AI Decision-Making in Low / No Trainable Data Domains

Despite their power, Large Language Models struggle with specialized expert tasks where there is little or no trainable data. But what if we could teach them like we teach management consultants - using expert-created rules of thumb? This harnesses the LLM’s general reasoning abilities but provides domain-specific guidance to provide high-quality results. I’ve been looking at how to apply this to negotiations and geopolitical challenges and early results show this practical approach could unlock AI’s potential in these high-value domains.