Erik Davtyan - How to Engineer Better Prompts Using Data Science

Erik Davtyan, Senior Software Engineer at Not Diamond, presents a talk on
“How to Engineer Better Prompts Using Data Science.”

Large Language Models can deliver strong results - but making those results consistent is still a challenge. This talk explores how data science methods can turn prompt engineering from trial and error into a more systematic, measurable process.

In this session, Erik dives into:
🔹 Why prompt engineering benefits from data-driven evaluation
🔹 How measuring and testing prompts improves LLM reliability
🔹 Practical approaches to prompt optimization

This talk was recorded during the PyData Yerevan November 2025 Meetup, held on November 26, 2025, at the American University of Armenia.
--
www.pydata.org

PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.

PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases.

00:22 Welcome!

Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVi...