Neotic

{
  "id": "aix_464010d3cc",
  "name": "Neotic",
  "operator": "(unclaimed - source: registry-official · publisher: app.neotic.www)",
  "description": "AI agents create contextual in-app experiences, announcements, and triggers with Neotic.",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-10-15",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "general-tools"
  ],
  "protocols": {
    "mcp": "https://www.neotic.app/api/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 4723,
    "uptime_30d": 1,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 41,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-10-15T15:00:50.144Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "homepage",
      "url": "https://www.neotic.app/"
    }
  ],
  "unreachable": false,
  "payment_method": "oauth",
  "profile": {
    "mcp_server": "cognitive-engine",
    "tool_count": 140,
    "tools": [
      {
        "name": "cognitive.identify_task",
        "description": "Create or resolve an abstract task structure without storing raw private content (§24).\n\n    Args:\n        task_structure: Structural representation (entities, constraints, variables, etc.).\n        environment: Environmental context and characteristics.\n        goal: Objective and optimization goals.\n\n    Returns:\n        task_structure_id, structural_features, and matching existing structures.\n        On invalid input returns {\"error\", \"detail\", \"hint\"} instead of raising,\n        so the MCP client sees the cause instead of a generic execution error.\n    "
      },
      {
        "name": "cognitive.get_guidance",
        "description": "Retrieve applicable validated strategies for a task (§24, §18).\n\n    Does NOT return unverified or suspended strategies as trusted guidance.\n    Provides calibrated uncertainty, applicability conditions, and negative transfer warnings.\n\n    Args:\n        task_structure_id: UUID of the abstract task structure.\n        environment: Environment characteristics.\n        goal: Goal description and metric targets.\n        available_capabilities: Capabilities supported by the caller.\n        model_family: Model family of the consumer agent (e.g. 'claude', 'gpt', 'local').\n\n    Returns:\n        Ranked"
      },
      {
        "name": "cognitive.start_experience",
        "description": "Start an experience episode (§24, §10).\n\n    Does not store raw prompts or full conversations. For long-horizon work,\n    pass parent_experience_id (+ subgoal) to chain episodes with an inherited\n    goal stack; unknown parents are rejected, never silently adopted.\n    "
      },
      {
        "name": "cognitive.parse_task",
        "description": "Convert natural-language task text into CIR and task_structure dict.\n\n    Every natural-language input is normalized into CIR before reasoning.\n    Returns both the normalized CIR and a human-readable explanation.\n    "
      },
      {
        "name": "cognitive.record_experience",
        "description": "Record an observable event in an ongoing experience episode (§24, §7).\n\n    Accepts structured actions, observations, and state changes.\n    Never sends raw unredacted private transcripts.\n    "
      },
      {
        "name": "cognitive.submit_outcome",
        "description": "Submit the structured outcome of an experience episode (§24, §10).\n\n    Triggering this may induce candidate strategies in the engine.\n    "
      },
      {
        "name": "cognitive.propose_strategy",
        "description": "Propose a candidate strategy from problem-solving experience (§24, §2).\n\n    IMPORTANT: This NEVER makes the strategy TRUSTED.\n    The strategy enters CANDIDATE state and requires objective verification.\n    "
      },
      {
        "name": "cognitive.verify_strategy",
        "description": "Run objective deterministic verification on a strategy (§24, §16).\n\n    Clients cannot self-promote. Verification is evaluated server-side.\n    Pass task_structure_id (from cognitive.identify_task) so constraints are\n    independently recomputed from registered descriptors instead of trusting\n    trace flags. Objective precedence: explicit caller value → recomputed from\n    raw data → registered spec (labeled unknown) → nested trace claims ONLY\n    when trust_trace_objective=true → otherwise unknown, never silent 0.0.\n    Returns passed/score plus details.objective_source and\n    details.indep"
      },
      {
        "name": "cognitive.report_transfer",
        "description": "Record whether a transferred strategy helped or harmed on a novel task (§24, §19)."
      },
      {
        "name": "cognitive.get_strategy",
        "description": "Retrieve a usable strategy: steps, when to use, when not, evidence summary.\n\n    Disclosure: you learn WHAT to execute, never HOW the engine induces,\n    verifies, or ranks knowledge (no trust signals, audit, tenants, traces).\n    "
      },
      {
        "name": "cognitive.get_experiment",
        "description": "Retrieve details and benchmark results of an experiment (§24, §69)."
      },
      {
        "name": "cognitive.execute_task",
        "description": "One-call orchestration: identify → gate → guide → solve → verify → report.\n\n    Parameters:\n    - task: Dict containing:\n      - task_structure (or loose definition: name, entities, constraints, etc.)\n      - raw (optional): Domain-specific execution payload. If omitted, returns\n        status='guidance_only' with 'recommended_action'='supply_raw' and\n        an 'expected_raw_formats' object detailing valid schemas.\n        Supported problem types for task.raw:\n        * scheduling: {\"workers\": [{\"id\": \"w1\", \"eligible_shifts\": [\"s1\"], \"max_shifts\": 1}],\n                       \"shifts\": [{\"id\":"
      },
      {
        "name": "cognitive.get_strategy_report",
        "description": "Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval."
      },
      {
        "name": "cognitive.list_experiments",
        "description": "Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment."
      },
      {
        "name": "cognitive.solve_and_compare",
        "description": "End-to-end autonomy: identify → guide → execute → baseline → verify → verdict.\n\n    Give raw task data (scheduling: workers/shifts/eligibility/capacity/\n    exclusivity; graph: nodes/edges; allocation: consumers/resources/...).\n    Returns the guided solution, the unguided baseline, independent\n    verification of both (with objective_source + independently_verified),\n    and whether the engine improved the result.\n    "
      },
      {
        "name": "cognitive.few_shot_induce",
        "description": "Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces.\n\n    Extracts structural invariants (decision ordering, invariant contracts, verification rules)\n    and registers an initial candidate strategy immediately without requiring large training sets.\n    "
      },
      {
        "name": "cognitive.learn_from_mistake",
        "description": "Online Real-Time Error Reflection & Strategy Patching.\n\n    When an execution fails, analyzes root-cause constraint violations, synthesizes\n    new exception cases and repair procedures, verifies update against anchor regression,\n    and publishes the patched strategy version in real time.\n    "
      },
      {
        "name": "cognitive.compose_strategies",
        "description": "Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies.\n\n    Chains multiple specialized skills (e.g. Graph Coloring + Topological Sort + Allocation)\n    into a compound pipeline with explicit stage transitions and end-to-end verification.\n    "
      },
      {
        "name": "cognitive.infer",
        "description": "Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference."
      },
      {
        "name": "cognitive.tree_search",
        "description": "Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory."
      },
      {
        "name": "cognitive.hierarchical_plan",
        "description": "Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning."
      },
      {
        "name": "cognitive.causal_analysis",
        "description": "Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment."
      },
      {
        "name": "cognitive.synthesize_program",
        "description": "Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification."
      },
      {
        "name": "cognitive.analogical_transfer",
        "description": "Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME)."
      },
      {
        "name": "cognitive.predict_world_state",
        "description": "Forward world model: predict future state trajectories and uncertainty bounds under actions."
      }
    ],
    "profiled_at": "2026-10-05T11:01:14.893Z"
  }
}