A Study on Enhancing Employee Engagement with GPT through Information Provision

Last registered on November 29, 2023


Trial Information

General Information

A Study on Enhancing Employee Engagement with GPT through Information Provision
Initial registration date
November 14, 2023

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
November 29, 2023, 9:56 AM EST

First published corresponds to when the trial was first made public on the Registry after being reviewed.



Primary Investigator

Peking University

Other Primary Investigator(s)

PI Affiliation
Peking University

Additional Trial Information

In development
Start date
End date
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
We are collaborating with a company that has integrated GPT into its internal office systems, allowing employees to directly engage with GPT through a dialog box in office software. However, the current usage rate of GPT among employees is relatively low. We plan to increase employee utilization of GPT through three pieces of information: information on the productivity gain of using GPT; the expectation management of GPT and the effective prompt techniques. Each employee will randomly receive one of these pieces of information or receive no information. We will observe the usage patterns of GPT for each employee before and after receiving the information, as well as their subsequent job performance.
External Link(s)

Registration Citation

Huang, Huaqing and Juanjuan Meng. 2023. "A Study on Enhancing Employee Engagement with GPT through Information Provision." AEA RCT Registry. November 29. https://doi.org/10.1257/rct.12489-1.0
Experimental Details


provide information via the chat box in the company's office software.
Intervention Start Date
Intervention End Date

Primary Outcomes

Primary Outcomes (end points)
usage of GPT for each employee, main measurement is the number of interaction rounds every day.
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
employees' satisfaction with GPT, employees' performance
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
- one control group: no information
- three treatment groups:
randomly provide one of the following three pieces of information to employees on the same day at the same time:
information on the effective prompt techniques.
information on the productivity gain of using GPT;
information on the expectation management of GPT;
Experimental Design Details
Randomization Method
randomization done in office by a computer
Randomization Unit
Was the treatment clustered?

Experiment Characteristics

Sample size: planned number of clusters
1100+ employees
Sample size: planned number of observations
1100+ employees
Sample size (or number of clusters) by treatment arms
each treatment arm comprises approximately one-fourth of the total employees, which is 280+ employees.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)

Institutional Review Boards (IRBs)

IRB Name
IRB Approval Date
IRB Approval Number


Post Trial Information

Study Withdrawal

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information


Is the intervention completed?
Data Collection Complete
Data Publication

Data Publication

Is public data available?

Program Files

Program Files
Reports, Papers & Other Materials

Relevant Paper(s)

Reports & Other Materials