Operating an AI agent as a custodian of your work. Bounded authority on your behalf, accountable for what it does, keeping what you hand it over months of unattended operation.
Everyone using these tools climbs the same ladder. Rungs one to four teach the agent to act. Rungs five and six are about what it is allowed to do when nobody is looking.
Below the line, a mistake is an output you catch. Above it, a mistake is an action nobody caught. The loop gives you unattended execution. It says nothing about unattended authority.
Trust cannot come from how confident an agent sounds. So trust is made testable.
Before any real action, the agent writes a falsifiable prediction: a claim, the exact check, a baseline, a horizon. It goes to an append-only outcome ledger. Later a deliberately dumb verifier settles it, true or false.
Authority becomes a meter read per model and per task class. It is designed to widen as predictions hold and narrow the moment they slip. No certificate to bank. "Autonomous" and "unsupervised" are different words, and the distance between them is what gets earned.
Today the meter runs in shadow mode: it scores, it does not yet move permissions. The essay keeps the honest status.
Most are applications of patterns other people named. The outcome ledger is the new part.
A blast-radius boundary around what an unattended cycle may do. Reversible work runs free; irreversible work is staged for a human, until it is earned.
Agent-authored predictions, settled by a dumb verifier, feeding the trust meter.
Knowledge durable across sessions and machines, not re-explained every morning.
A cheap deterministic gate every cycle; a capable model only when there is real work.
Taint, then availability, capability, cost. A multi-provider council for load-bearing calls.
The agent's whole working state as plain files, committed every cycle. Lose the machine, clone, relaunch.
A discipline and a stack, not one binary, the way SRE is a set of practices and tools rather than a single repo.
The hub: the manifesto, the core idea, and a map of the components below.
github.com/eprouveze/stewardship-engineeringAn autonomous work loop for a Claude Code session. Wakes itself, reads ground truth, advances one item per tick inside a hard envelope, logs every tick, and queues anything irreversible to a human.
github.com/eprouveze/heartbeatEarn-as-you-route model selection: a taint, availability, capability and cost cascade, a multi-provider council, and a falsifiable outcome ledger that earns autonomy per model and task class.
github.com/eprouveze/rightmodelPersistent memory as a git-native build artifact. Writes are commits, CI indexes and embeds, every machine is a disposable replica. No machine is primary.
github.com/eprouveze/anamnesisIn fragments, plenty of people got here first. What looks unclaimed is the synthesis, and the pre-action falsifiable prediction settled by an independent verifier.