LLMs already know open coding, axial coding, and grounded theory. Give them context in your system prompt, like "make sense of all these errors," and they'll group your error codes effectively without generic prompts.
I love how there's more failure modes than distinct open codes. That's like classic example of LLM has no idea what you're talking about out of context.
That's a really great callout, Triana.
What we teach in the course is certainly you should use an LLM at this point to kickstart and grouping together open codes, but we definitely have like a more complex or comprehensive system prompt here that's kind of giving it context, like you're trying to make sense of all of these errors from all these traces for my AI application. The other thing is you can totally use this open and axial coding lingo, like grounded theory, social science lingo, because LLMs have been trained to do this. Go ask ChatGPT what axial coding is. It knows what it is because it is like well established in the literature. Highly encourage people to do that. Like you don't have to have this prompt of like analyze these errors.
