The first question when evaluating an AI model's utility is not whether the model is smart, but what data and context are being provided to the model in the prompt; if a project, repository, ticket, or workflow is not part of the input, the model will hallucinate rather than reason accurately.
causalpending
Speaker
Unidentified Speaker — Harness Engineering Masterclass: Technical Deep Dive on how… [mQfTdNVCOB0]Evidence Quote
“So, if your current project or repository or the ticket or incident or workflow is not part of that input, the model will start guessing, and that's what we call hallucination. So, the first question is not actually that is the model smart. I think the first question is what are we giving it to work with in the first place.”
Source
Harness Engineering Masterclass: Technical Deep Dive on how to build Agentic Systems— The Carbon LayerCreated: 8/12/2026, 6:26:50 PM
Your notes
Loading notes...