Home > AI Solutions > Artificial Intelligence > White Papers > Rethinking Hierarchical Text Classification: Insights from Multi-Agent Experiments with Small Language Models > Useful prompting techniques for agentic workflows
Chain-of-Thought prompting encourages the LLM to break down complex problems into step-by-step reasoning. For more information, see Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.
To implement this type of prompting:
Human: Let's solve some math problems step by step.
Q: What is 15% of 60?
A: Let's approach this step by step.
Therefore, 15% of 60 is 9.
Now, can you solve this problem using the same step-by-step approach?
Q: What is 25% of 80?
A: Certainly! I'll solve the problem step-by-step.
Therefore, 25% of 80 is 20.