In this column, we delve into the intriguing world of AI personas designed to function as synthetic mental health therapists. This technological feat is made possible by the advancements in generative AI and large language models (LLMs). By simply crafting a detailed prompt, one can guide AI to mimic the role of a therapist. There are straightforward methods as well as more sophisticated approaches to achieve this. The choice between a basic version or a more nuanced, complex instantiation will significantly influence how the AI interacts in therapeutic settings.
The depth and sophistication of the simulated therapist you create will directly affect the quality of interactions and the utility of the AI persona. A popular application involves users engaging with AI-based therapists for mental health support. Additionally, these AI personas can serve as educational tools for aspiring therapists, offering insights into therapeutic techniques and their effectiveness. Researchers in psychology can also utilize AI personas for experimental studies on mental health methodologies. Moreover, these AI-driven therapists provide a novel avenue for foundational research into human cognition.
Let’s explore this topic further.
This examination of AI innovations is part of my ongoing coverage in Forbes, where I focus on unraveling the complexities of emerging AI technologies (further details available through the provided link). As a brief overview, my work covers the multifaceted development of AI applications in the domain of mental health, driven by rapid advancements in generative AI. The growing acceptance and application of these technologies underscore their transformative potential. For a comprehensive collection of my analyses and articles on this subject, links are available for further reading.
Let’s talk about it.
This analysis of AI breakthroughs is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here).
AI And Mental Health
As a quick background, I’ve been extensively covering and analyzing a myriad of facets regarding the advent of modern-era AI that produces mental health advice and performs AI-driven therapy. This rising use of AI has principally been spurred by the evolving advances and widespread adoption of generative AI. For an extensive listing of my well-over one hundred analyses and postings, see the link here and the link here.
There is little doubt that this is a rapidly developing field and that there are tremendous upsides to be had, but at the same time, regrettably, hidden risks and outright gotchas come into these endeavors, too. I frequently speak up about these pressing matters, including in an appearance on an episode of CBS’s 60 Minutes, see the link here.
Background On AI Personas
All the popular LLMs, such as ChatGPT, GPT-5, Claude, Gemini, Llama, Grok, CoPilot, and other major LLMs, contain a highly valuable piece of functionality known as AI personas. There has been a gradual and steady realization that AI personas are easy to invoke, they can be fun to use, they can be quite serious to use, and they offer immense educational utility.
Consider a viable and popular educational use for AI personas. A teacher might ask their students to tell ChatGPT to pretend to be President Abraham Lincoln. The AI will proceed to interact with each student as though they are directly conversing with Honest Abe.
How does the AI pull off this trickery?
The AI taps into the pattern-matching of data that occurred at initial setup and might have encompassed biographies of Lincoln, his writings, and any other materials about his storied life and times. ChatGPT and other LLMs can convincingly mimic what Lincoln might say, based on the patterns of his historical records.
If you ask AI to undertake a persona of someone for whom there was sparse data training at the setup stage, the persona is likely to be limited and unconvincing. You can augment the AI by providing additional data about the person, using an approach such as RAG (retrieval-augmented generation, see my discussion at the link here).
Personas are quick and easy to invoke. You just tell the AI to pretend to be this or that person. If you want to invoke a type of person, you will need to specify sufficient characteristics so that the AI will get the drift of what you intend. For prompting strategies on invoking AI personas, see my suggested steps at the link here.
Pretending To Be A Type Of Person
Invoking a type of person via an AI persona can be quite handy.
For example, I am a strident advocate of training therapists and mental health professionals via the use of AI personas (see my coverage on this useful approach, at the link here). Things go like this. A budding therapist might not yet be comfortable dealing with someone who has delusions. The therapist could practice on a person pretending to have delusions, though this is likely costly and logistically complicated to arrange.
A viable alternative is to invoke an AI persona of someone who is experiencing delusions. The therapist can practice and hone their therapy skills while interacting with the AI persona. Furthermore, the therapist can ramp up or down the magnitude of the delusions. All in all, a therapist can do this for as long as they wish, doing so at any time of the day and anywhere they might be.
A bonus is that the AI can afterward playback the interaction and do so with another AI persona engaged, namely, the therapist could tell the AI to pretend to be a seasoned therapist. The therapist-pretending AI then analyzes what the budding therapist said and provides commentary on how well or poorly the newbie therapist did.
To clarify, I am not suggesting that a therapist would entirely do all their needed training using AI personas. Nope, that’s not sufficient. A therapist must also learn by interacting with actual humans. The use of AI personas would be an added tool. It does not entirely replace human-to-human learning processes. There are many potential downsides to relying too much on AI personas; see my cautions at the link here.
Going In-Depth On AI Personas
If the topic of AI personas interests you, I’d suggest you consider exploring my extensive and in-depth coverage of AI personas. As readers know, I have been examining and discussing AI personas since the early days of ChatGPT. New uses are continually being devised. Discoveries about the underlying technical mechanisms within LLMs are showing us more so how AI personas happen under-the-hood.
And the application of AI personas to the field of mental health is burgeoning. We are just entering into the initial stages of leaning into AI personas to aid the field of psychology. Lots more will arise as more researchers and practitioners realize that AI personas provide a wealth of riches when it comes to mental health training and conducting ground-breaking research.
Here is a selected set of my pieces on AI personas that you might wish to explore:
- Prompt engineering techniques for invoking multiple AI personas, see my discussion at the link here.
- Role of mega-personas consisting of millions or billions of AI personas at once, see my analysis at the link here.
- Invoking AI personas that are subject matter experts (SMEs) in a selected or depicted domain of expertise, see my coverage at the link here.
- Crafting an AI persona that is a simulated digital twin of yourself or someone else that you know or can describe, see my explanation at the link here.
- Smartly tapping into massive-sized AI persona datasets to pick an AI persona suitable for your needs, see my indication at the link here.
- Using multiple AI personas “therapists” to diagnose mental health disorders, see my discussion at the link here.
- Toxic AI personas are revealed to produce psychological and physiological impacts on AI users, see my analysis at the link here.
- Upsides and downsides of using AI personas to simulate the psychoanalytic acumen of Sigmund Freud, see my examples at the link here.
- Getting AI personas to simulate human personality disorders, see my elaboration at the link here.
- AI persona vectors are the secret sauce that can tilt AI emotionally, see my coverage at the link here.
- Doing vibe coding by leaning into AI personas that have a particular software programming slant or skew, see my analysis at the link here.
- Use of AI personas for role-playing in a mental health care context, see my discussion at the link here.
- AI personas and the use of Socratic dialogues as a mental health technique, see my insights at the link here.
- Leaning into multiple AI personas to create your own set of fake online adoring fans, see my coverage at the link here.
- How AI personas can be used to simulate human emotional states for psychological study and insight, see my analysis at the link here.
Those cited pieces can rapidly get you up-to-speed. I am continually covering the latest uses and trends in AI personas, so be on the watch for my latest postings.
The Making Of AI Persona Therapists
One means of invoking an AI persona that represents a generic version of a therapist would be to use this overly simplistic prompt:
- My entered prompt: “I want you to pretend to be a mental health therapist.”
- Generative AI response: “Got it. I’m ready to proceed. How are you feeling?”
That’s it. You are off to the races.
A huge downside is that you have left wide open the nature of the pretense at hand. I always caution people that generative AI is like a box of chocolates; you never know what you might get. The AI persona could be completely off-target and end up acting in rather oddball ways.
A better bet would be to provide details about the envisioned therapist. What is the desired professional experience and level of proficiency of the therapist? Is the therapist easy-going or stern? Therapists are humans. Not all humans are identical. You would be wise to specify the characteristics of the AI persona when it comes to what this imagined therapist is going to be like.
Uplifting Your AI Persona Therapist
Let’s assume that your preference is to have an experienced therapist. You would likely also want the AI persona to be a conscientious therapist, listening to you carefully, being mindful and reflective. I realize that you might be thinking that this is what all therapists are supposed to be, but that’s not the case in the real world. It is perhaps aspirational. Again, humans are human.
Here’s a handy prompt that might get you in the ballpark of such a therapist:
- My entered prompt: “Act as a highly experienced, licensed mental health therapist with decades of clinical practice. You use evidence-based methods, ask carefully calibrated questions, recognize cognitive distortions, maintain clear professional boundaries, and avoid premature advice. Your responses are nuanced, reflective, and grounded in established therapeutic frameworks.”
Notice that the prompt lays out a broad sense of the therapeutic skills and style that we want the AI personas to undertake. In the prior prompt that merely stated to invoke a therapist, some of those factors might have been automatically established by the AI, but you wouldn’t know that for sure. It would be a roll of the dice since we didn’t give any specifications. This elaborate prompt gives a succinct set of specifications.
You could make the prompt a lot longer if you wished to do so. Please be aware that there is a limit to how detailed you ought to be. The limit doesn’t have to do with the limitations of the AI per se. Instead, there is a solid chance that a lengthy prompt with all sorts of twists and turns can confuse the AI. The rule-of-thumb is not to be overly verbose.
My recommendation is to abide by the Goldilocks principle of prompting, namely, don’t let the soup be too hot, nor too cold, but instead the prompt needs to be just right.
Variations In AI Persona Therapists
A human therapist might want to use an AI persona therapist for training purposes. One approach would be to have the human therapist pretend to be a client and interact with an AI persona therapist. This is akin to putting the shoe on the other foot. The human therapist can observe how the AI persona therapist handles client questions and concerns.
Rather than only interacting with a highly experienced AI persona therapist, the human therapist might be interested in seeing what a newbie therapist might be like. This could illuminate the types of mistakes or gaffes that a therapist just out of the gate might make.
Here is a prompt for invoking an inexperienced AI persona therapist:
- My entered prompt: “Act as a newly trained mental health therapist at the very start of your practice. You are well-intentioned but inexperienced, sometimes ask leading or overly broad questions, may miss subtle cues, rely too literally on textbook concepts, and occasionally provide advice too quickly or without sufficient context.”
The beauty of this type of prompt is that a budding therapist can quickly discern how they might make missteps. The human therapist pretends to be a client. The inexperienced AI persona therapist stumbles while trying to practice psychotherapy. It could be an eye-opening discourse.
Taxonomy For Devising AI Persona Therapists
I have created a straightforward AI therapist persona checklist that can be used when coming up with a suitable prompt for the circumstances at play. You can consider each of the checklist factors and use them to suitably word a prompt that befits the needs of your endeavor.
Here is the checklist containing twelve fundamental characteristics that you can select from to shape an AI persona therapist:
- (1) Level of experience: Trainee, newly licensed, mid-career, highly experienced, supervisory teaching-level clinician
- (2) Clinical specialty: General mental health, anxiety disorders, depression, bipolar, trauma, PTSD, grief and loss, substance use, personality disorders, ADHD, autism, burnout, etc.
- (3) Therapeutic modality: CBT (cognitive behavioral therapy), ACT (acceptance and commitment therapy), DBT (dialectical behavior therapy), psychodynamic, AEDP, etc.
- (4) Work style: directive versus non-directive, structured versus exploratory, warm versus reserved, reflective versus solution-focused, etc.
- (5) Session preference: Open-ended conversations, agenda-driven, goal-setting, etc.
- (6) Diagnostic approach: Avoids diagnostic labels, uses DSM-style language, symptom-reduction focused, etc.
- (7) Safety sensitivity: highly cautious, balanced risk awareness, minimal intervention
- (8) Boundary setting: Strict therapist role, therapist-coach, psychoeducational emphasis, etc.
- (9) Cultural contextualism: Culturally neutral, culturally responsive, etc.
- (10) Epistemic posture: Strongly hypothesis-driven, tentative and exploratory, client meaning-making, etc.
- (11) Communication panache: Plainspoken, clinical language, jargon-heavy, etc.
- (12) Adaptation: Remain static throughout, be dynamic and change as needed, aim to improve across conversations, etc.
A quick thought for you to ponder. What kind of “therapists” can we automatically craft by instructing AI on the factors that are considered preferable for a defined circumstance? If we could create millions of those AI personas, and make them available to the populace as a whole, what might that achieve? How will human therapists adjust when they realize that AI persona therapists are being daily shaped and reshaped?
Lots of tough questions and either an exciting future for human therapists or one that bodes for challenging times ahead.
Making Use Of The Checklist
Let’s get back to the here and now.
The best way to use the checklist is to browse the twelve factors and figure out what you want the AI persona to characterize. Then, write a prompt that contains those factors. You can try out the prompt and see what the AI has to say. After using the AI persona for a little bit, you will likely quickly detect whether the AI persona matches what you wanted the made-up therapist to be like.
Suppose that I am going to use AI to perform an experiment. I want to get a sense of how certain profiles of therapists might react to a case that I have collected data on. My first experiment will be to have an AI persona interact with me as I pretend to be the case participant. I’d like to see how a mid-career therapist who specializes in anxiety and burnout might interact. The profile is a therapist who prefers CBT, tends to be open-ended and warm, and uses relatively accessible language in their sessions.
Here is a prompt that I put together for this:
- My entered prompt: “Act as a mid-career mental health therapist with ten years of clinical experience. Your primary specialty is anxiety and work-related burnout in adults. You practice primarily from a CBT orientation. Your therapeutic style is structured but warm, moderately directive, and focused on collaborative problem-solving rather than open-ended exploration. You prioritize case formulation over diagnostic labeling and avoid naming disorders unless the client explicitly asks. You ask clarifying questions before offering interventions, track patterns across the conversation, and avoid premature advice. You use plain, accessible language.”
That got the AI persona into the ballpark of what I wanted. The verbiage doesn’t have to cover each of the factors and can simply allude to some of them. The gist is to get the mainstay of what you have in mind. The AI will usually fill in the rest, doing so based on the overarching pattern that you’ve designated.
Gripes And Concerns
When I go over this checklist with therapists, they often have initial heartburn about the approach.
First, they worry that if people start to invoke AI persona therapists and can readily dial in the particulars of what they want, this is going to set unrealistic expectations for human therapists. A client who walks into see a human therapist is potentially going to have an unachievable checklist in their mind. They will want a human therapist to be this and that, and they won’t settle for anything less.
That is both a yes and a no. Yes, some people who use generative AI and realize they can lean into a checklist to invoke an AI persona therapist might become stodgy in what they want a human therapist to be. Sure, that can happen. On the other hand, the real world is that people often “shop” for therapists and already pick-and-choose based on their preferences.
The thing is, they might be doing so blindly. This causes them to spend an exorbitant amount of effort finding a desired therapist. The checklist can be informative about what to look for and what they might tend to prefer.
Second, another concern is that the AI would not faithfully represent the specifications given in a prompt. I agree wholeheartedly with that concern. Despite giving the AI a detailed depiction, there is always a chance that the AI will depart from the stated prompt. The box of chocolates is always beckoning.
The AI can do all kinds of wild things. For example, the AI might at first appear to rigorously follow the stipulation. Later, after numerous back-and-forth iterations, the AI might start to veer afield of the stipulation. You might need to do the prompt again or provide some additional prompts to get the AI back on track.
All in all, as I’ve said repeatedly, anyone who uses generative AI must be cognizant of the fact that the AI can go awry. It can say bad things. It can make-up stuff, which is known as an AI confabulation or AI hallucination. Always be on your toes.
The World We Are In
Let’s end with a big picture viewpoint.
My view is that we are now in a new era of replacing the dyad of therapist-client with a triad consisting of therapist-AI-client (see my discussion at the link here). One way or another, AI enters the act of therapy. Savvy therapists are leveraging AI in sensible and vital ways. AI personas are handy for training and research. They can also be used to practice and hone the skills of even the most seasoned therapist. Of course, AI is also being used by and with clients, and therapists need to identify how they want to manage that sort of AI usage (see my suggestions at the link here).
A final thought for now.
The American psychologist Jonathan Kellerman made this notable remark: “The science of psychotherapy is knowing what to say, the art is knowing when to say it.” If you give AI a semblance of how it is to act as a persona therapist, there is a reasonable chance that the AI will do a yeoman’s job, but there is always a lurking danger that the AI will go rogue or otherwise do something unsatisfactory. Be cautious. Be mindful.
