RL environments — simulations of apps that agents need to use — are the fastest-growing data type and represent the next frontier for model evaluation and training.
Oswald identifies 'environments' — simulated worlds that train agents to use tools like Salesforce — as the fastest-growing data category, representing a shift toward deployment-relevant evaluation data. ✦ AI generated
Oswald Nitski · 20VC · 2026-07-25 · original ↗
starts at this moment · 41:08
“What data type is not hugely in demand today that you think will be hugely in demand next year?”
The data type that's growing the fastest for us is environments. People you know that you might have seen a lot about these RL environments on Twitter. It's kind of like a hype term. Every company kind of has a different definition for it. But we are certainly the leader in the category and view it as basically these simulations of apps that you might want your agent to use. And also as per rich start state, which we call like the world that is basically representative of all the data you might have on your machine like your laptop. And then we have tasks that train agents how to use those tools to accomplish something that's useful. It's a bit of a complicated annotation process because the agent has to interact with this simulated world. We have to make that start state, which can be hundreds of files, thousands of files. And the shift here is that the data that the models are now the agents are being evaled and trained on looks a lot closer to what they see in deployment. So, if you want to learn how to use something like Salesforce, you need a pretty high-fidelity mock that acts exactly like Salesforce in your eval and training. And it's complicated to get this set up. Just like years ago preference ranking was really hard to get set up. SFT was really hard to get set up when InstructGPT first came out. So, this is the frontier right now. Labs are figuring it out. Eventually, it'll get so smooth that enterprises can do it, too.
verbatim transcript · starts at 41:08
41:08communication that make it challenging. >> What data type is not hugely in demand today that you think will be hugely in demand next year? >> The data type that's growing the fastest for us is environments. People you know that you might have seen a lot about these RL environments on on Twitter. It's kind of like a you know hype term. Um every company kind of like has a
41:29different definition for it. Um but we um are are certainly the leader um in the category and view it as basically these like simulations of apps that you might want your agent to use. Um and also as per rich start state, which we call like the world that is basically representative of all the data you might have on your machine like your laptop. And then we have tasks that train agents
41:54how to use those tools to accomplish something that's useful. It's a bit of a It's a bit of a complicated annotation process because the agent has to like interact with this simulated world. We have to make that start state, which can be hundreds of files, thousands of files. Um and the shift here is that the data that the models are now the agents are being evaled and trained on looks a
42:17lot closer to what they see in deployment. Right? So, if you want to learn how to use something like Salesforce, you need a pretty high-fidelity mock that acts exactly like Salesforce in your eval and training. And it's complicated to get this set up. Just like years ago preference ranking was really hard to get set up. Uh, SFT was really hard to get set up when instruction when
42:36Instruct GPT first came out. So, this is the frontier right now. Um, labs are figuring out new labs are figuring it out. Eventually, it'll get so smooth that enterprises can do it, too. >> Are labs price sensitive on data acquisition? >> By data acquisition, um, >> Well, when they when they when they go on a project with you, uh, are they price sensitive? Like, are they haggling going, "Oh, well, you know,
43:02Edwin at Surge gave me a 10% discount. Can I have that?" Or are they like, "Just give me the [ __ ] data." >> Well, there's always the, you know, aspect of negotiation and the procurement team trying to get a better deal. Um, but we're we've chosen a great business where our work directly affects the business outcomes of our customers, right? So, we we have a great setup
- ·Environments are the fastest-growing data type for RL training
- ·Simulated app worlds that agents interact with to learn tools
- ·Includes a rich start state (hundreds to thousands of files)
- ·Shift toward evaluation data that mirrors real deployment conditions
- ·Agents must interact with simulated worlds to complete tasks
- ·High-fidelity mocks (e.g., Salesforce) are required for realism
- ·Analogous to how preference ranking and SFT were hard to set up
- ·Labs are figuring it out now; enterprises will follow later