Chat2Learn-AI RCT

Last registered on July 13, 2026
View Trial History

Pre-Trial

Trial Information

General Information

Title
Chat2Learn-AI RCT
RCT ID
AEARCTR-0019133
Initial registration date
July 09, 2026

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
July 13, 2026, 7:53 AM EDT

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

Locations

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

Request Information

Primary Investigator

Name
Mauricio Koechlin
Affiliation
The University of Chicago
Contact Primary Investigator

Other Primary Investigator(s)

PI Name
Ariel Kalil
PI Affiliation
University of Chicago
Contact Investigator
PI Name
Michelle Michelini
PI Affiliation
University of Chicago
Contact Investigator

Additional Trial Information

Status
In development
Start date
2026-08-10
End date
2027-12-31
Keywords
Behavior, Education
Additional Keywords
early childhood; language development; receptive vocabulary; parenting intervention; text messaging; artificial intelligence; parent-child interaction; randomized controlled trial
JEL code(s)
Secondary IDs
J-PAL: GR-14173
Prior work
This trial is based on or builds upon one or more prior RCTs.
Abstract
This study is a randomized controlled trial (RCT) evaluating Chat2Learn-AI, an AI-enhanced, text-based parenting intervention that delivers personalized, illustrated conversation prompts to help low-income parents foster their children’s language skills through back-and-forth, open-ended conversation. The study will randomize a sample of N=1,000 low-income preschool and kindergarten families (children ages 3–6) to a treatment (Chat2Learn-AI) or business-as-usual control condition for a six-month intervention period. Families will be recruited through multiple partner school networks across the U.S. The primary outcome measure is child receptive vocabulary skill, and secondary outcome measures are broader child language skill (listening comprehension), child curiosity, and parental beliefs about investing in their children's language skill development. Child outcomes will be collected through direct assessment and parental beliefs will be collected through online surveys administered pre- and post-intervention period.
External Link(s)

Registration Citation

Citation
Kalil, Ariel, Mauricio Koechlin and Michelle Michelini. 2026. "Chat2Learn-AI RCT." AEA RCT Registry. July 13. https://doi.org/10.1257/rct.19133-1.0
Sponsors & Partners

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

Request Information
Experimental Details

Interventions

Intervention(s)
Chat2Learn-AI is a text-based parenting program supplemented by large language models. Treatment families receive 3–5 researcher-designed, illustrated conversation prompts ("Chatty") per week via text, plus access to an on-demand AI chatbot ("Chatty-AI") that generates personalized, dynamic prompts based on the child's interests. The six-month intervention aims to increase back-and-forth, open-ended parent-child conversation. The business-as-usual control group receives no text-based program, only study-administration texts (e.g., opt-out procedures and survey reminders).
Intervention Start Date
2026-11-02
Intervention End Date
2027-04-30

Primary Outcomes

Primary Outcomes (end points)
Children's receptive vocabulary, measured by the Peabody Picture Vocabulary Test (PPVT-5).
Primary Outcomes (explanation)
PPVT-5 administered in person, 1:1, in a classroom setting during school hours (~10–12 min), in English or Spanish depending on the child's primary language, at baseline and endline. The PPVT is the pre-registered primary outcome for all power calculations and confirmatory hypothesis tests.

Secondary Outcomes

Secondary Outcomes (end points)
Children's listening comprehension (Woodcock-Johnson IV listening comprehension composite). Exploratory: children's expressive language skill and curiosity; parents' beliefs (growth mindset, agency, relational closeness); parental program engagement (text-back frequency).
Secondary Outcomes (explanation)
WJ-IV composite (oral comprehension + understanding directions subscales), ~5–10 min, at baseline and endline in English or Spanish. Expressive language via picture description task (validated in pilot study that preceded this RCT). Curiosity via a brief game-like digital assessment (Jirout & Klahr, 2012 framework; Rury et al., 2025). Parent beliefs via pre/post surveys. Engagement tracked via text-back frequency to prompts.

Experimental Design

Experimental Design
Families are randomly assigned 1:1 to the Chat2Learn-AI treatment or a business-as-usual control condition. Outcomes are assessed via direct child assessments and parent surveys at baseline and endline.
Experimental Design Details
Not available
Randomization Method
Randomization done in office by a computer.
Randomization Unit
Individual randomization.
Was the treatment clustered?
No

Experiment Characteristics

Sample size: planned number of clusters
N/A
Sample size: planned number of observations
1000 families
Sample size (or number of clusters) by treatment arms
500 control, 500 treatment (C2L-AI)
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Using PowerUP! (α=0.05, two-tailed; power=0.80; R²=0.45 from baseline covariates), a sample of N=800 with complete outcome data yields a minimum detectable effect size of 0.147 SD on the primary outcome (PPVT-5). The maximum randomized sample is N=1,000 (500 treatment, 500 control), assuming ~80% with outcome data after attrition.
Supporting Documents and Materials
IRB

Institutional Review Boards (IRBs)

IRB Name
Social and Behavioral Sciences Institutional Review Board
IRB Approval Date
2026-07-08
IRB Approval Number
IRB25-0708
Analysis Plan