Grant Harvey

Yeah.

I'm doing well.

I'm doing well.

I love that.

That's a very visual flowery description of me, which I welcomely embrace.

How are you?

Well, what are we talking about today, Grant?

Today, we are talking about reinforcement learning environments, the training grounds where AI agents learn to plan, use tools, adopt, and make judgment calls across multi-step tasks.

These environments are quickly becoming the bottleneck for real-world AI performance.

And in 2025, they were one of the most aggressively funded and least understood parts of the AI stack.

At Surge, he's helped build large-scale simulated workplaces like CoreCraft, environments used by frontier labs to test whether models can actually do knowledge work end-to-end.

He's also the co-author of Surge's recent research showing that even the best models fail roughly 40% of the time on real workplace tasks, with failures clustering around planning, adaptability, groundedness, and common sense.

Well, hopefully we can help out all of your VC friends and teach them a bit more direct from the horse's mouth here.

I guess to start, how did you end up at Surge AI building RL environments?

And what was the moment that you realized that this was the future of AI training?

Okay.

That's good to know.

Well, the RL example with you're going out onto the golf course and you're trying to, based on the feedback that you get, adjust your game.

That just, to me, feels like the most similar to how we humans learn in general.

Do you agree with that?