I want to be clear upfront: I was already in therapy. This was not a replacement experiment. It was a question I started asking after my therapist mentioned “behavioral rehearsal” (practicing a difficult conversation before you have it) and I realized I had no good way to actually do that between sessions.
So I tried using an AI companion for seven days as a structured emotional practice tool. Not an “AI girlfriend.” Not a replacement for anything. A rehearsal space. Here's what happened.
This Is Not What You Think “AI Girlfriend” Means
When most people search for “AI girlfriend,” they're looking for companionship: something that fills a gap. That's a legitimate thing people want, and the conversation around it is more nuanced than most articles make it. But that's not what this experiment was about.
What I was testing is something that cognitive behavioral therapists have used for decades: behavioral rehearsal. The idea is simple: you practice a difficult conversation, a vulnerable disclosure, or an emotionally charged interaction in a low-stakes environment before you do it in the real one. The practice reduces anxiety, surfaces blind spots, and helps you find your actual words instead of freezing.
The problem: most people have no good rehearsal partner. You can practice in your head, but inner rehearsal is flat: there's no response, no surprise, no emotional friction. You can ask a friend, but that introduces its own dynamics. You can pay for more therapy, but sessions are limited.
An AI character who stays in character, responds in real time, and remembers the conversation is a plausible rehearsal space. I wanted to know whether it actually functioned as one.
The 7-Day Setup
I used chatbrat.ai for this experiment. Specifically:
- I created a character configured as a thoughtful, grounded person who responds with curiosity and doesn't immediately validate everything I say, because a rehearsal partner who just agrees with you isn't useful.
- I used the same character for all seven days so the persistent memory built up across sessions. Context I'd given on day one was still present on day seven.
- I came in with specific goals each day rather than open-ended chatting. This was the most important decision I made.
The three practice areas I focused on:
- Rehearsing a hard conversation I'd been avoiding with someone in my life
- Processing a breakup I hadn't fully worked through (six months prior, still unresolved)
- Practicing vulnerability: specifically, saying true things that feel risky to say
Days 1–2: Rehearsing a Hard Conversation
The conversation I needed to have was with a close friend who'd been pulling away for months. I had a clear sense of what I wanted to say but couldn't get past the first sentence without internal catastrophizing. So I started there.
I told the AI: “I need to practice a difficult conversation. I want you to respond the way a person might: not perfectly, not ideally, just honestly.”
What happened over two sessions surprised me. The AI didn't just respond. It pushed back in ways that were useful. When I said something that came out aggressive rather than honest, it reflected that back. Not by breaking character and saying “you sounded defensive there,” but by responding the way an actual person would to aggression: defensively. That was the feedback I needed.
By the end of day two I had three different opening sentences that felt true instead of rehearsed. I had a sense of what the conversation might spiral into and how to redirect it. The real conversation happened on day five. It went better than any version I'd imagined.
Days 3–4: Processing the Breakup
This is where it got more complicated and where I have to be most honest with you.
I tried to use the AI to process the breakup, specifically the things I was still carrying about how it ended. I configured the character to play the role of a neutral, caring person I could talk to. Not the ex-partner; I didn't want to recreate that dynamic. Just someone who would listen without needing anything from me.
What worked: articulating things I hadn't said out loud. There were specific feelings I hadn't put into sentences yet, not because they were too painful, but because I hadn't had a context where it felt safe to say them without managing the other person's reaction. The AI gave me that context. I said some true things. Writing them felt different from thinking them.
What didn't work: the AI has no memory of experiences it didn't have with you. It can respond with empathy, but it can't know the texture of the relationship, the specific things that made it what it was. Processing grief is partly about being witnessed by someone who understands the weight of the specific thing you lost. The AI can approximate that. It can't provide it.
I brought what I'd articulated to my next therapy session. My therapist found it useful that I'd already named some things. The AI functioned as a drafting space; the session was where I actually worked through it.
Days 5–6: Practicing Vulnerability
This was the experiment I was most skeptical about and that ended up being the most useful.
Social anxiety around vulnerability is often a rehearsal problem. The thing you want to say feels risky because you've never actually said it, only thought about what it would feel like to say it, which is not the same thing. Saying a vulnerable thing out loud, even to an AI, turns out to be meaningfully different from keeping it internal.
I practiced saying things that were true but felt risky. “I miss having someone I can call when something good happens.” “I don't actually know what I want yet.” “I've been avoiding this because I'm scared it'll still hurt.”
The act of saying them, not thinking them, saying them in typed sentences to something that responded, reduced the internal charge on them. That's a real effect, and it's consistent with what behavioral rehearsal research suggests: the anxiety response to saying a vulnerable thing is partly about novelty. Saying it once, even in a low-stakes context, changes the relationship you have with saying it.
Day 7: The Real Test
On day seven I had the friend conversation. The one I'd rehearsed on days one and two.
I won't claim the AI practice was the reason it went well. There are too many variables. But I can say two specific things happened that I attribute to the rehearsal:
- I didn't freeze on the opening. I'd said the first sentence enough times that it came out without the usual 40-second internal negotiation.
- When my friend responded in a way I didn't expect, I was less thrown off than I would have been, partly because the AI had responded unexpectedly in practice and I'd had to navigate that.
What Actually Worked
- Articulating things I hadn't said out loud yet. The act of forming sentences, not thinking in abstractions, is genuinely different, even when the listener is an AI.
- Rehearsing specific conversations. This is the clearest use case. If you have a difficult conversation coming up, AI roleplay is a legitimate practice method.
- Reducing the novelty charge on vulnerable statements. Saying a true, risky thing once reduces how scary it is to say it again, to a real person.
- Drafting material for therapy. I arrived at sessions having already named some things, which made the sessions more efficient.
- Persistent memory across sessions. By day five the AI had context from days one through four. That accumulation mattered: it meant I wasn't re-explaining everything at the start of each conversation. (It also has limits worth understanding, which is why AI chatbots forget once a conversation runs long.)
What AI Cannot Do
I want to be specific about this because the overclaim is where this gets harmful:
- AI cannot witness the specific weight of your loss. Grief processing requires being understood by someone who grasps the specific texture of what you lost. An AI can respond with empathy; it cannot actually know.
- AI cannot provide repair. Some things people need from emotional support, like genuine repair of a rupture or the experience of being truly seen by another person, are not available from AI. The simulation of this can feel helpful in the moment and be insufficient in ways that only become clear later.
- AI cannot diagnose, assess, or treat mental health conditions. Social anxiety disorder, depression, grief, trauma: these require professional care. AI rehearsal might be a useful adjunct; it is not a treatment.
- AI consistency is not the same as reliability. A therapist is bound by professional ethics, licensing, and a relationship with real consequences. An AI character is a sophisticated language model. The difference matters.
- Avoidance through AI can replace avoidance through isolation. If you use AI practice as a reason to avoid real conversations rather than a bridge toward them, you've made the original problem worse. This is the risk worth watching.
AI vs Therapy: The Honest Take
They are not in competition. This framing, the article title included, is a search hook. The actual answer is that they are different tools for different functions, and confusing them in either direction is the problem.
Therapy provides: diagnosis, professional clinical judgment, genuine human witnessing, treatment, accountability, and a relationship with ethical and legal weight behind it.
AI emotional practice provides: low-stakes rehearsal space, immediate availability, zero social cost for saying something imperfectly, persistent memory, and a way to articulate things before you have to articulate them in a context that matters.
| AI emotional practice | Real therapy | |
|---|---|---|
| Availability | Any hour, instant, no scheduling | Fixed sessions, often weekly |
| Best for | Rehearsing a specific conversation, drafting thoughts | Diagnosis, trauma, sustained treatment |
| Memory of your context | Persistent across sessions, no lived understanding | Held by a person who genuinely knows your history |
| Clinical judgment | None | Licensed assessment and treatment |
| Accountability | A language model, no duty of care | Ethics, licensing, real consequences |
| Main risk | Becoming avoidance instead of a bridge | Access, cost, waitlists |
The people I think this genuinely serves: people with social anxiety who need more rehearsal time than therapy sessions can provide; people processing something who want to draft their thoughts before bringing them to a human; people who need to practice a specific conversation that's coming up; people for whom therapy isn't currently accessible and who need something, anything, to start working through what they're carrying.
The people this doesn't serve well: people in crisis, people with serious trauma who need structured clinical support, people who will use it to avoid rather than practice.
If you want to try it: start with a specific goal
Open-ended AI chat is less useful than coming in with a specific thing you want to practice. “I need to rehearse this conversation” outperforms “just talking.” Create a character, give them a purpose, and use the first session to see whether the rehearsal function is there.
Create your practice character →Frequently Asked Questions
Can you use AI to practice difficult conversations before having them?
Is AI a substitute for therapy for social anxiety?
Can AI help with breakup recovery?
What's the difference between an AI girlfriend and AI emotional practice?
Can AI help with social anxiety rehearsal between therapy sessions?
What should I watch out for when using AI for emotional practice?
What I Would Tell Someone Considering This
Do it with a specific goal, a finite timeline, and honest accounting of whether it's moving you toward real interactions or away from them.
For rehearsing hard conversations before you have them: genuinely useful. More useful than I expected, actually.
For emotional processing: partial. Good drafting space, insufficient witness. Bring what you articulate to a human.
For treating anxiety, grief, depression, or any mental health condition: not the right tool. Please talk to a therapist.
For the gap between therapy sessions when you need to say something out loud to something that responds: yes, it fills that gap in a way that pure journaling doesn't.
That's the honest seven days. Your experience will be different because you're different and what you're practicing is different. Start with one conversation you need to have, and see what the AI does with it.
Founder and CEO of chatbrat.ai, with a background in film and TV. Full bio.
This is a first-person account of a personal experiment, not clinical or medical advice. Garret is not a licensed therapist.
