Anyone building enterprise agentic AI should treat it as a full system requiring governed data, risk controls baked into multiple layers, end-to-end latency optimization, and telemetry from post-production as a critical source of improvement.
As a closing lesson, Rashmi advises organizations earlier in their agentic journey to treat agentic AI holistically as a system, grounded in governed data, layered risk controls, and continuous post-production learning. ✦ AI generated
Rashmi Shetty · The TWIML AI Podcast · 2026-04-16 · original ↗
starts at this moment · 45:45
“if you were talking to folks that have you know, similar enterprise requirements but are maybe further behind in the journey, you know, how would you talk to them about you know, lessons learned, best practices, things that have made your successes possible?”
You really need to treat agentic AI as a system. It's truly a system. You have to start with governed data. You have to kind of put in that risk controls baked into multiple layers of your application or your system. You have to look at latency as something that needs to be optimized end-to-end... your biggest gains do come from post-production telemetries also critical.
verbatim transcript · starts at 45:45
45:45system. It's truly a system. You have to start with governed data. You have to kind of put in that risk controls baked into multiple layers of your of your application or your system. You have to look at latency as something that needs to be uh optimized end-to-end. Consider take into considerations handoffs as well in this end-to-end experience for your customers in terms of latency expectations. And understanding that your biggest
46:16gains do come from post-production telemetries also critical. I think yeah, basically in in in a nutshell that you know, as you move from the AIML to the GenAI world and now to the agentic problems, I think bridging that bridging that world is important to understand. You don't throw away at least for Capital One, we had a very very good legacy of tech stacks that we had built, which we are leveraging to
46:41quickly jump onto the agentic bandwagon in the last year. So, so for us especially in our case, reasoning became explicit. Specializing became modular. Became very easy. Um yeah, so data quality, governance, integration, keeping an eye on end-to-end latency, post-part improvements. I think these are some of the key things that um that that that I would say that key lessons for anybody else wanting to go along this journey. For folks that
47:16are in similar you know, platform types of roles, is there um you know, a different slant or take on that or more nuanced or detail um for folks that you know, are thinking about expanding existing platforms or building out new platforms for that matter to accommodate agents? Yeah, I mean some of the new some of the nuances that I mentioned, you need to understand what services you're lacking to build
47:40this agentic capabilities. What are the policies that you're lacking to build these agentic possibilities. Look at observability from a completely new lens. Um instrument sooner. Define escalation threshold. I think go I think the problem of building agents has been solved for. We are moving very rapidly into a world where agent execution and governing of agents in execution and in execution environments is becoming more critical. Talk a little bit about kind
- ·Not just a model — a complete system
- ·Start with governed, trustworthy data
- ·Bake risk controls into multiple layers
- ·Optimize latency end-to-end
- ·Biggest gains come from post-production telemetry
- ·Treat production data as critical feedback source
- ·Continuous learning improves the system over time