Discussion on agentic LLM adoption in production, focusing on LangChain and LlamaIndex tooling, production readiness, tools, evaluation and observability, safety and guardrails.

Computer vision is becoming a key enabler of smart manufacturing, from quality inspection to robotic automation. Yet traditional development of AI models often requires large datasets, specialized expertise, and significant time. In this talk, we explore how no-code computer vision platforms are changing this landscape allowing engineers, operators, and domain experts to build, train, and deploy models without deep AI backgrounds. We’ll look at real examples from manufacturing and robotics to show how faster iteration, simpler data workflows, and scalable deployment can move automation projects from concept to production.

Deploy AI agents to production on Google Cloud Platform; theory and live coding.

In this talk, I will share our journey, which began with local applications leveraging Open-Source LLMs and has now evolved to serve our internal teams. I will dive into the practical lessons we've learned along the way, offering insights that can help you navigate the complexities of LLM implementation.