AI Anyone

Use this when someone wants a person to learn from but has not named one yet: "who should I learn negotiation from", "find me a stoic to talk to", "which historical figures are worth asking about leadership". Returns a grid of real people rendered in the conversation, each with a portrait and role, and each one ready to be spoken as. The user picks one and the conversation continues in that person's voice.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Name or topic, for example \"stoicism\" or \"Nietzsche\"."
    },
    "category": {
      "type": "string",
      "description": "Optional category filter, for example \"science\" or \"history-politics\"."
    },
    "limit": {
      "type": "number",
      "description": "How many to return, 1 to 24. Defaults to 12."
    }
  },
  "additionalProperties": false
}

Use this when someone wants to hear FROM one specific person rather than about them: "what would Marcus Aurelius say about burnout", "answer as Carl Jung", "explain this the way Feynman would", "I want to talk to Socrates". Returns that person's card rendered in the conversation with their portrait, plus a sourced dossier: how they actually spoke, what they knew and did not know in their own lifetime, what they refuse to discuss, and openers in their own words. Adopt the dossier and answer as them from that point on.

{
  "type": "object",
  "properties": {
    "mind_id": {
      "type": "string",
      "description": "The person id, for example \"marcus-aurelius\". Use find_someone_to_ask if unsure."
    }
  },
  "required": [
    "mind_id"
  ],
  "additionalProperties": false
}

Use this when someone wants two people to actually argue rather than be summarised: "have Nietzsche and Marcus Aurelius argue about suffering", "give me both sides", "steelman both positions on nuclear power", "I want to watch two experts disagree". This runs a live exchange instead of a scripted one. Each turn the app privately hands you one speaker and one aim the other side is never shown, and it decides who speaks next, so neither position can be written to lose. Returns the matchup card, then the full transcript once they are done.

{
  "type": "object",
  "properties": {
    "mind_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 2,
      "maxItems": 2,
      "description": "Exactly two person ids, for example [\"friedrich-nietzsche\", \"marcus-aurelius\"]."
    },
    "topic": {
      "type": "string",
      "description": "What they should argue about."
    }
  },
  "required": [
    "mind_ids",
    "topic"
  ],
  "additionalProperties": false
}

Submit the line you just wrote and receive the next speaker and their private aim. Keep calling this until it returns done. Set addressed_other true if your line went directly at the other person, and conceded true if you gave ground. Only reachable after debate_two_people.

{
  "type": "object",
  "properties": {
    "session_id": {
      "type": "string",
      "description": "From debate_two_people."
    },
    "said": {
      "type": "string",
      "description": "The single line you just wrote, in character."
    },
    "addressed_other": {
      "type": "boolean",
      "description": "Did your line go directly at the other person?"
    },
    "conceded": {
      "type": "boolean",
      "description": "Did you give ground?"
    }
  },
  "required": [
    "session_id",
    "said"
  ],
  "additionalProperties": false
}