The hottest new programming language is English," as Andrej Karpathy famously said. But does that hold true for writing end-to-end RAG applications with Qdrant? We will put it to the test.

We'll demonstrate how to build a complete Retrieval Augmented Generation (RAG) application by avoiding writing code ourselves at all costs.

We'll explore how far we can push AI systems to generate both frontend and backend code through natural language prompts and instructions, creating a fully functional RAG application powered by Qdrant's vector search capabilities.

We've evaluated different AI coding assistants, including Cursor, Aider, Claude Code, and GitHub Copilot. While Claude 3.5 and 3.7 have earned recognition for producing amazing frontend code, we'll assess its capabilities for full-stack development and discuss which frameworks deliver the most consistent and high-quality results.

Deutsche Telekom’s AI Competence Center (AICC) had a critical challenge: how do you efficiently and scalably deploy AI-powered assistants across a vast enterprise ecosystem?

The goal was to deploy GenAI for customer sales and service operations to resolve customer queries faster across the 10 countries where Deutsche Telekom operates in Europe.

In this Vector Space talk, Thierry from Qdrant and Arun from Deutsche Telekom talk about the key requirements for scaling enterprise AI agents, key AI stack considerations, and how the team built a Platform as a Service (PaaS) - LMOS (Language Models Operating System) — a multi-agent PaaS designed for high scalability and modular AI agent deployment.

Learn how Telekom's LMOS with Qdrant processes over 2 million conversations across three countries, and decreased the time required to develop a new agent from 15 days to just 2. These insights could be applicable to your enterprise use case!