Agentic workflows in production

Join us for an evening focused on how AI agents are moving from experiments to real production work!

Agenda:

18:00 Gathering, food & drinks

18:30 Sherlock: monday.com’s tickets investigator - The story of an agentic workflow, from POC to production

19:00 First AId Kit

Talk Abstracts:

Sherlock: monday.com’s tickets investigator - The story of an agentic workflow, from POC to production
What does an agent that actually works on real production tickets look like? In this talk, I’ll share the story behind Sherlock, a supervisor agent that started as a personal initiative, born from identifying a recurring pattern in ticket investigations: data collection, analysis, synthesis, and drawing conclusions. We’ll walk through the journey from a POC built during an internal hackathon, through designing an agentic workflow based on LangChain and LangGraph, writing prompts that embody a way of thinking and an understanding of the product and business context, and integrating with organizational analytics and observability systems. We’ll also cover the real challenges of moving to production: splitting agents by responsibility, context limits, guardrails, human-in-the-loop, architectural changes, and measuring impact.

First AId Kit
What if we could move a big chunk of bug fixing and solving production issues to agentic AI? That would be so cool. In this talk we will go through the end to end process of setting up a background agentic workflow that detects production errors, finds their root causes, assesses the right solution and opens a PR - so you wake up in the morning to tasks almost fully completed for you by your loyal agent.

Together We will go over the entire process - the infra challenges, the agentic accuracy issues, and the final result used nowadays in real, massive production environments.

Production issues still slow teams down. Finding the root cause is noisy, fixing it is manual, and the cycle continues. But how do you break that loop? In this session, you’ll see how you can wire production context into an AI agent that not only detects failing endpoints, but also traces the root cause, proposes a fix, and opens a pull request automatically.

Bios

Kamie Shami-Schnitzer - Senior Full Stack Developer
Kamie is an engineering team lead at monday.com with 5+ years of experience as a software developer, with a degree both in Computer science and Biology from Tel-Aviv university. Kamie is passionate about bringing real impact into products, integrating AI both in workflows and in the product itself. In he spare time, Kamie can be found traveling around the world with her family, reading or listening to some good music

Inbal Levy - Forward Deployed Engineer, Hud
Inbal Levy is a Forward Deployed Engineer and one of the earliest engineers at Hud. Leveraging a decade of cyber and defense experience, she helps organizations adopt AI by designing agentic workflows enriched with real-time production context. Her work empowers engineering teams to operate more efficiently, move with greater confidence, and resolve production issues faster than ever.