Extending AI agents and Durable Python at Golden Gate University

Want to learn more about Python and meet other Pythonistas?

Please register here: https://ti.to/sfpython/nov-12th-sf-python-ggu?source=meetup

Please support our sponsors Golden Gate University!

👉 Submit your 5, 15 or 25 mins talk proposals here: https://bit.ly/bapyacfp

SCHEDULED TALKS

🔎 Extending AI agents: Custom tools and Model Context Protocol - Elizabeth Fuentes Leone
As AI agents become increasingly prevalent in production systems, you face a critical challenge: extending these agents beyond their base capabilities to interact with proprietary systems, custom APIs, and domain-specific tools.
In this session, you'll build a fully functional AI agent using Strands Agents, an open-source framework, with minimal code. You'll learn how to enhance your agent's capabilities by integrating three types of tools: native framework tools, custom implementations, and Model Context Protocol (MCP) servers
Eli is a Data Analytics and ML/AI Developer Advocate at AWS who delivers technical content in English and Spanish. She specializes in generative AI, RAG systems, and developer tooling.

🔎 Durable Python - Itay Donanhirsh
Don’t you hate it when a pipeline fails in the middle and you need to restart it at 4am? In this talk will present the concept of workflows built using Durable-Python. It ensures reliable execution, even in the case of infrastructure failures, without requiring any code changes.
Why is that important? Over time, things will fail in production. Restarting a failing workflow composed of many components without doing redundant, expensive tasks is hard. This applies to DevOps, Data/AI pipelines, and other long-running tasks.
However, developing reliable and long-running workflows is complicated.
To address this, in this talk, we will present an open-source project that provides a “serverless” platform for durable Python execution. It ensures that Python code executed in the system is resilient to infrastructure failures and will automatically recover from the point it stopped without state or data loss. This allows developers to focus on the business logic rather than error handling and dealing with infrastructure faults.
We’ll brave a live demo implementing a long-running workflow, and explain how it works and the value it brings for building durable workflow automations.
Itay Donanhirsh is the co-founder and CTO of Autokitteh. Before that, he worked for Checkr, Lyft, Twitter, Google, and others. His experience with CI systems and developers' interactions with them inspired the creation of AutoKitteh, which is the subject of this talk.

AGENDA
6:30p Reconnect with friends!
7:00p Opening remarks, sponsors acknowledgement
7:10p Scheduled talks and Q&A + networking break
8:30p Wrap up last talk, more networking

THIS EVENT IS PRODUCED BY
SF Python, a volunteers-run organization aiming to foster the Python Community in the Bay Area