← back
Agentic Workflows on Vertex AI: Rukma Sen
Takeaway
Agents on Vertex AI are model+tools+orchestration with explicit responsibility for safety, privacy, and clear gen-vs-fact UX as wearables make AI ambient.
Summary
- Google Cloud's Rukma Sen frames agents as the human-facing interface bridging natural language users to model 'language'.
- Working definition: agent = model (brain) + tools (hands) + orchestration (nervous system) with memory and state.
- Distinguishes deterministic, generative, and hybrid agents; advocates ethical guardrails, data privacy, and clear gen-vs-fact labeling especially given wearables and ambient compute.
- Spectrum from single-agent (count-letters-in-banana failure case) to multi-agent architectures on Vertex AI, with each step trading simplicity for capability.
agentsvertex-aigoogle-cloud
Original description
Tired of chatbots that can barely answer basic questions? This talk dives deep into Vertex AI's agentic workflows. We'll walk you through the nuts and bolts of designing and building agents that can handle complex tasks, make decisions, and interact with your systems like a pro. You'll leave with the skills and knowledge to automate the boring stuff and unlock new levels of efficiency. Recorded live in San Francisco at the AI Engineer World's Fair. See the full schedule of talks at https://www.ai.engineer/worldsfair/2024/schedule & join us at the AI Engineer World's Fair in 2025! Get your tickets today at https://ai.engineer/2025 About Rukma AI Product Marketing, Google