Agentic education · Learning science

Actionable companion · Feedback & scaffolding

Learning with agency: Use of a Conversational Agent for Training Mental Health Professionals in Suicide Safety Planning: Pilot Feasibility and Acceptability Study

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Higher education. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Abstract Background Safety planning is recognized as one of the most effective interventions for reducing suicidal behaviors. The quality of safety plans strongly depends on professional training, and traditional methods, such as role-playing, are time-consuming and offer limited opportunities for repetition across diverse patient profiles. Generative artificial intelligence (GenAI) may provide innovative solutions by offering accessible, flexible, and realistic training environments. Objective This pilot study aimed to evaluate the acceptability and feasibility of a GenAI-based simulator designed to train mental health professionals in safety planning. Methods Twenty nurses and nursing assistants from psychiatric units in a French university hospital participated in a pre-post, single-session evaluation. After self-rating their ability, competence, and willingness to manage patients experiencing suicidal ideation, participants interacted individually with the text-based simulator for 20 minutes to perform a safety plan with a chatbot, then completed postsimulation acceptability items, and open-ended feedback. Composite scores were computed: acceptability (eg, helpfulness; 0‐40), realism (eg, looking like real interaction with patient; 0‐20), and challenge (eg, emotional challenge; 0‐30). Pre-post changes were tested (Wilcoxon signed-rank test), and age-group comparisons were performed. Results Acceptability was high (mean 31.9/40, SD 5.3; median 32, IQR 7), realism moderate-to-high (mean 15.1/20, SD 4.1; median 15, IQR 5.25), and challenge manageable (mean 17.0/30, SD 8; median 18, IQR 12.5). Participants rated usefulness (mean 7.65/10, SD 1.57; median 8, IQR 1.57), perceived learning (mean 7.6/10, SD 1.79; median 8, IQR 2), recommendation to use the chatbot for training (mean 8.3/10, SD 1.59; median 9, IQR 2.25), and feedback quality (mean 8.35/10, SD 1.27; median 8.5, IQR 1.25) favorably. Willingness to actively manage patients experiencing suicidal ideation significantly increased postsimulation (P=.03). Younger participants reported higher acceptability (P=.04) and realism (P=.03). Participants reported minimal concerns regarding the simulator’s use. Conclusions This pilot study demonstrates that a GenAI-based simulator for safety planning is feasible and highly acceptable among experienced mental health professionals. The findings are promising and warrant larger, controlled trials to assess impacts on training effectiveness and patient outcomes.

What kind of evidence is this?

Conversational & pedagogical agents · Comparative / pre-post study reported

Stage: Higher education. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

Twenty health care professionals were recruited for this study, including nurses and nursing assistants working in the psychiatric units of the University Hospital of Montpellier (CHU Lapeyronie, France). Participants were working in one of the following services: (1) 19-bed acute care unit specialized in the management of patients experiencing suicidal ideation, (2) 21-bed inpatient unit specialized in the management of patients with mood disorders, or (3) outpatient team providing short-term and close follow-up care for patients experiencing suicidal ideation discharged from the emergency unit. Participants were nurses and nursing assistants, as these professionals are primarily responsible for conducting safety planning in the participating units. No formal inclusion or exclusion criteria were applied beyond working in these units and regularly performing safety plans, and all eligible volunteers were included. Although this study focused on these professionals, the simulator is designed to be applicable to a broader range of health care providers involved in suicide prevention.

Limitations and uncertainty · source passage

Different types of training exist, but one of the most commonly used approaches combines theoretical instruction with role-playing exercises (ie, the trainee acts as the provider, while the trainer takes the role of the patient). A major limitation of this method is the amount of time it requires. Role-playing exercises cannot last very long due to the trainer’s limited availability, and the number of times these exercises can be repeated with trainees is therefore restricted. However, the greater the number of practice repetitions—particularly when involving a wide variety of patient profiles—the more skilled and confident the professional becomes in developing safety plans, regardless of the type of patient encountered. It is therefore necessary to find more efficient ways to train mental health professionals in safety planning. In the era of generative artificial intelligence (GenAI), this technology may be particularly useful for such training purposes. Indeed, growing evidence has demonstrated the potential benefits of GenAI in the field of mental health care, as well as in the domain of suicidal behaviors [12-17]. More specifically, GenAI can be used for the training of health care professionals. For example, in a recent study, a GenAI-based simulator was created to train mental health professionals in the assessment of suicidal ideation and showed promising results [16].

Design the system before the pilot

Define whether the agent asks questions, gives hints, explains or assesses. Test hallucinated feedback, excessive praise, misleading confidence and responses when the learner is confused. A conversational interface alone does not establish autonomous agency.

  • Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
  • Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.
  • Co-design accommodations with learners and specialists. Check access and error burden across groups without inferring subgroup effectiveness from small or unreported samples.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Choose one disciplinary task. Require a first attempt, a documented AI consultation, a critique of the output and an independent explanation. Align the comparison group and scoring rubric with the same objective. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Blind-score reasoning and accuracy on a new task without AI. Distinguish model examination scores, student perceptions and actual learner gains; only the last directly tests educational benefit. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Bénédicte Nobile; Zohar Elyoseph; Elia Gourguechonbuot; Josselin Guyodo; Jordi Garcia; Inbar Levkovich; Emilie Olie; Yuval Haber; Yossi Levi-Belz; Philippe Courtet. Use of a Conversational Agent for Training Mental Health Professionals in Suicide Safety Planning: Pilot Feasibility and Acceptability Study. JMIR Mental Health (2026-06-30). https://doi.org/10.2196/88440

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.