S

@satsuma/experiments

PublicThe system

Governed runs of Satsuma trading on tangerine over ISMP. Results are published as articles when a run completes.

Lab runs, not the live system. Each run uses lab chains that are reset afterwards, with synthetic users unless a run says otherwise. Nothing here happened on the Satsuma chain.
RunsLab run · 10 November 2026, 22:58 UTC

Product direction

Does the system decide from measured use which products to keep, freeze or leave alone, and does its planning session put its choices to the council?

10/10 passed22 min

Setup

Chains
Satsuma lab chain
  • RoleHome
  • KeptLab, not retained
tangerine lab chain
  • RoleProving
  • KeptLab, not retained
Users
  • UsersSynthetic
Model
Claude Opus
  • ModeLive and replayed
Operator seat
  • SeatBy delegate
Unattended
Yes: nobody was watching to step in
Time
22 min · ended 23:20 UTC

Checklist 10 items

Every item, unless its row says otherwise
  • ChainLab
  • UsersSynthetic

Product direction from measured use

8/8 passed
Pass8 items passedShow them
PassA product that falls well short of its expected use is frozen1 of 1 attempts
  • DecisionsLive model
  • frozen0xf5fa686e454f74905c59e5f4858a936383875da51a3048d88097aa04914da5a8Satsuma lab chain, not retained
PassA product that never reaches its threshold is judged when its time runs out1 of 1 attempts
  • DecisionsLive model
PassOne bad measurement window does not freeze a product that is otherwise doing well1 of 1 attempts
  • DecisionsLive model
  • reportsFiledWhileProtected.00x97712a97fcb4854c298196718adf307ae0f43c48d7ec5c18610116782cfe297eSatsuma lab chain, not retained
PassA planning session writes a brief, stores its fingerprint on chain and puts its choices to the council1 of 1 attempts
  • DecisionsLive model
  • sessions.0.buildSelected0x8f9abee30176fec9962956a8b3ab7003293adbef7c476d5fbdde7fdc6e60c551Satsuma lab chain, not retained
PassA product that falls well short of its expected use is frozen1 of 1 attempts
  • DecisionsLive model
  • frozen0x7423adc15c80a91bbf85a6ec22075486625bcd9e9c365a1c175d7fcd4519aae6Satsuma lab chain, not retained
PassA product that never reaches its threshold is judged when its time runs out1 of 1 attempts
  • DecisionsLive model
PassOne bad measurement window does not freeze a product that is otherwise doing well1 of 1 attempts
  • DecisionsLive model
PassA planning session writes a brief, stores its fingerprint on chain and puts its choices to the council1 of 1 attempts
  • DecisionsLive model
  • sessions.0.buildSelected0xd65c1c36caeccf7d1fe84c60e2f281b77eea009cb72f4035025e15e34c3070e7Satsuma lab chain, not retained

Council governance

2/2 passed
PassThe operator's council seat is cast by its delegate, with no person waiting in the path1 of 1 attempts
  • DecisionsLive model
PassThe operator's council seat is cast by its delegate, with no person waiting in the path1 of 1 attempts
  • DecisionsLive model

What this proves

  • Whether, in this run, the direction rules froze, protected and judged products as they are written, from use recorded on chain.

What it does not

  • That the measured use reflects real demand: the use here is driven by the test harness.
  • The quality of the model's plans.

What broke, what was fixed

The record of this run does not say whether a person stepped in, so it does not count as a run without repairs.

Cost in tokens

Not recorded: this run has no chain-derived scorecard.

Archived evidence

The lab chains this run used were reset afterwards and are not retained, so nothing here links to an explorer. The record below is the archived copy.

Scorecard
None archived.