Catalog/Classes/Fermi
CLASS · 02 / 06v0.4Live · v0.4

Fermi

Precise enough to act on, uncertain enough to be honest.

Named afterEnrico Fermi (1901 — 1954) — physicist famous for back-of-envelope estimation under thin data.

01 — The science

Why we named it Fermi.

Fermi was famous for answering questions no one thought answerable — how many piano tuners in Chicago? — with nothing but logic and back-of-envelope estimation.

The Fermi agent does the same thing with operational data: sparse signals, incomplete records, partial logs. It doesn't wait for clean data. It estimates with principled uncertainty, flags what it can't know, and gives you a number you can act on.

Every Fermi answer comes with bounds. You see the estimate, the confidence, and the assumptions — not because we bolted it on, but because order-of-magnitude reasoning is the contract.

Fermi class
How many piano tuners are in Chicago? Don't guess. Estimate.— Fermi's seminar, University of Chicago
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.

Live
FS

Demand Signal Forecaster

last run4m ago
cost / run$0.22
confidence94.7%
Live
AC

Procurement Spend Deviation Monitor

last run38s ago
cost / run$0.09
confidence96.2%
Staging
ES

Headcount Demand Estimator

last run6h ago
cost / run$0.14
confidence88.1%
03 — Qualification gate

The ALOFT pipeline, applied.

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

STAGE
01 · Curation
02 · Staging
03 · Deployment
04 · Operation
05 · Generalisation
A→L→O→F→T
01
Curation
  • Sparse-signal use case
  • Bounded uncertainty acceptable
  • Calibration target defined
02
Staging
  • Order-of-magnitude eval
  • Bounds tested on holdouts
  • Calibration plot validated
03
Deployment
  • Confidence interval published
  • Estimate shadow-runs ≥ 7d
  • Drift baseline frozen
04
Operation
  • Estimate vs actual MAPE < 12%
  • Calibration drift < 5%
  • Cost guardrail enforced
05
Generalisation
  • Estimator reused across class
  • New signal source qualified
  • Pattern memo published

Ready to deploy a Fermi agent?

Open the Workbench →Back to catalog
All classes
FeynmanFermi· currentGrossmannRamaMarcusWheeler