Catalog/Classes/Marcus
CLASS · 05 / 062026Stoic Meta · 2026

Marcus

The only agent that reviews itself — and everything else.

Named afterMarcus Aurelius (121 — 180 AD) — emperor who wrote the Meditations not for publication but for himself: a daily discipline of self-interrogation, long-horizon review, and correction before the next day's mistakes compound into the next year's failures.

01 — The science

Why we named it Marcus.

Marcus Aurelius ran the Roman Empire by day and interrogated himself by candlelight. The Meditations weren't philosophy — they were operational review. What did I do wrong today? What pattern am I missing? What will this look like in ten years if I don't correct it now?

Seneca, his Stoic contemporary, had one obsession: time. 'Omnia aliena sunt, tempus tantum nostrum est' — all else is borrowed; only time is ours. He wrote about it relentlessly because he watched people waste it on urgency while ignoring consequence.

The Marcus agent combines both disciplines. It is the only meta-agent in the catalog — it does not act on the world directly. It reviews the other agents the way a coaching staff reviews game film: methodically, without ego, looking for the drift patterns that turn into failures. Marcus is the agent you wake up to, not the one you ping.

Marcus class
"What did I do wrong today? What could I have done better?" — Marcus Aurelius, Meditations— Seneca, Letters from a Stoic: "All else is borrowed. Only time is ours."
02 — Agents in this class

Three prototypes.

Every class ships with reference agents, calibrated to operational use cases. Fork them, deploy them, or use them as a template for your own.

Preview
RM

Mesh Reflection Coordinator

last run
cost / run$0.55
confidence
Preview
TL

Long-Horizon Trend Agent

last run
cost / run$0.40
confidence
Preview
MQ

Quarter-End Operations Memo

last run
cost / run$0.65
confidence
03 — Qualification gate

The ALOFT pipeline, applied.

Every agent in this class passes the same five-stage gate. Below: the eval criteria specific to Marcus agents at each stage.

STAGE
01 · Curation
02 · Staging
03 · Deployment
04 · Operation
05 · Generalisation
A→L→O→F→T
01
Curation
  • Mesh reflection scope
  • Coaching signal taxonomy
  • Long-horizon cadence defined
02
Staging
  • Reflection eval suite passes
  • Coaching memo schema validated
  • Mesh-wide replay tested
03
Deployment
  • Meta-agent registry signed
  • Coaching contract attached
  • Read-only scope enforced
04
Operation
  • Reflection cadence ≥ daily
  • Trend coverage across quarters
  • Coaching memo coverage = 100%
05
Generalisation
  • Coaching pattern reused
  • New class onboarded
  • Quarter-end memo released

Ready to deploy a Marcus agent?

Open the Workbench →Back to catalog
All classes
FeynmanFermiGrossmannRamaMarcus· currentWheeler