A deep dive into how Prosus is deploying over 30,000 AI agents to create an 'AI Agentic Workforce'. The talk covers the transition from simple assistants to trusted senior colleagues, the internal tooling developed, and the crucial organizational strategies used to overcome adoption barriers and foster a bottom-up culture of innovation.
A discussion on the evolution of AI agent interaction, moving beyond simple text-based chat to create intuitive, GUI-driven experiences. The talk covers the practical challenges and solutions in building an impactful agent for busy professionals, focusing on quick actions, efficient data streaming, and enhanced interactivity.
Simba Khadder of Redis introduces Context Engineering 2.0, a new paradigm for AI agents that unifies structured data, unstructured data (RAG), and memory into a single, schema-driven surface. He critiques current methods like Text-to-SQL and direct API wrapping, proposing a unified context engine to provide reliable, observable, and performant data access for agents.
Jiquan Ngiam, CEO of MintMCP, discusses the paradigm shift from static programs to dynamic AI agents, outlining the significant security risks involved—supply chain vulnerabilities, third-party data poisoning, and inadvertent agent behaviors—and presents a three-pronged strategy for enterprise readiness: comprehensive monitoring, preventative guardrails, and secure, role-based deployment of Model Context Protocols (MCPs).
This talk introduces Discrete CKKS, a framework that extends the approximate FHE scheme CKKS to support exact integer arithmetic. It achieves this through a hybrid bootstrapping technique that both cleans noise and raises the modulus, enabling a high-throughput, vectorized engine for general-purpose discrete computations on encrypted data.
Poetiq, a startup by former DeepMind researchers, has developed a recursive self-improvement meta-system that builds "reasoning harnesses" on top of existing LLMs. This approach avoids the costly "fine-tuning trap" and has achieved state-of-the-art results on benchmarks like ARC-AGI and Humanity's Last Exam by automatically optimizing prompts and discovering novel reasoning strategies.