Glossary term
Glossary term
Agentic Systems
A prompt engineering technique that encourages a large language model (LLM) to explain its reasoning, step by step. For example, consider the following prompt, paying particular attention to the second sentence:
How many g forces would a driver experience in a car that goes from 0 to 60 miles per hour in 7 seconds? In the answer, show all relevant calculations.
The LLM's response would likely:
Show a sequence of physics formulas, plugging in the values 0, 60, and 7 in appropriate places.
Explain why it chose those formulas and what the various variables mean.
Chain-of-thought prompting forces the LLM to perform all the calculations, which might lead to a more correct answer. In addition, chain-of-thought prompting enables the user to examine the LLM's steps to determine whether or not the answer makes sense.
Created for this library
A math tutoring app uses chain-of-thought prompting so the model explains each step of an algebra problem rather than only outputting the final answer.
A financial analyst's research assistant uses chain-of-thought prompting to make the model show how it derived an earnings estimate before the analyst signs off.
A legal-tech vendor uses chain-of-thought prompting in its contract review agent so reviewers can audit the reasoning behind any flagged clause.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License