PyData London - 105rd Meetup

Venue: Riverbank House, 2 Swan Ln, London EC4R 3AD
Please note:
1. 🚨🚨🚨 A valid photo ID is required by building security. 🚨🚨🚨
2. This event follows the NumFOCUS Code of Conduct. Please familiarise yourself with it before attending.

If your RSVP status says "You're going" you will be able to get in. No need to show your RSVP confirmation when signing in.
If you can no longer make it, please unRSVP as soon as possible.

Code of Conduct:
This event follows the NumFOCUS Code of Conduct. Please get in touch with the organisers with any questions or concerns.

As always, there will be free food and drinks, generously provided by our host, Man Group.

Main Talks

1. Agentic Workflows for Data Engineers: How AI Agents Are Changing Our Daily Work - Yusuf Ganiyu
   Last month, I debugged a critical pipeline failure in 4 minutes that used to take 30. The difference? An AI agent that understands my data infrastructure.
   This isn't about replacing data engineers, it's about eliminating the toil that keeps us from high-value work. In this talk, I'll share practical experiments with agentic workflows from my work at AstraZeneca and teaching 20,000+ students at DataMasteryLab.
   We'll explore:

• What agentic workflows actually are (beyond the hype)
• Live demo: AI-assisted pipeline debugging with LangGraph
• Practical patterns: Schema evolution, data quality monitoring, self-healing pipelines
• The feature engineering bridge: Helping data scientists love you
• What AI still can't do (and why that matters)

Whether you're skeptical about AI hype or already experimenting, you'll leave with concrete patterns you can implement in your pipelines next week.
2. TBC

Lightning Talks

1. Github Codespaces for Data Analysis with Python - Stelios Christodoulou
2. TBC
   --------------------------------
   Logistics
   Doors open at 6.30 pm (get there early as you'll need to sign in with building security).
   Talks start at 7:00 pm, with drinks afterwards from 9:00 pm at The Banker (EC4).

We have reduced capacity for this event, but there will be plenty of people to discuss data science questions with.
Please unRSVP in good time if you realise you can't make it. We're limited by building security on the number of attendees, so please free up your place for your fellow community members.
If you want me to trim lightning talks down to two or shorten any abstracts, say which ones.