Jason M. LemkinCEO, SaaStr · Co-Founder of SaaStr AI, SaaStr Fund, Adobe Sign

AI Agents: Train Your Own Business AI Effortlessly! #shorts

21 Aug 2026 · 2 min

Watch on YouTube

2:19

In this short, Jason M. Lemkin outlines a roadmap for making AI agents a standard part of every business by the end of the year. He argues that teaching each user to build an agent is infeasible, so the solution is to let agents train themselves. The workflow he describes starts with gathering real or synthetically generated conversation feeds that represent the range of customer interactions a business might have. These feeds are classified into use‑case categories, and a few representative examples are selected. An API‑driven platform then hands the data to an autonomous training agent that runs an iterative evaluation loop—similar to Lemkin’s “Composer” agent—continuously refining its behavior until it meets the desired performance. When the agent encounters a logical gap (e.g., a specific refund rule or a backend system it does not know), it pauses, asks the business for the missing rule or integration details, and incorporates that information. Lemkin illustrates this with an e‑commerce returns scenario, showing how the agent can query the merchant’s refund thresholds, generate shipping labels, and invoke backend services via point‑and‑click integrations. He concludes with a forward‑looking vision where agents could autonomously discover and interact with external systems on behalf of the business, dramatically lowering the cost and effort of deploying AI assistants at scale.

Chapters

By the end of this year, I think most businesses are gonna have their own agent they deploy either on their website or behind a phone number or through email or to ChatGPT or Claude that you can just access. But to get all those businesses, right, take our 200,000 guests, get every single one of them using, building that agent. There's no way we make that happen this year if we have to teach all of our users how to build agents. And obviously that's, it's cost prohibitive for them to hire somebody to do it. So we are just down the path of agents can train the agent. And I think the trick there is we're just obsessive about when you hire the, you hire an FDE, I like, we look at what is the person actually doing, right? What is the actual literal process? And so I'll give you an example of what we do. We take, we could take a feed, right? And we can synthetically generate this if we have to, of all the different kinds of cases and experiences or conversations, right? That somebody might have with an agent that represents a business. We can take a real feed, we can generate a synthetic one. We then classify that into various use cases. We take a couple representative examples. We then give an agent that has full access to our platform, 'cause it's all API-based, right? And we say, great, I want you to train up this agent. Here's, here's an eval, here's a use case. Don't stop, little Ralph loop, don't stop until this comes back and it works. Yeah. And similar to our Composer agent, what it will do is it will interrupt when it says, hey, I've hit a logical point where I just don't have the instructions on how to do this. So in e-commerce, hey, somebody wants to process a refund, let's say, right? Different companies have different rules around that. If something's below or above a certain dollar threshold, they might say, you know what, we actually don't want you to return it. It's too expensive. Other cases they'll say, okay, we do want you to return it. There's also all sorts of little rules, right? This agent will figure out, they're like, look, I can build this. But I often find that businesses like you, and this is where we get value from scale, have rules like this. Can you tell me what yours are? Or it'll say, hey, there's, I know there's a backend system that say, let's take the case of returns, we'll print that shipping label and send you, say, a box or something to return something in. But I need to know where that system is, right? So we'll ask and request from the user to basically go use those. And we have a lot of integration, so it's a little bit point and click, right? And in the future, we see a world where it's like, I don't know, maybe you could give it access to just go hunt on your behalf.