Behind the Craft · Sunday, June 28, 2026
Jess Yan explains that for AI agents to produce predictable outputs, especially when handling complex tasks, it's beneficial to be prescriptive with initial prompts. This includes providing data schemas and breaking down tasks into discrete segments, which also aids in debugging.
“But I had a very specific schema that I wanted it to be aware of. So for example, I wanted it to know exactly what the structure of the data set was beforehand.”
“Um, and then I wanted to break down the steps into discrete, uh, discrete segments. So that I could get very predictable outputs at the end of the task.”
“Because these agents are, you know, randomized actors. So you do need to be somewhat prescriptive sometimes if you want to have, uh, very predictable outputs.”