Taking a look under your agent’s hood

Ryan Donovan (0:07)

Hello, and welcome to The Stack Overflow Podcast, a place to talk all things software and technology. I'm your host, Ryan Donovan, and today we're talking about agents. What are they building in there, and how to find out.

My guest for that is Yanbing Li, who is the Chief Product Officer at Datadog. So welcome to the show, Yanbing.

Yanbing Li (0:27)

Thank you for having me, Ryan.

Ryan Donovan (0:29)

My pleasure, my pleasure. Before we figure out what those pesky agents are doing, can you give us a little flyover of how you got into software technology?

Yanbing Li (0:37)

I feel like I've been software forever for most part of my life.

I would characterize my education as I've studied until there is no more school to go to. So I have a PhD in electrical and computer engineering. Then I've been an engineer ever since. Except for at Datadog, I'm far more focused on product than combinations of product and engineering. And my introduction to observability started with my time at Google. This is seven years ago when I was leading the observability effort at Google, both for powering Google's infrastructure as services, as well as being built as product as a part of the Google Cloud capability. So that was my first introduction to observability.

Then I had an interesting detour into everything AI, where I was building self-driving trucks at a company called Aura. And Aura today is probably still not just the first, but the only company that's operating driverless trucks commercially on US public road. So that was kind of the experience of absolutely needing to understand everything that AI agent is doing. Granted, self-driving started before the ChatGPT LLM days, but there is definitely a loss of parallel in thinking about what it takes to fully unleash your agent into the wild.

Ryan Donovan (1:59)

Observability is one of those things that's really ramped up a lot since, Datadog used to be metrics and dashboard company, but now fully part of the observability space. And everybody's trying to figure out how do you apply observability to agents? How are you thinking about keeping eye on agents when they're running?

Yanbing Li (2:16)

As you said, observability has existed for a long time for a really complex distributed system.

That part remains the same, but with AI agent, there are certain things that's new and different. First of all, starting was AI models playing instrumental role in bringing reasoning and intelligence into AI agent. Now we deal with the non-discrimininistic nature of AI models. I think that tend to be the first thing that when we talk about AI observability, we started with LLM observability, really to understand what the LLM is doing. But now that is quickly expanding from just observing the AI models and the interaction with the AI models to really understand the AI agent as a whole. If we think about AI agent is still a fundamentally a distributed system, it's just this distributed system is now powered by intelligent models underneath. There are certain things remain the same. We have to understand these new nuances that's introduced by AI.

Ryan Donovan (3:21)

Yeah. The observability of LLM is still a ongoing research project as I understand it. To get a greater detail to explainability. Is that right?

Yanbing Li (3:30)

There's certainly certain things at the research frontier, but I also think there's lots of things that's being in production. The fact that we do rely on AI agents in our day-to-day use, in some of the enterprise use cases, is an indication that LLM observability or agent observability, in combination with other things, is giving us levels of comfort to rely on these AI agents. And I do think it's a journey because I work with lots of the enterprises. They're still in this early phase of AI development. Can I trust my AI agent not to stay up, but also to do the right thing? I've seen a lot of successful agents, but when I speak to our customers, many more of them are still in the process of building that. And given the rapid landscape of AI, I'm sure this how we do it is going to be evolving continuously.

Ryan Donovan (4:27)

The LLM was you give it an input, it gives a response, and now there's multi-step turn taking, use-to-use, tool-use. What are the pieces that you have to observe in an AI agent?

Yanbing Li (4:39)

I think you said it really well. Certainly, we've started with understanding prompts and LLM output. But because agents has becoming this distributed system in nature, so it's becoming a lot more complicated. We do understand the reasoning, the tool calls, the prompts and the responses, and we need to understand the behavior. We need to understand why it's making certain decisions, and we need to also broadly understand what's the implication across the applications and outcome. So I think we're definitely evolving from simply observing just the software stage, software house to truly observing software behavior.