HoneyBook Engineering

As AI engineering moves from experiments to production, the challenge is no longer just “using an LLM” - it’s architecting real systems around agents, context, and control. In this meetup, we’ll explore how companies build reliable multi-agent flows, refactor early hacks into scalable architectures, and get AI coding agents to produce real, shippable work. We’re bringing together experts from HoneyBook, DoorLoop, and Unity to share how they design agent architectures, evolve prototypes into robust systems, and turn coding agents into productive teammates.

Join us for an evening where AI engineering gets practical, hands-on, and deeply real.

—----

Agenda:
17:30 - 18:30 - Food, drinks and mingling
18:30 - Onboarding Zen: Orchestrating Multi-Agent Flows into One Whole Experience - Idan Doron, Senior Full Stack Engineer at HoneyBook
19:00 - Refactoring the Agent: From Hardcoded Logic to Unified LangGraph & MCPs - Maor Oz, Technical Lead at DoorLoop
19:30 - AI Coding Agents: From Vibes to Production - Nir Jacob, Senior Full Stack Engineer at Unity
20:00 - More drinks and mingling!

The talks will be delivered in Hebrew.

—----

// Onboarding Zen: Orchestrating Multi-Agent Flows into One Whole Experience - Idan Doron, Senior Full Stack Engineer at HoneyBook
Forcing an LLM to behave the way you intend is a never-ending challenge, and we faced this challenge in our onboarding experience.
At HoneyBook, our onboarding experience uses multiple AI agents - contracts, invoices, pipeline, and an onboarding specialist - each tied to a unique UI mode. That worked well until we realized real users don’t stick to a single intent, and they move from one context to another while staying with the same agent and the same UI experience.
In this talk, we’ll explore how we built a multi-agent orchestrator that keeps onboarding seamless and context-aware. We’ll share how we designed intent routing, used “think tools” that guide reasoning without extra LLM calls, created safe fallback paths, and balanced model decisions with deterministic logic.

About the speaker:
Idan is a Senior Full Stack Engineer at HoneyBook, driving AI initiatives from product development to company-wide task forces. One of the first to introduce AI at HoneyBook, she now focuses on agentic AI engineering. In her free time, you can find her doing functional training or baking (though not at the same time).
LinkedIn

// Refactoring the Agent: From Hardcoded Logic to Unified LangGraph & MCPs - Maor Oz, Technical Lead at DoorLoop
How do you evolve from a fragile, hardcoded script into a scalable agent architecture? At DoorLoop, we began with almost no AI context, stitching together limited workflows without tools. It quickly became clear that this approach could not scale.
In this session, we will explore the real engineering journey of building an AI platform, tracing the evolution from early RAG experiments to fully stateful, production-grade agents. We’ll cover the steep learning curve of adopting LangChain, the early limitations of tool-less and prompt-only workflows, and the pivotal shift to the ReAct paradigm.
Finally, we’ll look ahead to the future of agent scalability, focusing on how the Model Context Protocol (MCP) enables clean, standardized connections between agents and internal tools, unlocking a more modular, extensible, and maintainable AI architecture.

About the speaker:
Maor Oz is an AI Technical Lead at DoorLoop. Over the past two years, Maor was a Technical Lead focused on strengthening the company’s infrastructure and developer experience. Six months ago, he transitioned into an AI Technical Lead role, where he now leads DoorLoop’s initiative to introduce and scale multiple AI agents across the company. In his free time, you can find Maor playing various instruments, creating music and playing video games.
LinkedIn

// AI Coding Agents: From Vibes to Production - Nir Jacob, Senior Full Stack Engineer at Unity
If you’ve ever found yourself in a never-ending debate with an AI where “You Are Absolutely Right!” you know the unique frustration of working with LLMs that sound certain but act chaotic.
This talk digs into what’s really happening under the hood when AI tries to help you write code and why things so often go sideways. We’ll walk through real cases where good prompts went bad, bad context ballooned into messy diffs, and where the AI’s confidence outpaced its correctness.
More importantly, we’ll explore practical methods to fix this with advanced context-engineering techniques, task delegation across specialized sub-agents, and patterns that dramatically reduce hallucinations and missteps. You’ll learn how to structure conversations, break down problems, and guide coding agents so they become dependable collaborators instead of unpredictable debaters.
This session will show you how to turn your AI slop into vibes and finally get AI to help you write better code, faster.

About the speaker:
Nir Jacob is a Senior Full Stack Engineer at Unity. He has spent the past year leading the adoption of AI-powered coding tools across R&D. With deep experience in building high-quality software and a curiosity-driven mindset, he loves exploring emerging technologies, experimenting with new developer tools, and pushing the boundaries of what’s possible. Outside of work, you’ll often find him tinkering with the latest AI assistants or testing whatever new tech lands on his desk.
LinkedIn

—----

See you soon!