Partner with us

Save $100 on your pass

Call to action
Your text goes here. Insert your content, thoughts, or information in this space.
Button

Back to speakers

Swetha
Ranganath
Principal Product Manager (AI)
Microsoft
Swetha Ranganath is a Principal Product Manager at Microsoft working on Microsoft 365 Copilot and Researcher experiences. Her work focuses on how AI can support real-world knowledge work—not just finding information, but helping people reason, decide, and execute in complex domains. She spends much of her time partnering with engineers, researchers, designers, and customers to translate messy, high‑stakes workflows into reliable AI systems, with a particular focus on evaluation, trust, and human‑AI collaboration. Swetha brings a practitioner’s perspective to conversations about what’s working, what’s not, and what it actually takes to make AI useful at scale. On panels, she enjoys exploring the trade‑offs behind product decisions and sharing lessons learned from building and deploying AI systems inside large organizations.
Button
25 February 2027 13:30 - 14:00
Panel | Context engineering in production: Retrieval, memory and data freshness for long-running agents
As AI agents take on longer, more complex workflows, maintaining accurate and relevant context becomes increasingly difficult. Agents must retrieve the right information, retain useful memory, and adapt to changing data without relying on outdated assumptions. Poor context management leads to incorrect decisions, increased latency, and unnecessary costs. This panel explores how engineers can design retrieval pipelines, manage agent memory, and maintain data freshness to support reliable, long-running agents in production. Key takeaways: → Designing retrieval pipelines that deliver accurate, relevant, and up-to-date context. → Managing agent memory while preventing context overload and unnecessary costs. → Maintaining data freshness and reliability across long-running, multi-step workflows.