Prompt engineering · topic 3 of 8
Chain of thought (CoT)
Step-by-step reasoning before the final answer—the most widely used nudge.
1) Chain of Thought (CoT)
The simplest and most widely used technique.
Instead of asking the LLM to jump straight to the answer, we nudge it to reason step by step.
This often improves accuracy because the model can walk through its logic before committing to a final output.
First CoT diagram on the slide (earlier in the CoT section).
For instance:
Illustration placed right after “For instance:” in the PDF.
It’s a simple example but this tiny nudge can unlock reasoning capabilities that standard zero-shot prompting could miss.
Key takeaways
- CoT exposes intermediate steps instead of a one-shot answer.
- Small prompt tweaks unlock behaviors plain zero-shot misses.
