talk-data.com talk-data.com

Event

November Meetup: When and How to Build an AI Agent + Faster data processing!

2025-11-20 – 2025-11-21 Meetup Visit website β†—

Activities tracked

2

πŸ’»Join PyData Boston for another deep dive into AI agents! This month, we'll have a talk from Pythonista Tri Dang on when and how to build an AI agent followed by a talk on how to make your data processing faster!

We currently have no food sponsor for this event! Reach out if you're able to sponsor!

RSVP is REQUIRED to attend Do not arrive before 6:30pm! πŸ“… Schedule: 6:30–7:00 β€” Networking 7:00–7:15 β€” Introduction 7:15–8:15 β€” Product Development: When and How to Build an AI Agent, with Tri Dang 8:15-8:30 - Break 8:30-9:15 β€” Optimize first, parallelize second: a better path to faster data processing with Itamar Turner-Trauring 9:15–9:30 β€” Wrap-up

Speaker: Tri Dang (Kyruus Health) Title: Product Development: When and How to Build an AI Agent Abstract: AI technologies are disrupting how we solve problems. For many companies including ours, we need to learn how to weave AI solutions into our problem space in a seamless way. This is the classic product development principle: first identifying a problem statement then using appropriate technologies to address the challenges. Without discipline, the AI hype often pushes us to do the opposite, forcefully embedding AI into a problem.

Speaker: Itamar Turner-Trauring (Pythonspeed) Title: Optimize first, parallelize second: a better path to faster data processing Abstract: You’re processing a large amount of data with Python, and your code is too slow. One obvious way to getting faster results is adding multithreading or multiprocessing, so you can use multiple CPU cores. Unfortunately, switching straight to parallelism is almost always premature, often unnecessary, and sometimes impossible.

πŸ“Venue provided by Moderna

This, and all NumFOCUS-affiliated events and spaces, both in-person and online, are governed by a Code of Conduct: πŸ‘‰ https://pydata.org/code-of-conduct/

⚑⚑**Speak at PyData!**⚑⚑ We are always looking for speakers! Sign up here and we'll be in touch: πŸ”— https://forms.gle/kfFZ5hiqA9W57Ewg7

⚑⚑**Sponsor an event!**⚑⚑ PyData events are free and open to all. We’re always looking for sponsors and hosts. Get in touch to support the community: πŸ“§ [email protected]

Sessions & talks

Showing 1–2 of 2 Β· Newest first

Search within this event →

Optimize first, parallelize second: a better path to faster data processing

2025-11-20
talk

You’re processing a large amount of data with Python, and your code is too slow. One obvious way to getting faster results is adding multithreading or multiprocessing, so you can use multiple CPU cores. Unfortunately, switching straight to parallelism is almost always premature, often unnecessary, and sometimes impossible.

Product Development: When and How to Build an AI Agent

2025-11-20
talk

AI technologies are disrupting how we solve problems. For many companies including ours, we need to learn how to weave AI solutions into our problem space in a seamless way. This is the classic product development principle: first identifying a problem statement then using appropriate technologies to address the challenges. Without discipline, the AI hype often pushes us to do the opposite, forcefully embedding AI into a problem.