Other
Our Research
Recent Publications
Preview abstract
This post delves into the shift within enterprise AI, moving from traditional Large Language Models (LLMs) to advanced, goal-oriented AI Agents and sophisticated Multi-Agent Systems (MAS). While individual agents, such as the "Data Agent" in Looker Conversational Analytics, excel at querying specific, governed datasets, they often fall short when addressing complex business challenges that span diverse, isolated systems across departments like Sales, Marketing, and Operations. To overcome these "data silos," we introduce and detail the architecture of a Multi-Agent System. This system, built on the Gemini Enterprise platform and utilizing the Agent Development Kit (ADK), features a Master Agent that coordinates various specialized Sub-Agents (including Data, Jira, and Salesforce agents). This coordination enables the system to independently break down intricate queries, gather validated information from disparate sources, and generate a cohesive, data-driven insight. This innovative architectural approach significantly boosts employee efficiency and effectiveness by automating the laborious process of data integration, thereby empowering users with a unified and intelligent platform. These AI Agents are designed to reason, plan, utilize tools, and autonomously complete complex, multi-step business tasks, with or without human involvement. Organizations globally are prioritizing the integration of AI Agents to enhance the efficiency and effectiveness of their workforce.
View details
On the Benefits of Traffic “Reprofiling” The Multiple Hops Case – Part I
Henry Sariowan
Jiaming Qiu
Jiayi Song
Roch Guerin
IEEE/ACM Transactions on Networking (2024)
Preview abstract
Abstract—This paper considers networks where user traffic is regulated through deterministic traffic profiles, e.g. token buckets, and requirescleanguaranteed hard delay bounds. The network’s goal is to minimize the resources it needs to meet those cleanrequirementsbounds. The paper explores how reprofiling, i.e. proactively modifying how user traffic enters the network, can be of benefit. Reprofiling produces “smoother” flows but introduces an up-front access delay that forces tighter network delays. The paper explores this trade-off and demonstrates that, unlike what holds in the single-hop case, reprofiling can be of benefit even when “optimal”cleansophisticated schedulers are available at each hop.
View details
Google’s Aqsa Fulara: 5 Things You Need To Create A Successful Career As A Product Manager
Aqsa Fulara
Rachel Kline
Authority Magazine (2024)
Preview abstract
A product manager’s specific role varies from one company to the next. Still, all product managers balance many aspects of their job, including customers’ needs, a vision for new products, and the project team. So what tools and strategies are needed to create a successful career as a product manager? What are the “5 Things You Need To Create A Successful Career As A Product Manager”? Authority Magazine speaks with Aqsa Fulara, a product manager at Google to answer these questions with stories and insights from her experiences.
View details
Storage Systems For Real-Time Personalized Recommendations
Jayasekhar Konduru
Aqsa Fulara
DZone (2024)
Preview abstract
This article explores the demands of real-time personalized recommendation systems, focusing on data storage challenges and solutions. We'll present common storage solutions suitable for such systems and outline best practices.
View details
Optimizing quantum gates towards the scale of logical qubits
Alexandre Bourassa
Andrew Dunsworth
Will Livingston
Vlad Sivak
Trond Andersen
Yaxing Zhang
Desmond Chik
Jimmy Chen
Charles Neill
Alejo Grajales Dau
Anthony Megrant
Alexander Korotkov
Vadim Smelyanskiy
Yu Chen
Nature Communications, 15 (2024), pp. 2442
Preview abstract
A foundational assumption of quantum error correction theory is that quantum gates can be scaled to large processors without exceeding the error-threshold for fault tolerance. Two major challenges that could become fundamental roadblocks are manufacturing high-performance quantum hardware and engineering a control system that can reach its performance limits. The control challenge of scaling quantum gates from small to large processors without degrading performance often maps to non-convex, high-constraint, and time-dynamic control optimization over an exponentially expanding configuration space. Here we report on a control optimization strategy that can scalably overcome the complexity of such problems. We demonstrate it by choreographing the frequency trajectories of 68 frequency-tunable superconducting qubits to execute single- and two-qubit gates while mitigating computational errors. When combined with a comprehensive model of physical errors across our processor, the strategy suppresses physical error rates by ~3.7× compared with the case of no optimization. Furthermore, it is projected to achieve a similar performance advantage on a distance-23 surface code logical qubit with 1057 physical qubits. Our control optimization strategy solves a generic scaling challenge in a way that can be adapted to a variety of quantum operations, algorithms, and computing architectures.
View details
Swinging the Engineer/Manager Pendulum
T3chFest, Madrid (2023)
Preview abstract
Both coding and people need continuous, intense and conscious focus and attention. Being manager teaches you the business, being IC teaches you the possibilities of the tech. Being at the intersection makes you invaluable.
When you move to one side, your skills on the other begin to deteriorate, what to do? If you move to manage, are you going to be a forever manager? What is management in tech anyway? Can go back to write code?
This talk will show what is the process to onramp and offramp and what are the pitfalls on the way.
View details
×
![]()