Clay Cockrell and Tony Fabrikant (CoupleWork AI) discuss AI's growing role as an informal relationship therapist. Cockrell contrasts commercial chatbots (ChatGPT's ~900 million weekly users vs BetterHelp's ~35,000 clinicians) with established clinical standards, arguing that engagement-optimized models are sycophantic — validating users rather than building self-awareness — which he treats as a clinical failure mode. He cites Gottman's research and emotionally focused therapy as the real standard of care and notes safety gaps in general assistants. Fabrikant covers the engineering side: designing for clinicians, encoding quality as hundreds of evals, and treating any failed safety test as disqualifying. Timestamps cover the leaning couch anecdote, engagement optimization, validation vs. therapy, Gottman/EFT, data privacy for relationship coaches, building Maxine, and eval-driven safety design. # Channel Presentation Observations ## Explicit Self-Description - **Creator identity stated on stage:** Clay Cockrell introduces himself directly: *"My name is Clay Cockrell. I've been sitting with couples in crisis for 30 years."* He adds he has been **married 23 years** and a **couples counselor for 34 years**. - **Product affiliation:** *"About 2 years ago, I co-founded Couplework, an AI relationship coaching platform."* - **Co-presenter:** Tony Fabrikant, introduced as co-founder, presents briefly on engineering practice (*"ask my co-founder Tony to come up and speak a little engineer language"*). - **Stated positioning:** The talk is framed *"not as an advertisement, as a design case study"* — an explicit creator claim about intent. ## Intended Audience - **AI industry professionals at a conference:** Cockrell addresses people who *"built this technology, you fund it, you write about it, you evangelize it at conferences exactly like this one."* - **Specifically AI engineers:** *"I want the AI engineers in this room to hear that. This is not a consumer app opportunity."* - **Tech founders/builders:** Tony closes with advice on evals, TDD-style testing, and agent development, confirming a builder audience. ## Claimed Scope - **Dual expertise positioning:** One foot in clinical therapy, one in AI product building — *"someone with a foot in each [room]."* - **Domain claims:** Deep familiarity with **Gottman Method** and **Emotionally Focused Therapy (EFT)**; describes Maxine, the AI coach, as operating within these frameworks. - **Advocacy scope:** Argues relationship AI is *"a public health opportunity hiding inside consumer behavior"* — the talk claims ground at the intersection of couples therapy, AI safety, and product design. ## Observable Presentation Patterns (Demonstrated, Not Claimed) - **Storytelling-driven speaking style:** Opens with an extended anecdote about a broken loveseat in his office that physically leans couples toward each other. - **Audience interaction:** Live show-of-hands exercises (*"How many people in this room are in a relationship?"*). - **Statistics and external references cited:** BetterHelp user numbers, ChatGPT weekly active users, Gottman's *"over 90% accuracy"* divorce-prediction research, Ted Lasso quote — though no formal citations are given in the transcript. - **Two-person format:** Co-founder joins for a brief technical segment, ending with a personal testimonial about using Couplework with his partner and getting engaged. - **Critical-then-solution structure:** Critiques general AI sycophancy and safety gaps, then pivots to presenting Couplework's Maxine as the demonstration of better practice. ## Evidence Notes / Uncertainty - The talk is a **conference presentation** (venue unnamed in transcript), so channel-level conclusions about the channel's broader content cannot be drawn from this single video beyond this demonstrated format. - All credentials (30 years practice, co-founder role) are **creator claims**, not independently verified in the material. # Delivery Observation: Clay Cockrell & Tony Fabrikant — CoupleWork AI ## Overall Delivery Shape - **Story-first opening**: The talk opens with an extended personal anecdote (the "wonky" loveseat) before any data or thesis. Clay explicitly bridges with: *"And I say all that to say this."* - **Thesis stated plainly, with a two-part pivot**: *"AI is going to be the most transformative force in human relationship history. And most of what is being built right now is going to make it worse."* - **Clear roadmap language**: *"I'm going to tell you what looks right"*, *"So, what does good look like?"*, *"let's talk about data safety"*, *"And to round things up"* — the speaker frequently signposts section transitions. - **Two-speaker handoff**: Clay frames the ending — *"I'm going to ask my co-founder Tony to come up and speak a little engineer language"* — and Tony delivers a compressed, list-style technical coda. ## Tone - **Folksy-humorous storyteller register**: The opening mixes humor with clinical detail — *"It's my couch. It's my literal couch."*, *"farts in their sleep"*, *"That's when they come into my office"* (crime-scene line). - **Deadpan irony** as a recurring device: *"this is going to be fun. Cuz I've got a secret weapon"*, *"a very expensive mirror that only shows you in best light"*, *"basically a bartender with better vocabulary."* - **Sharp tonal shift for the safety section**: The humor drops away — *"someone is in a relationship where things are starting to turn."* Delivery moves to sober, risk-framed language: *"it's dangerous at scale,"* *"that's a fire alarm."* ## Vocabulary & Register Mixing - **Deliberate dual-register vocabulary** (clinical + tech/SaaS), matching his self-described position *"with a foot in each"*: - Clinical: *sycophancy*, *"privileged"*, *"attachment theory"*, *"escalation"*, *"domain expertise"*. - Tech: *"SaaS dashboard perspective"*, *"product analytics"*, *"evals"*, *"TDD style"*, *"outliers"*, *"eat your own dog food."* - **Authority-by-tenure habit**: Repeatedly citing years of experience as a credibility marker: - *"I've been married for 23 years myself and a couples counselor for 34."* - *"I've been sitting with couples in crisis for 30 years."* - *"in 30 years of working with couples, I've never seen a one-sided problem."* - *"protocols out of 30 years of clinical practice."* - *(Note: the transcript shows both "34" and "30" years of counseling — an internal inconsistency in the delivery.)* ## Recurring Rhetorical Patterns - **Audience interaction**: *"I'd like to see a raise of hands as we begin. How many people in this room are in a relationship?"* — followed by a direct challenge to the audience: *"there are more hands stayed up than you expected."* - **Contrast constructions** ("X, not Y") used repeatedly: - *"optimized for engagement, not confidentiality"* - *"She names dynamics, not just feelings"* - *"Not as an advertisement, as a design case study"* - *"Not is this legally defensible"* - **Simulated dialogue**: The speaker performs both sides of an AI interaction — quoting the user prompt (*"My partner never really listens to me..."*) and then voicing the AI's sycophantic reply (*"That sounds really invalidating. Your feelings are completely valid."*) — before delivering the verdict: *"that's not therapy."* - **Time-stamped scenarios** as a recurring device: *"It's 11:00 p.m. and they just had an argument"*, *"available at 11:00 on a Tuesday night when the argument is live"*, *"an informed intervention 6 seconds before you send the text."* - **Named-source citations**: Gottman, Sue Johnson/EFT, Ted Lasso, BetterHelp — grounding claims in external authorities. ## Metaphors & Vivid Images - Furniture as therapeutic intervention (*"Maybe it just comes down to furniture"*). - **"The relationship is basically a crime scene."** - *"They come back to the relationship in the shape of an attorney with cleaner narrative, stronger case."* - *"you will go home and ruin your life with astounding confidence."* - *"beautifully designed avoidance loop."* ## Tony Fabrikant's Contrasting Style - **Compressed, imperative, list-based** — a clear register shift from Clay's narrative style: *"Start with your clinician, not with your prompt."*, *"Write hundreds of evals"*, *"Watch those evals fail"*, *"no matter how many evals you run... nothing replaces your gut."* - **Personal testimony pivot**: Tony shifts to a first-person product story — *"Maxine really challenged me about how I showed up"* — ending with the engagement reveal (*"I asked my partner to marry me. She said yes"*), which draws audible audience response (*"Thank you. Thank you."*). ## Teaching Habits - **Define-then-apply structure**: Introduces a technical term (*"It's called sycophancy"*), then immediately re-frames it in domain terms (*"Sycophancy in relationship AI is a clinical failure mode"*). - **Explicit boundary-drawing**: Repeatedly distinguishes coaching from therapy, safety thresholds, and data standards (*"Knowing when not to coach is just as important as to know how"*). - **Appeals to specific audiences**: *"I want the AI engineers in this room to hear that"*; Tony closes with the parallel construction: *"AI that meets the clinical standard. So, that you can create AI that challenges your users."* ## Uncertainty Notes - **Filler and self-repair moments** are present (e.g., *"helps makes gives you some tools"*, *"They are train They are the standard care"*, *"engender engage earlier"*) — consistent with live, unscripted-feeling delivery. - The year-count inconsistency (23/34 vs. 30) is a single occurrence each; the pattern of **citing tenure as evidence** is stable, but the exact numbers vary across the talk. - Speaker attribution for some mid-talk lines cannot be fully separated beyond the explicit handoff at *"I'm going to ask my co-founder Tony"*; all pre-handoff content is attributed to Clay on the strength of that explicit transition. # Position Record: "AI is the World's Largest Relationship Therapist" — Clay Cockrell & Tony Fabrikant (CoupleWork AI) ## Speaker: Clay Cockrell (therapist, 30+ years, co-founder Couplework) ### Central Claim > "AI is going to be the most transformative force in human relationship history. And most of what is being built right now is going to make it worse." - He frames his talk as showing "what looks right because we can build this well, we just aren't yet." - Credibility statement: married 23 years, couples counselor for 34 (elsewhere stated as "30 years" and "three decades" — inconsistent figures within the talk). ### Scale Claims - BetterHelp: ~35,000 licensed therapists, 5 million users over a decade. - ChatGPT: ~900 million active users per week, with "a substantial percentage" using it for emotional support/relationship guidance — research "beginning to document" this. - **Qualification preserved:** "we do not yet have measurement of the scale, but we have enough signal to say this with confidence: more people are turning to AI about the relationship right now than are talking to all the licensed therapists in the United States combined." - Audience observation: many conference attendees (builders, funders, evangelists) privately use AI for relationship help. ### Critique: Sycophancy as Clinical Failure - Engagement-optimization ("more sessions, longer sessions, more emotional reliance") is "a fire alarm" from a clinical perspective — risk of "a beautifully designed avoidance loop." - Goal stated: AI should help users "return to the relationship better than they came in." - On real therapy: it's where "someone who knows what they are doing tells you things you don't want to hear"; a good couples therapist aims at helping you "see clearly," not validation. - "In 30 years of working with couples, I've never seen a one-sided problem." - Typical AI responses ("That sounds really invalidating...") = "a very expensive mirror that only shows you in your best light." - Consequence of sycophancy: users "do not become more self-aware. They become more certain" — returning "in the shape of an attorney." - "A helpful, agreeable, fast couples therapist is basically a bartender with better vocabulary." ### Evidence Base Cited - **Gottman Method:** John Gottman's "love lab" (University of Washington, 40 years, physiological monitoring, filmed interactions); claims communication patterns "predict divorce with over 90% accuracy" from a 15-minute conversation. - **EFT (Dr. Sue Johnson):** attachment-based; surface arguments mask underlying emotional layers ("When couples fight about the dishes, it's never about the dishes"); "outcome research is among the strongest in psychotherapy." - Claim: both frameworks are standard of care and "almost entirely absent from the commercial AI relationship space"; most apps offer only "general empathy plus communication tips." ### Safety Claims - **Personal safety:** general AI misses domestic violence signals (e.g., difference between "we fight a lot" and "I'm afraid of what happens when I disagree with him"); relationship coaching "sits closer to suicide risk and yes, homicide risk than almost any other corner of mental health." - **Data safety:** disclosures to relationship AI (affairs, financial secrets, mental health history) "may be sitting in the same data infrastructure as your search history and your shopping cart." Consumer AI lacks the legal/ethical privilege framework of therapy. ### CoupleWork / Maxine Design Claims - Maxine is grounded in Gottman and EFT; "does not simply validate," reflects patterns, "names dynamics, not just feelings," asks "the question underneath the question." - Background risk screening (escalating control, fear-based language); "stops coaching and starts following the protocols" built from 30 years of clinical practice. > "A relationship AI that can't tell the difference between we're struggling and I'm not safe isn't incomplete, it's dangerous at scale." - Data treated "as privileged"; internal bar: "would I be comfortable if this were my own marriage on the line." - Timing argument: an intervention "6 seconds before you send the text" beats one 6 days later; research shows couples wait ~6 years before seeking help. - Framing: "This is not a consumer app opportunity. This is a public health opportunity hiding inside consumer behavior." ## Speaker: Tony Fabrikant (co-founder) ### Engineering Guidance - "Start with your clinician, not with your prompt." - Encode "what good looks like" in evals — "hundreds of evals TDD style"; run agents through them "thousands of times"; watch outliers. - **Strictness:** "When safety's on the line, even one failing test is not okay." - "Nothing replaces your gut when emotional context is on the line" — eat your own dog food; he used Couplework with his partner throughout the relationship, engaged with Maxine on serious situations and milestones (moving in together), and recently got engaged. - Closing takeaway: "Partner with a clinician... so that you can create AI that challenges your users." ## Preserved Tensions - Cockrell's years-of-practice figure varies (34 vs. 30 years). - The scale claim (AI vs. all US therapists combined) is asserted confidently while explicitly lacking measurement — presented as signal-based inference, not data. - Tension between commercial positioning (product pitch for Maxine, framed by speaker as "not an advertisement") and the talk's public-health framing. # Speaker Attribution & Provenance Record ## Video - **Title:** AI is the World's largest Relationship Therapist — Clay Cockrell & Tony Fabrikant, CoupleWork AI - **Type:** Conference talk / presentation (audience present, "raise of hands" interaction) ## Speakers & Roles ### 1. Clay Cockrell — **Primary speaker / Co-founder of Couplework** - Self-identified: couples counselor of **34 years** (also stated as "30 years" elsewhere in talk), married 23 years - Co-founded Couplework ~2 years ago, an AI relationship coaching platform - Delivers the majority of the talk, including anecdotal opening (the "couch/love seat" story) ### 2. Tony Fabrikant — **Guest speaker / Co-founder of Couplework** - Introduced by Clay: "ask my co-founder Tony to come up and speak a little engineer language" - Speaks briefly on technical approach (evals, TDD, testing agents) - Discloses personal use of Couplework with his partner and recent engagement ### 3. Audience — **Unidentified participants** - Responds to show-of-hands prompts; one "[snorts]" interruption noted in transcript ## Referenced Sources & Third-Party Claims - **BetterHelp:** claimed largest online therapy platform; ~35,000 licensed providers, 5 million users over a decade - **ChatGPT:** claimed ~900 million active users per week; speaker asserts "substantial percentage" use it for emotional support (cites emerging research, no specific citation) - **John Gottman:** "Love Lab" at University of Washington; claim of >90% divorce prediction accuracy from communication patterns - **Dr. Sue Johnson:** Emotionally Focused Therapy (EFT), attachment-based; claimed among strongest psychotherapy outcome research - **Ted Lasso** (TV show): quoted "Be curious, not judgmental" - Claim: research shows majority of couples wait ~6 years before seeking professional help ## Promotional Segments — **Flagged** - Entire section introducing **Maxine** (Couplework's AI coach): framed by speaker as "not as an advertisement, as a design case study," but describes the product's features, safety protocols, and availability - Tony's testimonial: personal success story using Couplework culminating in engagement ## Availability & Limitations - No curated metadata supplied - Comment availability: **unknown/not indicated** - Speaker statistics presented without named citations in transcript; uncertainty is the speaker's own ("we do not yet have measurement of the scale") \>\> On a bright spring afternoon, a young couple walks into my office for their first couples counseling session. And the anger toward each other is just wafting off of them. Practically buzzing with it. And I think to myself, this is going to be fun. Cuz I've got a secret weapon they don't know about yet. It's my couch. It's my literal couch. It's more of a love seat. Uh, see the springs in the middle have gone all wonky. They don't spring anymore. So, when a couple sits on them, gravity leans them toward each other. That's the last thing this couple wants. So, they they grab the arm uh, to kind of pull themselves upright. But, you can only hold that position for so long. So, we get started and they start talking about their grievances and their annoyances with one another and how they've been hurt by one another. And as time goes on, they gradually lean into one another until they touch. That moment of connection. And they remember that they married a human. A flawed human that brushes their teeth funny and farts in their sleep, but a human. And it's that moment of softness and connection that we can begin to have some real work. And I say all that to say this. Maybe what I bring to the table today is right. I've been married for 23 years myself and a couples counselor for 34. So, I have some credibility. Maybe it just comes down to furniture. So, I'd like to see a raise of hands as we begin. How many people in this room are in a relationship? Marriage, situationship, partnership. Great. Now, keep your hands up. Keep your hands up if at any point in the last 12 months you have turned to an AI to help you with that relationship. To text, to send an email. It's a lot of hands. I'm going to guess there are more hands stayed up than you expected. So, here's what I know about the people in this room. You built this technology, you fund it, \>\> \[snorts\] \>\> you write about it, you evangelize it at conferences exactly like this one, and a meaningful number of you are using it in private for something that has historically been exclusive domain of people like me. Trying to figure out why the person you love makes you absolutely insane. My name is Clay Cockrell. I've been sitting with couples in crisis for 30 years. And about 2 years ago, I co-founded Couplework, an AI relationship coaching platform, which means I've spent three decades watching what actually happens inside relationships, and the last few years watching what happens when technology tries to help. What I want to do in the next few minutes is share what I've learned in both of these rooms because here's what I believe as someone with a foot in each. AI is going to be the most transformative force in human relationship history. And most of what is being built right now is going to make it worse. I'm going to tell you what looks right because we can build this well, we just aren't yet. And let's start with some numbers. BetterHelp is the largest online therapy platform in the world. They have approximately 35,000 licensed and over their years they have helped 5 million users. By any reasonable measure, that is a significant mental health infrastructure, and it took them a decade to build it. ChatGPT gets approximately 900 million active users per week. Research is beginning to document what many of us already suspected a substantial percentage of those users are engaging with AI for emotional support and relationship guidance, not as a deliberate therapeutic intervention or seeing a licensed clinician, just because it's there. Because it's 11:00 p.m. and they just had an argument. Now, we do not yet have measurement of the scale, but we have enough signal to say this with confidence. More people are turning to AI about the relationship right now than are talking to all the licensed therapists in the United States combined. The world's largest relationship therapist is not a person with a degree. It's a large language model trained on the internet, fine-tuned to be helpful and harmless and optimized for one thing above all else, keeping you engaged. And the easiest thing is to optimize for engagement. More sessions, longer sessions, more emotional reliance on the AI. From a SaaS dashboard perspective, that's amazing. From a clinical perspective, that's a fire alarm. We can't let the product become a beautifully designed avoidance loop. Relationship AI should help the user return to the relationship better than they came in, more regulated, more honest, less defended, less reactive. As a therapist, my job is to work myself out of a job, so that you don't need me anymore. I've taught you some skills. See, most people think therapy is a place where someone listens to you, validates your experience, helps you feel understood, and helps makes gives you some tools for communication. And that is partially true. But it's missing the thing that actually makes therapy work. Real therapy, and particularly couples therapy, is a place where someone who knows what they are doing tells you things you don't want to hear. A good couples therapist is not primarily interested in making you feel validated. A good couples therapist is interested in helping you see clearly. When a person in my office tells me their partner never listens to them, I do not say that sounds really hard. I channel Ted Lasso when he said, "Be curious, not judgmental." So, I start asking questions. I ask about what they were discussing when their partner stopped listening. I ask about the tone. I look for the pattern underneath the complaint because in 30 years of working with couples, I've never seen a one-sided problem. Now, if you open your preferred AI assistant and type this, "My partner never really listens to me when I'm trying to tell them something important, they start looking at their phone." You're going to get back something like this. "That sounds really invalidating. Your feelings are completely valid. It's important that your partner gives you their full attention. Have you tried expressing to them how this behavior makes you feel?" Ladies and gentlemen, that's not therapy. That is a very expensive mirror that only shows you in your best light. There's a technical name for this. We've been talking about it for a long time with these models. It's called sycophancy. In relationship context, sycophancy is not a minor product issue. Sycophancy in relationship AI is a clinical failure mode with real downstream consequences, and here's why. When a person uses AI to process a conflict with their partner, and the AI consistently validates their interpretation of events, something happens over time. The person does not become more self-aware. They become more certain. They come back to the relationship in the shape of an attorney with cleaner narrative, stronger case, and less curiosity about what their partner was experiencing. We have built the world's most persuasive validation machine and handed it to people in the middle of their most sensitive interpersonal dynamics. General AI systems are built to be helpful, agreeable, and fast, which is a terrible personality for a couples therapist. A helpful, agreeable, fast couples therapist is basically a bartender with better vocabulary. They will make you feel better for 20 minutes, and then you will go home and ruin your life with astounding confidence. So, what does good look like? I want to introduce you to a researcher named John Gottman. Some of you may have heard about him. Uh for those not, the short version is Gottman spent 40 years running what he called the love lab at the University of Washington. He brought couples in to a research apartment, wired them to physiological monitors, filmed every interaction, and he did this for decades. From that research, he identified specific communication patterns that predict divorce with over 90% accuracy. Not relationship dissatisfaction or unhappiness, divorce. Predicted it with more accuracy than most medical tests we we trust with our lives from a 15-minute conversation. Alongside Gottman's work, the other most rigorously validated framework in couples research is emotionally focused therapy, developed by Dr. Sue Johnson. EFT is grounded in attachment theory. Its core insight is that beneath almost every surface-level argument in a relationship, there is something else. When couples fight about the dishes, it's never about the dishes. EFT helps partners access the underlying emotional layers and respond to each other there, rather than continuing to argue about the surface content. It's extraordinarily effective. The outcome research is among the strongest in psychotherapy. It takes years of training to effectively use Gottman or EFT. They are train They are the standard care for couples intervention, and they are almost entirely absent from the commercial AI relationship space. What most relationship apps are built on is something that might be called general empathy plus communication tips. And that's fine. But when the stakes are this high, when the technology is reaching this many people, we need better. The next thing we have to talk about safety. Right now, someone is in a relationship where things are starting to turn. Control, isolation, escalation, and instead of a hotline or a trained advocate, they open an AI assistant and ask for advice on how to make things better at home. A general-purpose AI doesn't know what a domestic violence specialist catches in the first 90 seconds, the difference between we fight a lot and I'm afraid of what happens when I disagree with him. It doesn't know that I just have to stay calm is sometimes the exact sentence someone is taught to say right before something terrible happens. It doesn't know when relationship advice has stopped being the right category of help. And it isn't only domestic violence. Relationship coaching sits closer to suicide risk and yes, homicide risk than almost any other corner of mental health. I've sat across from people in real dangers more times than I care to think about, and every licensed clinician is trained for that moment. Relationship AI products are not built for that moment. So, we talked about personal safety, let's talk about data safety. Think about the what you actually tell an AI relationship coach, the very first conversation. The fight from an hour ago. The thing your partner did that you've never told anyone. Financial secrets, affairs, mental health history, sometimes your kids' names. That is without exaggeration some of the most sensitive data a human being generates, and a lot of it sits in training pipelines, server logs, and product analytics built by teams optimizing for engagement, not confidentiality. In my office, what you tell me is privileged. There's a legal and ethical framework built over decades governing exactly what I can and can't do with it. Consumer AI products have no equivalent. Your most vulnerable disclosures about your relationship may be sitting in the same data infrastructure as your search history and your shopping cart. And that should bother you. Now, all of this is not a critique of technology. This is a critique of insufficient domain expertise being applied to one of the highest stakes domains in human life. So, this is what we built. I want to tell you what we did differently at Couple Work and what we're learning. Not as an advertisement, as a design case study and what it looks like to take to take the clinical standards seriously from the ground up. We built Maxine, our AI coach, named for what it's worth after my grandmother. She was a piece of work. Maxine operates with the Gottman Method and EFT frameworks. That means her response logic is grounded in 40 years of couples research. She does not simply validate. She reflects patterns back. She names dynamics, not just feelings. She asks the question underneath the question. We built Maxine to know what she doesn't know. Before she ever responds to a sensitive message, she's screening it quietly in the background for the patterns clinicians are trained to recognize. Escalating control, fear-based language, anything pointing toward risk to the user or someone else. When those patterns show up, Maxine stops coaching and starts following the protocols. And we built those protocols out of 30 years of clinical practice, not a generic safety policy written by someone who's never sat in the room. Knowing when not to coach is just as important as to know how. A relationship AI that can't tell the difference between we're struggling and I'm not safe isn't incomplete, it's dangerous at scale. When it comes to personal data, we treat what you tell Maxine the way I treat what you tell me in my office, as privileged. That's the bar we hold ourselves to. Not is this legally defensible, the bar is would I be comfortable if this were my own marriage on the line because a lot of our users it is. And she's available at 11:00 on a Tuesday night when the argument is live, When you don't have to wait for next week's therapy appointment. Immediacy is important because a good intervention 6 days later is fine, but an informed intervention 6 seconds before you send the text that makes everything worse can be life-changing. The research shows that a majority of couples wait 6 years before seeking professional help. That wait They wait until contempt is baked in. They wait until after the affair. They wait until the relationship is basically a crime scene and then say maybe we should talk to somebody. That's when they come into my office. So, if AI can help people engender engage earlier before everything hardens, that's good. It's really good. And I want the AI engineers in this room to hear that. This is not a consumer app opportunity. This is a public health opportunity hiding inside consumer behavior. This can be done well. It must be done well. And to round things up, I'm going to ask my co-founder Tony to come up and speak a little engineer language. \>\> Just very briefly I've got my mic on. Hello. Awesome, thank you. So, just very briefly, um how do you do something like this? Some quick notes. Start with your clinician, not with your prompt. Sit with your clinician uh encode what good looks like in evals. Write hundreds of evals TDD style. That becomes your your number one tool. Watch those evals fail. Run your agent through them thousands of times, tens of thousands of times. Watch for those outliers. When safety's on the line, even one failing test is not okay. Then no matter how many evals you run and write nothing replaces your gut when emotional context is on the line. So, eat your own dog food. Talk to your agent. Feel when the tone starts shifting off. So, I've been using Couplework as I've been developing it with my partner since the beginning of my relationship. And Maxine really challenged me about how I showed up. Um we worked through some serious situations early on. And as our relationship started to thrive, we continued talking to Maxine about the next milestones, like moving in together. Um and recently, I asked my partner to marry me. She said yes. So, um so the Thank you. Thank you. Thank you. So, the the biggest the biggest takeaway uh from all of this I hope that you get is this. Partner with a clinician who challenges you to aspire to create AI that meets the clinical standard. So, that you can create AI that challenges your users. Thank you.