A live feedback loop for the way you think out loud. Real conversations with figures from history, scored as you talk on clarity, depth, follow-through, and presence. The conversation is the lesson. The meter is how you see it.
Historical figures hand-tuned, character by character. Marcus Aurelius is not Cleopatra is not Einstein. The voices are calibrated against their own writings and against research on how conversation actually goes deep.
Pick one and the conversation begins. The meter starts at fifty.
Every utterance is scored across 22 behavioral signals: depth, follow-through, specificity, emotional presence. The meter updates in under a millisecond.
The meter does not grade you, it shows you. A factual question barely moves it; an interior question, the kind that requires the figure to actually think, moves it fast.
After each conversation, the topics you've explored light up. Threads that run deep, questions you left open, territory you haven't reached yet.
The tapestry grows with every session. A visual record of the thinking you've done, unique to you and the figures you've talked with.
Every session ends with an Arc Score built from four factors. Two progressions track growth on different axes. Mind Levels move with your average score across all conversations. Relationship depth advances with each figure individually, from Acquaintance to Familiar to Conversant.
The figure who knew you existed on session one knows you well by session twenty.
Three layers, all designed against decades of research on dialogue, learning, and retention. The score appears on the same screen as the conversation, visible to the speaker as they talk. Each session builds on the last, and each historical figure speaks from their own writings.
A live score on the same screen as the avatar. Twenty-two signals measure the depth, follow-through, and presence of every turn you take. Five named zones tell you where the conversation is, from Surface Skim to Flow State. Built on published research on what makes dialogue go deep.
Each character remembers what you talked about last time. As your conversations go deeper, they reveal more substantive material. The conversation itself becomes the lesson. Memory across sessions turns it into practice that compounds.
Hand-built character by character. Each one draws from their own writings: Einstein from his relativity papers, Curie from her radium memoir, Douglass from his Narrative. The voices, the personality, the worldview, all proprietary work calibrated against the historical record and against decades of research on conversation.
The 22-signal scoring model is built on published methodology. The memory architecture is grounded in Aron 1997 and Altman and Taylor 1973. The vendor partnerships powering voice, avatar, and infrastructure are live.