16/09, 15:30–15:50 (Asia/Jerusalem), אולם 7
Language: English
A Python unit-test framework - for making sure that Agents do as they're expected.
LLM Agents are powerful constructs - capable of asking questions, using tools, reasoning iteratively while fixing their mistakes or assumptions.
When creating such agents for a specific purpose, we want to make sure that purpose is achieved. However, because these beings exist in a conversational, non-deterministic environment, doing proper unit tests becomes tricky.
In this talk I will present a method, as well as a Python framework, for tackling this problem.
Intermediate
Target audience –Developers
Adam Kariv is a software engineer (and founder) of While True Industries, an open data consultant and activist.
He has over 25 years of experience in developing, designing and managing software projects, from open-source data-wrangling libraries to enterprise-scale, mission-critical systems developed by over 20 engineers. He is the founder of the Public Knowledge Workshop (‘Hasadna’), an Israeli NGO working to make government data more accessible, and has extensive experience working with civil society organization and government agencies to build better tools for publishing data.