c5b6a</guid><category><![CDATA[What’s New: Biology x AI]]></category><pubDate>Mon, 17 Nov 2025 01:13:12 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/bed21e_6f4b3750aba54bbb8c1d4ac7592fc565~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>ketaki ghatole</dc:creator></item></channel></rss>