Clinician perceptions of Socrates 2.0: A multi-agent artificial intelligence tool to facilitate Socratic dialogue
Open accessAbstract
Cognitive behavioral therapies (CBTs) are effective for various mental health disorders. Socratic dialogue, which helps patients examine and challenge maladaptive beliefs, is a key component of CBTs. Despite their effectiveness, CBTs often face challenges with low homework completion. Digital mental health tools that use generative artificial intelligence (AI), and specifically large language models, may enhance patients’ homework experience by engaging them in interactive Socratic dialogue. This feasibility study explored clinicians’ perceptions of Socrates 2.0, which employs a multi-agent AI approach combining an AI therapist, AI supervisor, and AI external rater. The tool was developed to engage users in Socratic dialogue to help them identify, evaluate, and potentially reframe maladaptive beliefs outside of therapy sessions, and thus reinforce skills, such as cognitive restructuring. A total of nine clinicians with at least a master’s degree were given two weeks of unlimited access to Socrates 2.0 and participated in semi-structured interviews. Transcripts were analyzed thematically. Positive themes included surprise at the tool’s sophistication, its potential as a therapy supplement, empowerment of patients, accessibility, and improved perceptions of AI in mental health care. Negative themes included concerns about repetitive questioning, potential replacement of therapists, limitations in crisis situations, and technology literacy barriers. Clinicians also desired empirical evidence of effectiveness and clarity on data privacy. Overall, clinicians recognized the potential of Socrates 2.0 to enhance CBT but emphasized the importance of careful integration and addressing identified concerns.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Clinicians rated Socrates 2.0 as generally acceptable and feasible and saw potential for supplementing therapy, particularly for out-of-session cognitive reappraisal exercises.
“Clinicians rated Socrates 2.0 as generally acceptable and feasible and saw potential for supplementing therapy, particularly for out-of-session cognitive reappraisal exercises.”
From AI-Facilitated Cognitive Reappraisal via Socrates 2.0: Mixed Methods Feasibility Study. (2025) · cites this paper as [14]
Cites
A cognitive model of posttraumatic stress disorder
Ehlers, A., & Clark, D. M. (2000) · Behaviour Research and Therapy · doi:10.1016/s0005-7967(99)00123-0 · Cited by 6,147 · see citing works
The Efficacy of Cognitive Behavioral Therapy: A Review of Meta-analyses
Hofmann, S. G., Asnaani, A., Vonk, I. J. J., Sawyer, A. T., & Fang, A. (2012) · Cognitive Therapy and Research · doi:10.1007/s10608-012-9476-1 · Cited by 3,445 · see citing works
Cognitive Therapy in Depression
Kovács, M. (1980) · Journal of the American Academy of Psychoanalysis · doi:10.1521/jaap.1.1980.8.1.127 · Cited by 3,422 · see citing works
Psychometric assessment of three newly developed implementation outcome measures
Weiner, B. J., Lewis, C. C., Stanick, C., Powell, B. J., Dorsey, C. N., Clary, A. S., Boynton, M. H., & Halko, H. (2017) · Implementation Science · doi:10.1186/s13012-017-0635-3 · Cited by 2,819 · see citing works
Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017) · JMIR Mental Health · doi:10.2196/mental.7785 · Cited by 2,730 · see citing works
Psychotherapy relationships that work III.
Norcross, J. C., & Lambert, M. J. (2018) · Psychotherapy · doi:10.1037/pst0000193 · Cited by 578 · see citing works
Perceptions and opinions of patients about mental health chatbots: scoping review
Abd-Alrazaq, A. A., Alajlani, M., Ali, N., Denecke, K., Bewick, B. M., & Househ, M. (2021) · Journal of Medical Internet Research · doi:10.2196/17828 · Cited by 301 · see citing works
Kazantzis, N., Whittington, C., Zelencich, L., Kyrios, M., Norton, P. J., & Hofmann, S. G. (2016) · Behavior Therapy · doi:10.1016/j.beth.2016.05.002 · Cited by 280 · see citing works
Recommendations for the ethical use and design of artificial intelligent care providers
Luxton, D. D. (2014) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2014.06.004 · Cited by 243 · see citing works
Older adults can use technology: why healthcare professionals must overcome ageism in digital health
Mace, R. A., Mattos, M. K., & Vranceanu, A. (2022) · Translational Behavioral Medicine · doi:10.1093/tbm/ibac070 · Cited by 232 · see citing works
The Wiley Handbook of Cognitive Behavioral Therapy
(2013) · Wiley eBooks · doi:10.1002/9781118528563 · Cited by 144 · see citing works
Clarke, J., Proudfoot, J., Birch, M.-R., Whitton, A. E., Parker, G., Manicavasagar, V., Harrison, V., Christensen, H., & Hadzi-Pavlovic, D. (2014) · BMC Psychiatry · doi:10.1186/s12888-014-0272-1 · Cited by 138 · see citing works
Can AI replace psychotherapists? Exploring the future of mental health care
Zhang, Z., & Wang, J. (2024) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2024.1444382 · Cited by 112 · see citing works
Generative artificial intelligence in mental health care: potential benefits and current challenges
Torous, J., & Blease, C. (2024) · World Psychiatry · doi:10.1002/wps.21148 · Cited by 90 · see citing works
Graham, A. K., Weissman, R. S., & Mohr, D. C. (2021) · JAMA Health Forum · doi:10.1001/jamahealthforum.2021.1149 · Cited by 63 · see citing works
Conklin, L. R., & Strunk, D. R. (2015) · Behaviour Research and Therapy · doi:10.1016/j.brat.2015.06.011 · Cited by 59 · see citing works
Bunyi, J., Ringland, K. E., & Schueller, S. M. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.742196 · Cited by 57 · see citing works
The Challenges in Designing a Prevention Chatbot for Eating Disorders: Observational Study
Chan, W. W., Fitzsimmons‐Craft, E. E., Smith, A. C., Firebaugh, M., Fowler, L. A., DePietro, B., Topooco, N., Wilfley, D. E., Taylor, C. B., & Jacobson, N. C. (2022) · JMIR Formative Research · doi:10.2196/28003 · Cited by 51 · see citing works
Conceptualizing Patient Barriers to Nonadherence with Homework Assignments
Kazantzis, N., & Shinkfield, G. (2007) · Cognitive and Behavioral Practice · doi:10.1016/j.cbpra.2006.08.003 · Cited by 44 · see citing works
Advances in PTSD Treatment Delivery: the Role of Digital Technology in PTSD Treatment
Kuhn, E., & Owen, J. E. (2020) · Current Treatment Options in Psychiatry · doi:10.1007/s40501-020-00207-x · Cited by 34 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
AI-Facilitated Cognitive Reappraisal via Socrates 2.0: Mixed Methods Feasibility Study.
Held, P., Pridgen, S. A., Szoke, D. R., Chen, Y., Akhtar, Z., & Amin, D. (2025) · JMIR Mental Health · doi:10.2196/80461 · Cited by 7 · see citing works
“Clinicians remarked that the AI interface could make conventional CBT homework feel more approachable and interactive [14], but data from end users (eg, patients) are needed.”
InfluentialSelf-citationRidings, L. E., Held, P., Kuhn, E. R., & Stirman, S. W. (2026) · Journal of Traumatic Stress · doi:10.1002/jts.70092 · Cited by 1 · see citing works
“…including the delivery of psychoeducation (Yilanli et al., 2024), behavior and emotion identification (Chen et al., 2022; Shah et al., 2022; Tanana et al., 2021), mental health risk detection (Bantilan et al., 2021), and the delivery of specific therapeutic components (Held et al., 2025a).”
Held, P., Smith, D. L., Pridgen, S., Hutzler, I., & Szoke, D. R. (2026) · doi:10.2196/preprints.108739
- Authors
- Held, P., Pridgen, S. A., Szoke, D. R., Chen, Y., Akhtar, Z., & Amin, D.
- Affiliations
- Rush University Medical Center (US)
- Corresponding author
- Held, Philip
- Venue
- Cognitive and Behavioral Practice
- Publisher
- Elsevier BV
- Published
- 2025-10
- ISSN
- 1077-7229 (ISSN-L)
- OpenAlex
- W4415012514
- Cited by
- 2
- References
- 20
- Citations by year
- 2026: 2
- FWCI
- 1.62
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Cognitive and Behavioral Practice (publishedVersion, cc-by-nc-nd)
- Funders
- Crown Family Philanthropies
- U.S. Department of Defense (W81XWH-22-1-0739, HT9425-24-1-0666, HT9425-24-1-0637)
- Topics
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Social Sciences › Psychology › Clinical Psychology › Psychotherapy Techniques and Applications
- Keywords
- Socratic dialogue, large language models, cognitive behavioral therapy, homework completion, cognitive restructuring, maladaptive beliefs, clinician perceptions, digital mental health tools, generative AI, technological literacy, data privacy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
