AI development hits everyone, so hit us. Everybody wants AI agents to replace regular UIs. In this talk, I will describe the evolution of our multitool AI agent, built with Node.js on top of Google Vertex AI. I’ll dive into our journey of choosing the right models and scaling development through CI/CD, TDD, and performance monitoring. Is it even possible to achieve stable results for AI projects that can hallucinate and return various responses? Interestingly, we eventually decided to remove MCP servers and Zod schema validation—technologies often considered the "standard" for these tasks. Want to know why we moved away from them? Join my session to get these insights and ask your questions live!

We will analyze what actually works in the field of autonomous LLM agents, the existing limitations and their causes, research directions aimed at extending the duration of fully autonomous task execution, explore potential architectures of fully autonomous systems, economic autonomy of agents, and where we currently stand on the path toward achieving it.

In this topic, we will go through the step by step guide how to build an AI application using PHP and large language models. We will understand how your bot can respond like ChatGPT and manage your private data without training or extensive expertise in Data Science. We will also review existing libraries and how these approaches can be utilized in your applications.

In this talk, I'll give a quick introduction to LLM and how to use it in a PHP application. I'll show some examples using the LLPhant project including a retrieval-augmented generation (RAG) system using a local LLM (Llama 3) and Elasticsearch as a vector database.