# Scaling AI Agents Without Breaking Reliability — Preeti Somal, Temporal AI Engineer · 2025-07-28 Preeti Somal, SVP of Engineering at Temporal, argues that the platform is the right choice for building reliable, scalable agentic AI applications. Temporal provides battle-tested orchestration through workflow abstractions, handling state, retries, and failure transparency so developers can focus on business logic. She cites customers like Dust and Gorgias running AI agents on Temporal in production, achieving up to 6x faster feature delivery. The platform uses signals and queries for human interaction, stores full workflow history for debugging and compliance, and offers Temporal Cloud for managed scalability. Somal emphasizes that agents are complex distributed systems requiring robust orchestration, and Temporal’s decade of production use in mission-critical applications proves its reliability. ## Questions this episode answers ### What speed improvement have companies seen when using Temporal for AI agent development? Preeti Somal, SVP of Engineering at Temporal, says that customers using Temporal for AI agent development have sped up their feature delivery velocity by over 6 times. She notes that developers can focus on business logic while Temporal handles reliability and scalability, enabling them to put applications into production in weeks. [8:08](https://aie.addtry.com/da92ea74-5058-4af5-ba75-deb2ae03ffb0?t=488000) ### Which programming language recently became the most popular for building AI agents with Temporal? Preeti Somal highlighted that Python recently became the most popular language for Temporal SDKs, overtaking others in January. This trend underscores Python’s dominance in AI agent development, as developers increasingly use Temporal to build reliable, scalable agentic applications. [4:10](https://aie.addtry.com/da92ea74-5058-4af5-ba75-deb2ae03ffb0?t=250000) ### Which real-world companies are running AI agents on Temporal in production today? Preeti Somal mentioned that Gorgias, a customer service platform for brands like Reebok, Timbuk2, and Glossier, runs AI agents on Temporal in production. Additionally, companies like Dust are building their agents on Temporal, with another unnamed company recently featuring Temporal in its tech stack. Temporal provides these companies with agility and reliability, allowing them to focus on business logic. [5:14](https://aie.addtry.com/da92ea74-5058-4af5-ba75-deb2ae03ffb0?t=314000) ## Key moments - **[0:00] Intro** - [0:33] 'It is what is also called a water bear and is the most resilient animal known to humankind.' - **[1:17] The Problem** - [2:35] LLMs are inherently unreliable: when Preeti asks who has called an LLM and it succeeded 100% of the time, no one in the audience raises a hand. - **[3:15] Temporal’s Fix** - [3:56] Temporal's Python SDK usage overtook all other languages in January, reflecting Python's dominance in AI agent development. - [5:23] Gorgias runs AI agents on Temporal at scale in production for customer service for brands like Reebok, Timbuk2, and Glossier. - **[6:34] Architecture & Code** - [6:56] Temporal's workflow abstraction handles all error handling and retries, letting developers focus on business logic without writing plumbing code. - [8:04] Developers using Temporal have sped up feature delivery velocity by over 6x, according to customer case studies. - **[8:50] Booking Demo** - [10:23] Nowhere in there will there be statements like, 'If something fails, keep retrying it.' - **[12:31] Temporal Cloud** - [13:42] Temporal's Code Exchange provides open-source examples of agentic AI workflows, allowing developers to run and inspect the code. - **[14:17] Get Started** ## Speakers - **Preeti Somal** (guest) ## Topics Modular AI Orchestration ## Mentioned Dust (company), Gorgias (company), Temporal (company), AgentOps (product), Temporal Cloud (product) ## Transcript ### Intro **Preeti Somal** [0:15] My name is Preeti, and I'm part of the engineering team at Temporal. How many people here have heard of Temporal? Perfect, great. So, Temporal is the company that takes reliability incredibly seriously—so seriously that our mascot is a tardigrade. Does anybody know what a tardigrade is? Yes? Some folks? Well, it is what is also called a water bear and is the most resilient animal known to humankind. And so that's how seriously we take reliability. Definitely stop by our booth for some stickers and some pins to just show how much you care about reliability. Alright, so my goal in the next 17 minutes or so is to convince all of you that Temporal is theright choice of platform as you go out to build agentic AI applications. So let's diveright in. We've heard a lot about how, you know, agents are just software. However, they are complex distributed systems, they need to cope with LLMs, and they must scale and provide durability and reliability, otherwise no one's going to trust your agent. You know, we can build, like, really cool stuff, but if it doesn't work, nobody's using it. ### The Problem **Preeti Somal** [1:38] We also know that complex systems need orchestration. Decks used the word "workflow" a few times, and essentially at the core of agentic AI applications is a complicated workflow that orchestrates multiple processes, needs to handle state potentially over long periods of time, there needs to be human interaction for approvals or other reasons, and of course they need to be able to be able to run in parallel for efficiency, call tools. There's just a lot of things going on. You know, how many of you feel like building agents is really simple? You're just calling one switch statement,right? Yeah? I mean, there's a lot of things that are interacting here, and how can you actually keep track of that, make sure it's running reliably, as well as tracing and looking at the visibility of all of these pieces? And again, you know, these systems are inherently unreliable. How many of you have called an LLM and it succeeded 100% of the time? Yeah? Nobody's raising their hands. So we've dealt with this. As you're building these applications, you are seeing inherently how unreliable some of the toolchain here is. And then, you know, difficult to debug and test. And Alex has been talking about AgentOps being kind of built around this, but clearly the insight into what's happening has been incredibly hard to get. It's been incredibly difficult to test this in pre-production. ### Temporal’s Fix **Preeti Somal** [3:15] Well, the interesting thing here is that these problems have existed for some time in building complex distributed systems. And Temporal is a company that was founded around solving these problems. Our mission really is to outsource the reliability and scalability parts of building a complex distributed application seamlessly. So again, you can focus on the hard parts of writing your business logic. The way that Temporal works is that we've built language idiomatic SDKs. The languages are available there. And in fact, one of the fun facts here is that Python has overtaken all the other languages in the month of January, and that sort of is showing how much of Python is being used in building these applications. We handle all the plumbing code for you, making sure that every process executes reliably and providing you guardrails. And this is a battle-tested product. Temporal has been in production for over a decade. Temporal is used in mission-critical applications. These are just a few examples of our customers using Temporal in production today. So we feel that using Temporal for running these, for building your agentic AI applications, gives you reliability out of the box. But, you know, I can stand here and talk all day about it. You probably don't believe me. So we have some customer quotes here that will help you understand this. One of them is from a customer called Dust that is building their agents on top of Temporal. And the other is a company you may have heard of that recently talked about the tech stack they use, and Temporal is very clearly featured there as well. We also have a number of use cases published. So Gorgias, for instance, is using AI agents today in production, built on Temporal. This is the company that does customer service for brands like Reebok or Timbuk2 or Glossier. These are all household names. And the reason I'm bringing this up is just to help you understand that customers are today running agents on Temporal at scale in production. And what Temporal is bringing to them is incredible agility and speed, because they can focus on writing their business logic and don't need to worry about reliability. The reason I put up the payments example here is to show you how mission-critical some of the workloads that are running on Temporal are. And finally, you know, some more quotes here from customers, developers using Temporal around building agentic AI applications. I hope some of this is resonating in terms of the issues that you are seeing as well as you're going out and building these applications. Alright, let's talk a little bit about architecture and code, because no talk here can be complete if we don't talk architecture and code,right? Alright, I was hoping I would get some clap, so let's get this going. Alright. So this is an example of an architecture before Temporal. What we're seeing here is there is a lot of interaction and error handling that developers are being forced to code. ### Architecture & Code **Preeti Somal** [6:56] And when you use code using Temporal, essentially we can abstract all of that out into this concept of a workflow. A workflow is something that you write. This is very much a developer-focused tool. This is not a tool that a business user or a non-technical person would use. This is a developer going in and coding and building their applications using these SDKs around the concept of a workflow abstraction. And at the end of the day, when you think about agents, you essentially are just orchestrating a number of pieces around the interaction, the large language models, the chat history database, and the tools,right? These are the key abstractions that are in play, and you're orchestrating that using Temporal. What's the impact? You know, everybody's going to tell you they've got the best platform here, but what is the impact for engineers? What we really are able to do is accelerate development. And what you can do is take Temporal and you can put applications out in production in weeks. We've had customers with case studies where we've sped up their feature delivery velocity by over 6x once they've started using Temporal. You can reach greater scale. One of our customers is a consumer application that is scaling with events, and they don't need to worry about handling any of that scale logic at all. So our cloud will handle the scale for you. Of course, you know, once you've got reliability nailed, you can sleep better at night, and that's always important. And with reliable applications, customers are happier. Now, I've talked a lot. ### Booking Demo **Preeti Somal** [8:50] I wanted to walk through an example. I'm not doing a demo because of all the various issues. And it also seems like, for some reason, travel is like the classic use case everybody seems to be demoing. So let's diveright in. So we've got a demo of a ticket booking agent. This demo is live at our booth as well, so if you're interested, you can go look at that at the booth. And what we'll do is I'll quickly walk you through a little bit of the architecture and how Temporal would work here. And so clearly, you know, some of the key pieces here are around the user, the system, which is Temporal, and AI, your language models, goals, and tools. And the way that Temporal works here is essentially going to be able to take this flow and wrap pieces of this in Temporal concepts. So, for instance, the workflow defines the flow of the application, and it's written as code. So this is where you would orchestrate the interactive loops. You would receive we have this notion of a signal, which is how the workflow gets input. We have a notion of a query. So there's a rich set of abstractions that you program against to build that workflow that will essentially take kind of all of the pieces of this model that I'm showing you and translate that into code. And nowhere in there will you have any statements or code that we call plumbing code. That is, nowhere in there will there be statements like, "If something fails, you know, keep retrying it." All of those pieces are handled by Temporal. We also store all of the workflow history so that you can go in and you can look at the visibility of what is happening as your agent is navigating this complex set of interactions. Temporal has the notion of activities, and so the tools that you use can be wrapped into activities. And again, this is just code. And of course, with LLMs, you can use whatever provider you need. We are able to help you validate the inputs and drive towards the goal. And again, failures are handled transparently by Temporal. And then interactions are managed through Temporal signals and queries, and they're stored in the workflow history. So there's a very clear sort of record of how your agent is executing, and you can go in and look at that. You can also export that. One of the things we are hearing is customers want access to that history for compliance reasons or for kind of being able to go and debug in their test dev environment. So we allow the capability to export that entire history, and you can use it for whatever sort of purpose you might need. And finally here, you know, you can kind of look at the fact that we've got the ability to have loops. We can, you know, it's a very rich programming model where you can take the various sort of use case patterns for your agent, and you can build them as a workflow pretty quickly and get up and running. ### Temporal Cloud **Preeti Somal** [12:31] And then Temporal Cloud, of course, is where we do all of the heavy lifting around the reliability and scalability pieces for you. So your agent, your workflow, the code actually runs in your environment, and Temporal Cloud is where all of the execution state, the call stack, the, you know, looking at all of the failures and retries, all of that is happening within Temporal Cloud. I know I'm speeding through a lot here, but definitely come by our booth as well. The worker is what I was just talking about. This is your code. It runs in your environment. It is essentially fitting into any of your own CI/CD practices. A big part of the Temporal focus has been on meeting developers where they are. We don't want you to change how you write code. We just want you to get more efficient and help you focus on writing your business logic and not having to worry about all of the reliability and scalability issues here. And this, for instance, is the worker code for the use case that I was just showing. I know this is a screenshot. What I wanted to show here is we've got this concept of code exchange. Temporal, if you weren't aware, is an open-source product as well. So you can go in, and I know this conference loves QR codes for some reason. So you can go in and you can actually look at the code, at the code exchange, and see how Temporal operates there. ### Get Started **Preeti Somal** [14:17] Finally, Temporal Cloud is available. You can go sign up. We are giving away credits. So getting started and kicking the tires on using Temporal is fairly easy. You can go to code exchange. You can look at any example you want. You can run that in your local dev environment. You can run it against cloud, and you can be up and running pretty quickly here. And we are, like I said, we are on the expo floor. Come by and chat with us. We are booth G3. Perfect. Thank you. --- This library is powered by PodHood (https://podhood.com), the podcast website platform.