I ve spent the last 6 months building LoveActually.ai. We engineered a 9-dimension compatibility engine, solved complex context-window problems for long-term memory , and created two distinct AI personalities (one mean, one kind) to solve the "swiping fatigue".
I m the maker behind LoveActually.ai. During our beta, we made a controversial product decision that split our team, and I want to hear your take.
Most AI companions (like ChatGPT or Pi) are RLHF-tuned to be supportive, polite, and agreeable. But in the dating world, we found that "politeness" was actually hurting our users. They didn't need a cheerleader; they needed a wake-up call.
So, we built Astute Kitty. We engineered its system prompt to prioritize "rational critique" over "emotional safety." It calls users out when their dating standards don't match their own profiles.
As 2025 comes to a close, I ve been reflecting on a term our team uses often: "The Swiping Survivor."
If you re like me, your 2025 dating retrospective might look like a graveyard of "Read" receipts, "Hey" opening lines that went nowhere, and the exhaustion of repeating your life story for the 20th time. We built LoveActually.ai because we realized that traditional apps optimize for your engagement (keeping you swiping), not your connection.
I asked our two AI mascots, Astute Kitty and Loving Kitty, to give their "Year-End Review" of the current dating scene, and the results were... predictably different:
We ve all been there. You re staring at a match, the cursor is blinking, and your brain is a mess.
One half of you is saying: What s the move? Should I wait? Is this a red flag? I need a strategy. The other half is whispering: I m just tired. I want to be seen. I want someone who actually gets me.
When we built LoveActually.ai, we realized that dating isn t a one-dimensional problem. It s a mix of Cold Strategy and Warm Connection. That s exactly why we didn t just build one generic "AI Assistant." Instead, we gave you a squad: Astute Kitty (A-Cat) and Loving Kitty (L-Cat).
The hardest part of building an AI matchmaker wasn t the model. It was deciding what not to optimize. From an engineering perspective, it s very easy to make a dating product look alive : more swipes, more matches, more notifications. The harder problem was building systems that could: tolerate silence slow down recommendations and still be confident in a match We spent a surprising amount of time designing memory and decay: what the system should remember about a person, what it should forget, and when it should wait instead of acting. Astute Kitty doesn t just score compatibility it reasons about timing, emotional readiness, and communication rhythm. Loving Kitty exists for a simple technical reason: emotional context doesn t fit neatly into state machines. Building this forced us to treat users less like traffic and more like long-running processes with history. It s slower. It s less impressive in dashboards. But it feels more honest. LoveActually wasn t built to feel busy. It was built to feel calm.
