From Needs Assessment to Pre-Trial Specification: Participatory Co-Design of a Generative AI Chatbot (CARES-MDD) for Persons Living with Depression in Hong Kong Psychiatric Care

1. Introduction

Major Depressive Disorder (MDD) is a leading cause of disability worldwide [1], accounting for substantial disease burden, diminished functional capacity, and elevated suicide risk [2,3]. While empirically validated psychological interventions, most notably Cognitive Behavioral Therapy (CBT),are recommended as first-line treatments, fewer than half of affected individuals receive adequate care [4,5].

Digital mental-health interventions (DHIs) may increase access to information and self-management support; however, sustained engagement, cultural relevance, and integration with routine psychiatric care remain important challenges [6,7]. Critically, the overwhelming majority of mental health DHIs are developed without participatory input from clinical populations, producing tools that feel generic, robotic, and emotionally misaligned for individuals contending with severe depressive symptoms [8,9].

The emergence of Generative Artificial Intelligence(AI) and Large Language Models (LLMs) offers an opportunity to bridge this gap. Unlike rigid, rule-based algorithms, L LLMs can generate responsive language that may be perceived as empathic or validating; however, such outputs are not equivalent to human understanding or clinician-delivered therapy and require empirical safety and efficacy evaluation [10,11,12]. When integrated with evidence-based psychotherapeutic frameworks—specifically CBT, which targets transdiagnostic cognitive and behavioral maintaining mechanisms (e.g., cognitive distortions, avoidance, and rumination; [13,14])—generative conversational agents can deliver flexible, tailored micro-interventions in real time.

However, translating generative AI into a psychiatric adjunct treatment tool requires tuning, localized adaptation, and safety governance .This formative mixed-methods study aimed to identify user-defined requirements, stakeholder-identified failure modes, and governance conditions for the development of Conversational Artificial-intelligence for REducing Symptoms and REmission for Major Depressive Disorder (CARES-MDD), which is a Hong Kong Cantonese AI-supported conversational agent for persons living with depression. The study was designed to inform a pre-specified, staged validation programme for CARES-MDD, including content curation, technical evaluation, safety assurance, and prospective feasibility testing before efficacy trial. Specifically, the study sought to: (1) characterise digital behaviour, generic AI-chatbot use, barriers to emotional disclosure, and desired chatbot features among people attending psychiatric outpatient services; (2) translate these findings, together with feedback from lived-experience experts and clinical professionals, into prioritised AI chatbot design recommendations; and (3) describe stakeholder perceptions of perceived usefulness, acceptability using consensus rubrics and qualitative interviews to collect their positive and negative points when testing CARES-MDD.

2. Materials and Methods

2.1. Study Design

This study employed a mixed-methods, participatory co-design framework, drawing upon established guidelines for DHIs [15,16,17]. Recognizing that the target demographic has important experience and opinions of generative-AI, the investigation was structured into two interrelated phases:

Phase 1 (Needs Assessment): A cross-sectional quantitative and qualitative survey investigating baseline digital habits, help-seeking attitudes, self-stigma, and conversational AI acceptability/ needs among a clinical cohort. Phase 2 (Participatory Co-Design and Test-run Evaluation): A stakeholder co-design/ feedback phase involved adult Lived Experience Experts (LEEs) advisers and multidisciplinary clinical professionals. Phase 1 findings were used to identify candidate design priorities, including privacy and discretion, use pattern, low-burden access and barriers reported. Phase 2 included a workshop of LEEs to integrate the prioritized implementation ideas to co-design the generative AI-chatbot (CARES-MDD), then invited them for test-run CARES-MDD to evaluate its acceptability, perceived usefulness and perceived safety in mixed-methods evaluation, for its potential for progression to a randomized-controlled trial (RCT) design.

2.2. Participants and Recruitment Settings

Phase 1 Cohort. A clinical cohort of 511 outpatient psychiatric attendees was recruited from Child and Adolescent Psychiatric Outpatient Clinics at Queen Mary Hospital Service attending between July 22 and August 21, 2025. Eligible participants possessed a personal smartphone with daily internet access, and demonstrated the ability to read written Chinese and communicate in Cantonese.

Phase 2 Reference Group. The Phase 2 participatory co-design involved the interview of 18 experts, comprising of 10 LEEs, alongside a multidisciplinary expert group of 8 clinical professionals (2 clinical psychologists, three counsellors, 1 psychiatrist, and 2 psychiatric nurses). LEEs had a confirmed clinical diagnosis of Major Depressive Disorder (MDD) based on the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-V) [18], ascertained by case psychiatrists. The LEEs were all aged 18 years or above, restricting the reference group to legal adults was intended to ensure that participants had the developmental maturity to discuss lived experiences of depression, emotional disclosure, and digital mental health support in an interview setting. Exclusion criteria included acute suicidal risk, active psychosis, or concurrent substance use disorders. While the LEEs guided the humanistic and user-experience elements, the clinical experts provided feedback of the content, and appropriateness of the interaction. Furthermore, the expert panel provided opinions on the safety features in practical use.

2.3. Phase 1: Needs Assessment Measures and Data Collection

An electronic questionnaire was developed to capture quantitative metrics and qualitative insights across four primary domains:

Online behavior and AI chatbot use: Their daily digital screen time, generic conversational AI adoption rates, daily online interaction duration, and digital engagement frequency were asked. Depressive symptom severity was assessed using the validated Chinese version of the 9-item Patient Health Questionnaire (PHQ-9) as clinical variable [19].

Help-Seeking and Self-Stigma: Standardized psychometric instruments measured help-seeking behaviors (Help-Seeking Scale, max score 28) and internalized mental health stigma (Self-Stigma Scale, max score 24, where higher scores denote lower stigma), from the Knowledge and Attitudes to Mental Health Scales (KAMHS) [20] which was recently validated in Hong Kong [21].

Barriers to emotional disclosure and help-seeking within existing psychiatric care networks: Participants also completed an open-ended item asking, “What are the reasons that prevent you from sharing emotional difficulties with others?”

Desired AI Chatbot Specifications: To guide the system architecture and feature prioritization, a final open-ended item asked, “What is the most desired feature of an AI chatbot within the existing psychiatric system?”

2.4. Phase 2: Co-Design Workshop, Beta-Runs, and Mixed-Methods Evaluation

To translate the needs assessment findings into actionable AI chatbot development, a participatory co-design workshop was conducted with Lived Experience Experts (LEEs). The engagement protocol was grounded in established Youth Participatory Action Research (YPAR) principles [22] and guidelines for co-designing digital health interventions with young people [23], which used non-medicalized language, culturally relevant humor, and open body language (e.g., maintaining eye-level seating) to actively cultivate trust and rapport. Active listening techniques, such as reflective summarizing and open-ended prompting, were utilized to verify shared understandings, clarify conceptual misinterpretations, and empower LEEs to expand upon their ideas on the prioritization of the AI chatbot theme. This collaborative process directly informed the prioritized implementation strategies for the Conversational Artificial-intelligence for REducing Symptoms and REmission for Major Depressive Disorder (CARES-MDD) intervention (detailed in Appendix A2), bridging the gap between clinical utility and user-centered design.

Following the initial co-design workshops, the expert group was invited for multiple test-run cycles conducted over a development window. The expert reference group attended several supervised, in-person test-runs throughout this period to report any good and bad points about the CARES-MDD. At the conclusion of this iterative cycle, participants completed an evaluative rubric encompassing seven core therapeutic domains, which were generated directly from the prioritized co-design strategies (Appendix A2). Participants rated these domains on a 10-point visual analog scale (1 = completely inadequate, 10 = exceptional), as shown in Table 1.

2.4.1. Description of the CARES-MDD Chatbot

The CARES-MDD application is a text-based, multi-threaded chatbot application developed using a large language model and designed to communicate in natural Hong Kong-style Cantonese. Its conversational content was developed by psychiatrists and clinical psychologists and reviewed by members of the clinical team with reference to evidence-informed, primarily CBT principles. To address clinical safety, CARES-MDD has a keyword-based crisis-signposting module screening for high-risk crisis triggers (e.g., ‘suicidal’, ‘death’, ‘giving up’). Detection of these triggers initiates an automated safety interface,’ temporarily suspends the generation of routine chatbot content, and displaying a static emergency interface with 24/7 direct-dial crisis hotlines. The research team also conducted periodic clinical review of chatbot content and system responses to identify potential safety concerns on a weekly basis. CARES-MDD was designed to support compliance with applicable data-protection requirements. Appropriate measures were implemented to protect participant information and restrict access to study data to authorized members of the research team. It was not intended to diagnose MDD, provide emergency care, replace professional assessment, or autonomously manage suicidal risk. The CARES-MDD system identity, intended use, and technical configuration, together with its safety-screening and crisis-response pathway, are summarised in Appendix Table A1 and Table A3.

2.5. Analysis

We used descriptive statistics and inferential tests to examine closed-ended questions regarding participants’ digital behaviors, help-seeking patterns, and the evaluation rubrics. Quantitative analyses were conducted using Excel and R statistical software (version 4.3.0; R Foundation for Statistical Computing, Vienna, Austria). Between-group comparisons of continuous outcomes Welch’s unequal variances t-tests according to distributional and variance considerations. Continuous variables, including digital engagement durations, psychometric clinical baselines (e.g., PHQ-9) and usability metrics (SUS, WAI-SR), were summarized as means and standard deviations (SD). Categorical variables, such as generic AI adoption rates and interaction frequencies, were reported as frequencies and percentages.

For qualitative data derived from phase 1, short-text responses were coded to categorize non-mutually exclusive recurring themes (e.g., privacy concerns, fear of judgment). To provide cultural context, frequently occurring Chinese terms within these responses were mapped and visualized using word clouds. The qualitative feedback of phase 2 as conducted in an inductive, data-driven iterative process [24]. Due to limitations within the data set (short phrases or sentence fragments), full thematic analysis was not appropriate [25]. Transcripts were read by M.S.Y.Y. and K.Y.H.L. to familiarize themselves with the responses. Next, two coders (M.S.Y.Y. and K.Y.H.L.) undertook the content analysis, generating codes directly from the data rather than from a pre-existing coding framework. Brief descriptive labels (“codes”) were applied to transcript segments, and multiple codes were applied if participants’ narratives presented multiple meanings. Following this, M.S.Y.Y. and K.Y.H.L. met to discuss these coding decisions—specifically conducting inter-rater reliability checks on approximately 30% of the transcripts—and revisions and refinements of the codes were undertaken via negotiated agreement. Following this process, first-order codes (“categories”) were grouped bottom-up into second-order themes based on commonality of meaning. M.S.Y.Y. and K.Y.H.L. then convened to review and refine the final themes.

2.6. Ethical Approvals and Consent Procedures

The assessment received institutional review board approval from the Institutional Review Board of The University of Hong Kong/Hospital Authority Hong Kong West Cluster (UW25-299). Informed consent was obtained from adult participants and their parents (for minors) prior to engagement. Participant confidentiality was secured by decoupling contact information from survey data and assigning de-identified alphanumeric study IDs.

3. Results

3.1. Phase 1 Results: Clinical Needs Assesssment for Barriers and AI Chatbot Usse

The cohort comprised 511 young people (mean age 14.97 ± 1.86 years; 54.0% female, 46.0% male). Analysis of online behavior revealed a significant divergence based on psychological distress levels. Participants recorded a significantly high digital footprint, spending an average of 296.3 minutes per day online. Nearly 2 out of 3 young people (66.2%) are already familiar with and navigating generic AI chatbot, implying the clinical population is already primed for conversational agents. While adoption is high, frequency data highlights a critical gap: 56.4% of active users have only had sporadic, surface-level interactions (fewer than 10 conversations total). This suggests that while young people are curious about AI chatbot, current generic AI chatbot tools are not providing the sustained, meaningful engagement required for psychological intervention for the clinical demographic (Table 2).

Of the 511 participants, 65 (12.7%) provided additional comments in response to the question, “What are the reasons that prevent you from sharing emotional difficulties with others?” Comments were generally brief, comprising a phrase or one to two sentences (total word count = 834). Iterative thematic analysis identified Privacy concerns (n = 22), characterising emotional disclosure as “privacy” or a “personal matter” and expressing concern that their concerns can be gossiped to others; Fear of judgement (n = 16) encompassed anticipated misunderstanding, criticism, stigma, or negative evaluation, as reflected in comments such as “other people’s views and prejudices” and “afraid of being misunderstood”); and Avoidance of burdening others (n = 8) captured concerns that disclosure might negatively affect or inconvenience others, illustrated by “do not want to affect other people’s mood” and “do not want to disturb others”. These are visualised in word cloud in Figure 1.

42 (8.2%) provided additional open-ended comments in response to the question, “What is the most desired feature of an AI chatbot within the existing psychiatric system?” Comments were generally brief, comprising short phrases or single sentences (total word count = 586). Iterative thematic analysis identified four non-mutually exclusive desired features. The most common theme was 24/7 immediate accessibility ($n=18$), with participants valuing on-demand emotional support between formal clinical appointments (e.g., “always available” and “immediate reply when I cannot sleep”). Privacy and non-judgmental space ($n=12$) reflected the preference to share vulnerable emotions without fear of human evaluation, characterized by comments like “no human judgment” and “completely confidential”. Localized empathy ($n=8$) captured the desire for naturalistic, Hong Kong-style Cantonese interactions that feel culturally resonant rather than robotic (e.g., “sounds like a local friend”). Finally, practical psychological guidance ($n=4$) referred to the need for actionable coping strategies, exemplified by “helps me reframe my negative thoughts”. These are visualised in word cloud in Figure 2.

3.2. Phase 2 Results: Co-participatory Design and Expert Evaluation

Following the Phase 1 needs assessment, 10 LEEs (mean age 22.9 ± 2.9 years; 50% female, 50% male) and 8 clinical experts were invited for the initial workshop for co-design (appendix A2). They were then invited to test run for the acceptability, perceived safety, and feasibility of progression to definitive trial of CARES-MDD. Only the LEEs had the pre- and post-observations adapting the outcome assessors. Quantitative rubric scores across the seven evaluative domains are summarised in Figure 3.

Participants provided generally favourable ratings across all CARES-MDD evaluation domains. Empathy and HK-Cantonese understanding, Accuracy and useful CBT info, and Balance of privacy and clinical governance achieved the highest median scores, reflecting strong acceptability of the chatbot’s culturally resonant communication, perceived usefulness and acceptability, and value clinician oversight. Acceptability of RCT methodology also demonstrated robust feasibility. Conversely, Safety features and adverse digital events alongside Active listening and Socratic questions showed wide interquartile ranges, indicating polarized experiences; some valued these features, while others found automated overrides abrupt and socratic questioning could be demanding during distress. Finally, Supportive pacing and intervention duration yielded the lowest median score, capturing challenges foreseeable if it is positioned as an open-ended, indefinite intervention. The descriptive observations of the CARES-MDD test-run were summaraised in Table A4. Additionally, Table 3 thematically organizes the qualitative feedback underlying these quantitative evaluations.

Among positive experiences, LEEs valued CARES-MDD as a private “tree hole” for emotional disclosure and perceived it as more private than commercial applications, because it was not perceived to use disclosed content for targeted advertising which would pass the information to vendors. The use of natural Hong Kong-style Cantonese was viewed as familiar, emotionally accessible, and appropriate to local expressions. CBT-informed content was generally regarded as clinically appropriate and distinguishable from generic emotional support, particularly when interactions progressed beyond brief exchanges (approximately five conversational turns). To ensure privacy, participants advocated for using pseudonyms to prevent data misattribution. However, they simultaneously supported backend clinician oversight, noting that human supervision of their conversations provided necessary reassurance against potential AI unreliability. Rather than limitations, their sharing of negative experience establish parameters for future trial methodology. Specifically, the cognitive demands of a text-based modality indicate that the intervention is optimally targeted toward a specific demographic: namely, younger, digitally native populations with a higher baseline tolerance for typing. Furthermore, the eventual onset of digital fatigue suggests that CARES-MDD is most viable as a time-limited intervention instead of an open-ended, indefinite intervention. Technologically, the LMM occasionally exhibited inconsistent longitudinal memory, failing to seamlessly recall contextual details from very early sessions, a stark contrast to human psychotherapist. Automated safety overrides were sometimes perceived as abrupt, particularly when triggered by non-suicidal colloquial exclamations such as “死啦” (“oh no”). Some participants expressed residual concern about possible AI hallucinations, despite not reporting such experiences during the study.

4. Discussion

This study reported a mixed-methods study: first, to characterize the online digital behavior, usage of generic AI chatbots for emotional concerns, its barriers, and needs assessment of a desired AI mental health chatbot specifications; second, to co-design and evaluate the iterative test-run of the CARES-MDD among experts living with MDD. By bridging a clinical needs assessment data (Phase 1), we identified (1) barriers of self- stigma and fear of human judgement for sharing emotional concerns in add-on support within existing psychiatric care framework; (2) high technological readiness with generic AI chatbot for emotional concerns ; and (3) the desired features for development of an AI mental health chatbot for this specific clinical demographic. Phase 2 reported an iterative expert co-design process of CARES-MDD involving LEEs and a clinical expert reference group. They prioritized and shared positive experience regarding CARES-MDD’s features of local style communication, CBT-curated RAG instead of generic content, and the balance of privacy and safety monitoring. Rather than limitations, their sharing of negative experience regarding LMM-related risks and intervention pacing highlight key areas requiring reference parameters for future trial methodology.

The Phase 1 data shows that conventional, human-delivered support systems are often hindered by the target demographic’s high self-stigma and fear of judgment. Even among this vulnerable cohort already attending psychiatric outpatient clinics, qualitative themes highlighted concerns about sharing emotions for support regarding anticipated negative evaluation, and a reluctance to burden others [26]. These barriers may reduce willingness to seek help even when clinical need is present, particularly when the clinical population fear that their emotional disclosures will be misunderstood, shared beyond their control, or impose on others.[27,28]. An AI chatbot has the potential as add-on micro-intervention to foreground immediate accessibility without burdening people around, employing a conversational register that approximates support interaction rather than formal assessments.

It was further supported by the findings that most outpatient attendees had high technological readiness, with widespread surface acquaintance with AI chatbots. Users who have interacted briefly with commercial chatbots may hold implicit expectations derived from those platforms (rapid factual responses, task completion, minimal affect) that are poorly matched to the longitudinal, reflective, emotionally containing functions that a therapeutic chatbot must serve [24]. The desired features identified by participants were closely aligned with these barriers. Participants valued immediate availability, a private and non-judgemental conversational space, natural local style communication, and practical psychological guidance. These findings support the need and the essential features of developing an adjunctive AI chatbot (CARES-MDD) that would not shara data to vendors, accessible between appointments, and culturally congruent. The co-design process similarly underscored participants emphasised the importance of conversational tone, appropriate emotional validation, and a style that feels natural rather than formal or clinical.

The Phase 2 evaluation indicated generally favourable perceptions across the seven consensed CARES-MDD domains. Empathy and local style understanding, the accuracy and usefulness of CBT-informed content, and balance of privacy and safety received the highest ratings. Participants valued CARES-MDD as a private “tree hole” for emotional disclosure and perceived it as distinct from commercial applications because it was not seen as using personal content for advertising or commercial targeting. The preference for unique identifiers or pseudonyms further illustrates the importance of maintaining confidence that individual disclosures will not be confused with those of another user. Participants appreciated that CARES-MDD responded in colloquial Cantonese rather than formal written Chinese, and several noted that this linguistic calibration created a sense of relational proximity uncommon in health-technology products [29,30].

Participants did not frame privacy as the absence of clinical oversight. Rather, they supported proportionate human oversight when data governance arrangements were transparent and sensitive personal details were protected. This finding is important for the design of clinically oriented conversational AI: trust may depend on clearly communicating what is monitored, who can access information, what will be documented, and the circumstances under which confidentiality may be overridden because of safety concerns.

CBT-informed content was perceived as more useful than generic reassurance when interactions progressed beyond short exchanges. Participants and experts considered the chatbot more helpful when it could validate distress, clarify the immediate concern, and only subsequently introduce structured reflection or cognitive restructuring. This supports a staged conversational design: initial empathic listening and emotional validation should precede problem-solving or Socratic questioning. The interactions were perceived as more useful after several active exchanges, particularly when a session involved at least five conversational turns. This observation addresses a methodological challenge in DHI research: operationalizing intervention “dosage” outside of traditional psychiatric frameworks. Unlike conventional psychotherapy, which relies on structured 50-minute appointments, unguided digital tools face tremendous variability in user engagement duration. Because meta-analyses indicate that an effective clinical dosage for digital interventions ranges from 30 to 60 minutes per week [31], future RCTs can formally define an “active digital session” as a continuous interaction lasting approximately 10 minutes which estimates to comprise approximately minimum five reciprocal turns.

Several LEEs also reported that abrupt safety override responses, while appropriate from a risk-management standpoint, interrupted the conversational flow at moments when continued empathic engagement may have been more therapeutically productive. Clinical professionals specifically noted that while algorithmic safety gates are non-negotiable from a duty-of-care standpoint, their current implementation in generative AI systems typically operates as a binary interrupt — abruptly redirecting conversation to crisis resources — rather than as a graduated, therapeutically calibrated transition. In human clinical practice, the decision to escalate, contain, or stay present with distress is a moment-to-moment clinical judgement informed by relationship history, non-verbal cues, and dynamic risk appraisal.

A central question explored during the co-design interviews was how clinical users conceptualize the identity of CARES-MDD. Instead, users perceived CARES-MDD prototype as a portable, on-demand conversational support and skills-coaching tool during unassisted hours (e.g., late nights or between outpatient visits). Multiple LEEs affirmed their willingness to recommend CARES-MDD to peers who ‘aren’t ready for traditional therapy yet.’ By allowing distressed individuals to practice cognitive restructuring and emotional articulation in an unobserved, safe environment, the conversational agent serves as an accessible entry point that may lower psychological barriers and build readiness for future formal human psychiatric care.

The integration of generative AI into psychiatric populations raises broader ethical and clinical considerations for the field, particularly regarding unhealthy dependence, hallucination risks, and longitudinal memory constraints [32,33,34]. Their qualitative feedback highlighted a known vulnerability inherent to current LLMs [35]. LLM models unable to dynamically contextualise the psychotherapeutic clinical formulation of the engaging client unlike human therapist, they may be better served as a complementary tool for “augmenting” pre-existing therapist alliance with patients, rather than serving as the therapist alliance in standalone role [36]. In the era of entering into the AI, we should be more cautious in the role of AI chatbot in monitoring its possible safety issues and adverse digital events. Although the LEEs did not experience so, they mentioned the risk of AI hallucinations and psychosis that they overheard. The LLM risks identified in the process are summarized in the subsequent Table 4, aligning with the guideline for an AI chatbot architecture ready for future trials [37].

Participants’ comments regarding long-term engagement should be interpreted as design considerations for future evaluation rather than as evidence of an optimal intervention duration. Participants anticipated digital fatigue if CARES-MDD were available as an open-ended or indefinite intervention. In light of attrition commonly reported in unguided digital mental-health interventions, a time-limited, on-demand format may offer a pragmatic starting point for prospective feasibility testing. An approximately 8-week intervention window could allow participants sufficient opportunity to engage with CBT-informed self-management content while limiting prolonged exposure and the potential for overreliance on the conversational agent [40,41]. To mitigate digital fatigue issue, further RCT trial could integrate the ecological momentary assessment technique which has shown evidence on boosting adherence through self-monitoring and reminder effects [42,43].

Participants generally considered randomisation, including allocation to a psychoeducation-only active digital control, to be fair and acceptable. Future trial design should minimise participant burden, particularly for providing appropriate reimbursement, online modes for assessments; and include follow-up sufficient to examine engagement, acceptability, safety-related events, and longer-term outcomes. While this formative study provided evidence on the architectural feasibility, cultural acceptability, and safety governance boundaries of CARES-MDD, it was not designed to evaluate randomized clinical efficacy or comparative attrition. Therefore, rather than demonstrating clinical superiority, these findings provide the critical structural parameters, such as the minimum 5-turn intervention dosage, the system and clinical measures to counteract the potential LLM risks e.g., pre-consented clinical escalation pathways, required to safely initiate a definitive RCT.

4.1. Strengths, Limitations, and Future Clinical Directions

A strength of this investigation is its mixed-methods methodology, uniting a relatively large clinical sample (N = 511) with more in-depth mixed-method evaluation of LEEs throughout the development lifecycle, and CARES-MDD shows acceptable ecological and cultural validity. However, several limitations must be acknowledged. First, the pre-to-post observations from the uncontrolled beta-testing phase are strictly descriptive; they could not deduce therapeutic efficacy and further clinical trial is needed. Second, it was a convenience sample drawn from a single professional and community network, which limits the generalizability. Nevertheless, given the uncompensated time commitments required for these phases of co-development, leveraging a network with pre-established clinical rapport was essential to maintain experts and accurately capture user-driven needs within existing resource constraints. Third, CARES-MDD is fundamentally without highly experimental technological features. This design choice was driven by the co-design participants, who prioritized clinical reliability and evidence-based safety over technological novelty, which might lead to “blackbox” concerns. While this limits the platform’s technological boundary-pushing, it ensures the intervention maintains the rigorous clinical safety required for vulnerable psychiatric populations.

Future work in developments of generative-AI Chatbots for mental health purpose must prioritize three interrelated agendas to address the universal challenges. Technically, the field should move beyond on aligning global clinical guidelines and standardizing protocols for LLM applications across the disciplines [44,45]. Clinically, the next appropriate evaluative step involves prospective designs, such as full-scale RCTs, to systematically examine the clinical effectiveness. Digital adverse events should be continually assessed in future trials. Conceptually, the pronounced help-seeking barriers and high self-stigma identified in Phase 1 motivate a critical agenda for comparative research: investigating whether initial AI-mediated emotional disclosure can serve as a transitional bridge within a stepped-care pathway, lowering psychological barriers and facilitating subsequent engagement with human-delivered psychiatric care [46]. Addressing these universal challenges will be paramount for integrating generative AI as a safe, regulated, and continuously audited adjunct to global mental health services [12].

5. Conclusions

In conclusion, the needs assessment demonstrates that while the use of generic AI chatbots for emotional support is already prevalent among psychiatric outpatients in Hong Kong. Barriers—namely fear of judgment and burdening others—continue to impede traditional help-seeking behaviors within traditional psychiatric care system. This underscores the necessity that AI chatbots with specified features are needed for individuals living with MDD, even among those already engaged in psychiatric care. By utilizing a needs-driven participatory framework with LEEs, a CBT-grounded generative AI chatbot for MDD, has been co-developed, with mixed-methods findings supporting it is feasible to use end-users and clinical experts. The findings provide preliminary, clinically grounded design parameters and feasibility information for subsequent evaluation. A future trial should compare CARES-MDD plus usual care with an appropriate active digital control plus usual care, incorporate predefined safety and adverse-event monitoring, and evaluate engagement, long-term safety, and clinical outcomes. This mixed—methods study does not establish the efficacy, safety, or therapeutic equivalence of CARES-MDD; these questions require subsequent prospective controlled trials.