Large language models can now power capable software agents, yet real‑world success comes from disciplined engineering rather than flashy frameworks. Most reliable agents are built from simple, composable patterns instead of heavy abstractions.
The talk will introduce patterns to add complexity and autonomy only when it pays off. Attendees should leave with a practical decision framework for escalating from a single prompt to multi‑step agents, also keeping in mind guardrails for shipping trustworthy, cost‑effective agents at scale.
Sushant Mehta
Research Engineer
Google Deepmind
Cadence
Website: https://www.cadence.com/en_US/home.html
Cadence’s goal is to empower engineers at semiconductor and systems companies to create innovative, intelligent, and highly differentiated electronic products that transform the way people live, work, and play. The company’s Intelligent System Design strategy helps customers develop differentiated products—from chips to boards to systems—in AI, IoT, mobile, 5G, consumer, cloud, data center, automotive, aerospace, and other market segments. Cadence offers specialized IP with industry-leading performance, power efficiency, and interconnects, as well as AI-specific verification and implementation solutions. The company also employs machine learning within its tools and solutions to enable the best power, performance, and area (PPA), quality of results (QoR), and time-to-market (TTM) benefits.
Flexnode
Website: https://flexnode.io/
Flexnode designs, builds, and operates high density, rapidly-deployed, scalable modular data centers purpose-built for today and tomorrow’s most complex IT projects. Supporting 150kW+ racks, Flexnode’s data centers are AI-ready, specifically designed for today’s leading chipsets (i.e., NVIDIA GB200/B300, AMD MI355X) and future developments. Flexnode works closely with our clients to configure modular solutions to meet their exact needs. In addition, Flexnode works closely with all major hardware, cooling, and networking providers, giving its clients optionality while also ensuring solutions are precisely configured to optimize their IT initiatives. Flexnode’s modular design enables deployments from 1MW to 300MW+, reduces design-build time and construction material waste, while delivering industry-leading rack densities, PUE and resiliency. With densities increasing significantly, Flexnode’s modular design is a fast, reliable, and cost-effective way to deploy both today and tomorrow’s chipsets without sacrificing capex, power, space, or operability. In collaboration with best-in-class data center design, engineering, and construction partners, Flexnode delivers on projects ranging from 50kW to 1MW racks, to underpin vital AI initiatives globally.