Using Prompt Engineering to Better Communicate with People

Choose your words as carefully with people as you do with generative AI.

January 26, 2024

Illustration by Travis Constantine

Post

Annotate

Save

We should choose our words as wisely with people as we do with generative AI. In this article, the author offers six guidelines to consider when initiating discussions with stakeholders, whether they’re customers, partners, or employees: 1) Structure your prompts the right way. 2) Utilize reflective and thoughtful probing. 3) Convey empathetic language and humility. 4) Harness humor, playfulness, and emotions. 5) Acknowledge key challenges. 6) Be a good (and patient) listener.

It seems like everyone knows, or wants to know, how to produce the best possible prompts for generative AI. Having the right prompts can, in theory, allow managers to gather important information in a matter of seconds. But, among the buzz and promise of masterful prompt engineering, there is an emerging risk that managers will view generative AI as a one-stop-shop for gathering information. In doing so, they may neglect their most valuable information resources: employees, partners, and customers. These stakeholders offer contextual information and tacit knowledge that is beyond the capability of any generative AI tool. As we get better at speaking to robots, we should remember how to most effectively speak to our colleagues and customers, too.

New!

HBR Learning

Writing Skills Course

Accelerate your career with Harvard ManageMentor®. HBR Learning’s online leadership training helps you hone your skills with courses like Writing Skills. Earn badges to share on LinkedIn and your resume. Access more than 40 courses trusted by Fortune 500 companies.

Capture your audience’s attention with smarter emails, Slacks, memos, and reports.

Start Course

Learn More & See All Courses

Josh Morton is an Assistant Professor of Strategy and Innovation at Leeds University Business School, University of Leeds, and an Associate Fellow at the Digital Futures at Work Research Centre.