How to (not) fail a GenAI project: practical lessons and technical insights from building and evolving Multi-Agent Chatbots in production
2025-05-27 , Sala 7

Why do even successful GenAI projects often plateau after reaching production?

Moving from PoC to a live system is only the beginning — the real challenge lies in scaling it, making it trustworthy, and continuously improving its impact. Whether you’re navigating your first demo or already running a GenAI solution in production, this talk is for you.

Here I’ll share hard-earned lessons from building production-grade multi-agent chatbots (e.g. “talk-with-your-documents”) in a corporate environment — lessons grounded in hands-on experience, packed with practical tips and references to GenAI tools and frameworks that actually work.

We’ll cover:
- why involving business stakeholders early and often is not just a nice-to-have, but a critical success factor — and how to do it.
- how to build robust evaluation pipelines using real user data and expert input to assess relevance, accuracy, and overall system performance over time.
- how to strike the right balance between elegant simplicity and complex agents architectures, with a focus on composable patterns and advanced strategies for RAG (chunking, pre-retrieval, post-retrieval, and more).
- the main challenges of unstructured data — and how smart preprocessing can be helpful in compensating for poor document quality.
- post-deployment strategies: onboarding users, increasing trust through transparency (think interactive source tracing and agent flow visualization), and iterating based on real-world queries and feedback.

This is a new, original talk for AI Heroes, aimed at developers, AI engineers, and product teams building GenAI solutions. Get ready for a session filled with hands-on advice and real-world lessons learned from taking GenAI projects to production across a variety of contexts and scenarios.

Expected length: 40 minutes

Benedetto is a Computer Engineer with a strong background in software development and a deep focus on Artificial Intelligence.

He holds a Master’s degree in Computer Engineering with a specialization in Data Science & AI from Politecnico di Torino, where he developed a solid foundation in machine learning, data processing, and intelligent systems.

He currently works as an AI Engineer at Datapizza, where he helps companies unlock the value of Generative AI by designing and building production-ready solutions, collaborating with an exceptional team of talented engineers and AI experts to bring ideas from prototype to production.

Over the past year, he has led the development of multi-agent chatbots in enterprise environments, combining LLMs, advanced RAG strategies and powerful evaluation pipelines to deliver real-world impact.