Aaron Birnbaum and Matthew Makansi

A two-agent architecture for enhanced reasoning Our work addresses this challenge with a novel approach based on the interplay of two LLM-driven agents, which has similarities to how human clinicians tackle management problems. The Dialogue Agent is user-facing and equipped to rapidly respond based on its current understanding of the patient. This agent handles the conversational aspects of the interaction, gathering information about the patient’s condition, addressing their concerns, and building rapport. By leveraging natural

Introduction If you’ve ever analyzed data using built-in t-test functions, such as those in R or SciPy, here’s a question for you: have you ever adjusted the default setting for the alternative hypothesis? If your answer is no—or if you’re not even sure what this means—then this blog post is for you! The alternative hypothesis parameter, commonly referred to as “one-tailed” versus “two-tailed” in statistics, defines the expected direction of the difference between control and

Introduction Let’s talk about Kubernetes probes and why they matter in your deployments. When managing production-facing containerized applications, even small optimizations can have enormous benefits. Aiming to reduce deployment times, making your applications better react to scaling events, and managing the running pods healthiness requires fine-tuning your container lifecycle management. This is exactly why proper configuration — and implementation — of Kubernetes probes is vital for any critical deployment. They assist your cluster to make

Introduction Many generative AI use cases still revolve around Retrieval Augmented Generation (RAG), yet consistently fall short of user expectations. Despite the growing body of research on RAG improvements and even adding Agents into the process, many solutions still fail to return exhaustive results, miss information that is critical but infrequently mentioned in the documents, require multiple search iterations, and generally struggle to reconcile key themes across multiple documents. To top it all off, many

ChatGPT launched in 2022 and kicked off the Generative Ai boom. In the two years since, academics, technologists, and armchair experts have written libraries worth of articles on the technical underpinnings of generative AI and about the potential capabilities of both current and future generative AI models. Surprisingly little has been written about how we interact with these tools—the human-AI interface. The point where we interact with AI models is at least as important as

“Conduct a comprehensive literature review on the state-of-the-art in Machine Learning and energy consumption. […]” With this prompt, I tested the new Deep Research function, which has been integrated into the OpenAI o3 reasoning model since the end of February — and conducted a state-of-the-art literature review within 6 minutes. This function goes beyond a normal web search (for example, with ChatGPT 4o): The research query is broken down & structured, the Internet is searched for information,

There are some Sql patterns that, once you know them, you start seeing them everywhere. The solutions to the puzzles that I will show you today are actually very simple SQL queries, but understanding the concept behind them will surely unlock new solutions to the queries you write on a day-to-day basis. These challenges are all based on real-world scenarios, as over the past few months I made a point of writing down every puzzle-like

I have been a data team manager for six months, and my team has grown from three to five. I wrote about my initial manager experiences back in November. In this article, I want to talk about something that is more essential to the relationship between a DS or DA individual contributor (IC) and their manager — the 1:1 meetings. I remember when I first started my career, I felt nervous and awkward in my

Advancements in agentic artificial intelligence (AI) promise to bring significant opportunities to individuals and businesses in all sectors. However, as AI agents become more autonomous, they may use scheming behavior or break rules to achieve their functional goals. This can lead to the machine manipulating its external communications and actions in ways that are not always aligned with our expectations or principles. For example, technical papers in late 2024 reported that today’s reasoning models demonstrate

Acknowledgements The authors would like to thank Dzmitry Huba, Hubert Eichner, Kallista Bonawitz, Mark Simborg, Peter Kairouz, Prem Eruvbetine, Sarah de Haas for their extensive feedback and editing on the blog post itself, and the teams at Google that helped with algorithm design, infrastructure implementation, and production maintenance. In particular, we would like to thank the collaborators who directly contributed to this effort: Adria Gascon, Albert Cheu, Allie Culp, Andri Saar, Artem Lagzdin, Brendan McMahan,