Date Compiled: 2026-04-28
Type: concept — superada
Domain: Factory Overviews
Description: SuperAda is the enterprise-scale multi-agent system built by Kelly (Austen) — a crew of 7 agents plus 4 meta-crons running 136+ autonomous tasks.

SuperAda Overview

SuperAda is the enterprise-scale multi-agent system built by Kelly (Austen). It is named after Ada Lovelace and structured after the Star Trek crew — each agent has a specific role, a specific model, and a specific capability. The system runs 136+ active autonomous tasks at any given time.

What SuperAda Is

SuperAda is not a single agent. It is a crew of 7 agents (Ada, Spock, Scotty, Geordi, Zora, Midas, Book) plus 4 meta-cron agents that manage the fleet. The agents are named after Star Trek characters not as a gimmick, but because each name maps to a real capability: Spock is reasoning, Scotty is execution, Geordi is vision, Zora is data, Midas is financial, Book is ethical.

The architecture is governed by the autonomy-policy-v3 — a formal policy for what agents may do without human approval. The shared cognitive substrate is the world-model (world.json), which all agents read and write to coordinate without sharing memory.

Key Concepts

  • him-model (Human-in-the-Middle): The cognitive separation between human intent and agent execution. Ada handles everything between.
  • isc (Inference Selection Criteria): A standard for writing task criteria. Governs what model handles what task.
  • meta-crons: 4 agents managing the ~98-cron fleet — Cron Watcher, Error SOS, Token Budget, Auto-Lobster Converter.
  • lobster-pipelines: Typed JSON envelope + resumable approval gates for complex multi-step autonomous tasks.

How It Relates to Kelly Router

Kelly Router uses a 3-agent crew (Carson, Sally, Amelia). SuperAda uses 7+ agents with a formal architecture. Both follow the principle that agents should be isolated and task-specific. SuperAda's contribution is the formalization: the 7-agent-crew-topology, the autonomy policy, the world model, and the ISC criteria.

Source Articles

superada-enterprise-crew, superada-multi-agent-architecture, superada-enterprise-operations, him-model, autonomy-policy-v3, isc, world-model, meta-crons, lobster-pipelines, 7-agent-crew-topology

  • 7-agent-crew-topology — SuperAda's 7-agent Star Trek crew (Ada, Spock, Scotty, Geordi, Zora, Midas, Book) is the canonical 7-agent-crew-topology reference implementation
  • world-model — world.json is the shared cognitive substrate all 7 agents read and write to coordinate without sharing memory
  • him-model — Ada handles everything between human intent (Henry) and agent execution: the cognitive HiM separation made explicit in the crew architecture
  • isc — Inference Selection Criteria governs what model handles what task: the standard for writing task criteria in the SuperAda crew
  • meta-crons — 4 meta-cron agents (Cron Watcher, Error SOS, Token Budget, Auto-Lobster Converter) manage the ~98-cron fleet
  • lobster-pipelines — typed JSON envelope + resumable approval gates for complex multi-step autonomous tasks
  • autonomy-policy-v3 — the formal operating policy governing what agents may do without human approval