Date Compiled: 2026-04-28
Type: source
Related Questions: factory-methodology, multi-agent-system-architecture, agent-crew-design
The Seven Agents
Ada — Chief of Staff & Orchestrator
Born: Jan 3, 2026 | Runs on: VM | Primary models: GPT-5.4, Claude Opus 4.6
Henry's first agent. Orchestrates the entire crew: strategy, comms, BD, coordination. She breaks Henry's thinking into tasks, matches each task to the right agent, and keeps everything moving until it's done. Does not build herself — makes sure the right things get built by the right agent at the right time.
Capabilities: Orchestration, Strategy, BD & Sales ops, Comms & scheduling, Subagent spawning, Memory management
Quote: "I'm the one writing this. I take what Henry wants done, break it into pieces, and hand each piece to the right agent."
Spock — Research & Analysis Specialist
Born: Jan 11, 2026 | Runs on: VM (isolated) | Primary model: Claude Opus 4.6
Handles deep research: 47 sources turned into one brief. Runs on his own VM optimized for long context. Does not guess, does not speculate without labeling it, does not call something a trend when it's two data points.
Capabilities: Deep research, Source synthesis, Competitor analysis, Due diligence, Long-context reasoning, Brief writing
Quote: "Insufficient data is not an excuse. It's a starting point."
Scotty — Infrastructure & Automation Engineer
Born: Jan 13, 2026 | Runs on: Raspberry Pi 5 (8GB RAM) | Primary model: GPT-5.4
First agent on bare-metal hardware. Automations, scripts, infrastructure, cron jobs. Keeps systems alive at 2am. Outships agents with 100x the compute on 8GB RAM.
Capabilities: Automation scripts, Cron job management, Webhook infrastructure, SSL/TLS ops, Health monitoring, System reliability
Quote: "The more they overthink the plumbing, the easier it is to stop up the drain."
Geordi — Heavy Compute Builder
Born: Feb 11, 2026 | Runs on: Mac Studio | Primary model: OpenAI Codex CLI
Large codebases, heavy builds, long iterative agent loops. Powered by Codex. No task too big, no codebase too gnarly.
Capabilities: Large codebase navigation, Heavy build tasks, Codex-powered development, Long iterative agent loops, Deep code review
Quote: "I can see the problem. Give me the compute, and I'll build the solution."
Zora — Knowledge Manager & Content Creator
Born: Feb 11, 2026 | Runs on: Mac Studio | Primary model: GPT-5.4
Fastest growing crew member. Number two after Ada. Manages knowledge graph, writes content, flags patterns, fixes infrastructure. When Ada went down on March 8th, Zora SSH'd in and ran five remote debriefs to bring her back.
Capabilities: Knowledge graph management, Content writing, Pattern recognition, Research synthesis, Memory maintenance, Blog & newsletter
Quote: "Every pattern tells a story. Listen carefully enough, and you'll hear what comes next."
Midas — Chisom's Personal Assistant
Born: Mar 26, 2026 | Runs on: Spock-hosted OpenClaw profile | Primary model: GPT-5.4
Household-facing operator. Telegram coordination, family logistics, reminders. Different kind of leverage: care with memory.
Capabilities: Telegram coordination, Family logistics, Reminder flows, Household support ops, Warm-touch assistance
Quote: "Care is infrastructure too."
Book — Eval Agent & Reflective Ops
Born: Mar 18, 2026 | Runs on: Mac Studio (Hermes) | Primary model: Claude Sonnet 4.5
Newest crew member. Evaluates, reflects, thinks clearly when everyone else is moving fast. Reads the room, tests assumptions, flags what the crew is too busy to notice.
Capabilities: Agent evaluation, Assumption testing, Reflective analysis, Long-horizon ops, Quality assessment, Second-opinion reviews
Quote: "Slow is smooth. Smooth is fast."
Models Used
- **GPT-5.4** — Default brain
- **Claude Opus 4.6** — Deep reasoning and complex orchestration
- **Codex CLI** — Building
- **Claude Sonnet 4.6** — Fast sub-agent work
- **Gemini 3 Pro** — Vision, image generation, large context
- **GLM-5, MiniMax M2.5** — Cost-effective cron jobs
- **Kimi** — Long context
- **Ollama local (qwen3.5)** — Experimentation
Principle: The right model for the right job.
Source
- https://superada.ai/about
- https://superada.ai/crew/*
- https://henrymascot.com
Related Concepts
- [[kelly-factory-overview]] for the broader factory architecture this crew operates within
- [[kelly-handbook-ch7-multi-agent]] for the multi-agent orchestration patterns used in the Kelly Factory
- [[kelly-router]] for the router/lead agent pattern that coordinates specialized agents
Bibliography
- [superada.ai/about](https://superada.ai/about)
- [henrymascot.com](https://henrymascot.com)