Aug 22, 6:00 – 7:30 AM (UTC)
Event time displays in your timezone.
1117 RSVPs
Session 4 is where experimentation ends and real delivery begins. We cover how to evaluate your agentic systems properly, what governance and production operations actually look like, and how to choose the right first pilot for your organization. We talk about your career too, and how to position your RPA skills for the agentic architecture roles that are opening up 🤖
We're talking evaluation frameworks, governance foundations, production operating models, and how to pick the right first pilot for your organization & we're also talking about you- your career, your skills, and how to position yourself as the person who leads this transition. 🎯
Recap and target state Reconnect the 5-session journey and explain the shift from experimentation to operational delivery of agentic AI
Evaluation framework Quality, latency, cost, failure modes, human effort saved, and business KPIs for judging whether your agentic system is actually working
Governance foundations Identity, access, audit trails, approval layers, model choices, prompt and version control, and compliance considerations for enterprise agentic systems
Production operating model Monitoring, incident handling, ownership, support, rollback options, and continuous improvement loops for agentic automation in production
Choosing the first pilot How to define good pilot selection criteria, scope boundaries, stakeholders, and expected outcomes for your first real agentic deployment
LangSmith
Recap of Session 4 outcomes and setting the stage for Session 5 — governance, risk, and responsible enterprise adoption of agentic AI
See you in Session 4! 🚀
NatWest Group
Vice President - RPA & Analytics
Iris software
Solutions Consultant
RPA Manager at Boundaryless Group
UiPath MVP
UiPath
Community Lead - Asia Pacific & Japan
Explore the UiPath Community ecosystem!