Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement

Source

arXiv

arxiv.org/abs/2607.11749v1

Read the source

Source

Plain-Language Brief

A study examined how using a large language model (GPT-5) to rewrite work emails in either a playful or professional tone affects recipient behavior. The study found that playful editing increased emotional positivity in emails, while professional editing decreased it. However, neither condition directly affected open rates, reply rates, or response times. Instead, the emotional positivity of the sender's overall emails predicted both opening and replying rates.

What the Document Says

  • The study involved 121 employees across six companies who sent work emails under three conditions over three weeks: unaided writing, GPT-5 rewriting in a playful tone, and GPT-5 rewriting in a professional tone.
  • Across 16,880 emails, playful editing increased emotional positivity (B=+0.068, p<0.001), and professional editing decreased it (B=-0.041, p<0.001).
  • Neither condition directly altered open rates, reply rates, or response times.
  • Within-sender positivity strongly predicted both opening (OR=2.05) and replying (OR=3.32, p<0.001)
  • The study suggests that AI-assisted communication shapes workplace engagement not through its use, but through the emotional tone of the language it produces.

Key Concepts Mentioned

  • Large language model (GPT-5)
  • Playful tone
  • Professional tone
  • Work emails
  • Emotional positivity
  • Open rates
  • Reply rates
  • Response times

Claims Made by the Document

  • Playful editing increases emotional positivity in work emails.
  • Professional editing decreases emotional positivity in work emails.
  • Neither playful nor professional editing affects open rates, reply rates, or response times directly.

Evidence Used

  • B=+0.068 and p<0.001 for playful editing
  • -0.041 and p<0.001 for professional editing
  • OR=2.05 and OR=3.32, p<0.001

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Large language models (LLMs) are rapidly reshaping workplace communication, yet whether AI-assisted writing changes how recipients actually behave, and through what channel, remains unknown. Here, in a randomized crossover field experiment, 121 employees across six companies sent work emails under three conditions over three weeks: unaided writing, GPT-5 rewriting in a playful tone, and GPT-5 rewriting in a professional tone. Across 16,880 emails, playful editing increased emotional positivity (B=+0.068, p<0.001), and professional editing decreased it (B=-0.041, p<0.001), yet neither condition directly altered open rates, reply rates, or response times. Instead, within-sender positivity strongly predicted both opening (OR=2.05) and replying (OR=3.32, p<0.001), a significant indirect pathway through which AI editing shaped behavior, in the absence of any direct effect. These findings suggest that AI-assisted communication shapes workplace engagement not through its use, but through the emotional tone of the language it produces.