It expires in weeks, not years
A prompt that worked in January behaves differently in July. The model changed underneath it and nobody told you.
How it works
Doestep answers one question: does this still work, on this model, right now? It answers that with evidence anyone can audit. First, why that question needs asking.
One object carries the whole story: a fact, computed from real runs.
The problem
A prompt that worked in January behaves differently in July. The model changed underneath it and nobody told you.
“I built an agent that 10x’d my workflow.” Great. Can anyone else run it and get the same result? Usually not.
The internet is full of AI skills nobody can verify. Claims are cheap. A logged reproduction is not.
A playbook gets proven, a new model breaks it, the community proves it again. The model-release event is the heartbeat.
An author writes a testable playbook and freezes it as an immutable version.
Other people actually run it, on a real model, with real inputs.
Each run is an append-only repro report: worked, worked-with-changes, or broke.
Confidence is computed from distinct reports, never written by hand.
The model registry gets a new row. This is the heartbeat.
Every affected playbook flips to “not yet verified on the latest model.”
Doesteppers race to re-run the top playbooks. The loop repeats.
The five things it’s built on
Every version is frozen. A report is meaningless unless it’s pinned to the exact version that was run, so editing in place is impossible by design. Versioning isn’t a feature; it’s what makes verification trustworthy.
Models, versions, and release dates. Adding a row, a new model release, is what flips affected playbooks to “not yet verified on the latest.” Freshness is relative to models, not the calendar.
Every run is an event: who ran it, which version, which model, and the result. Never edited, never deleted. Corrections are new reports. Append-only means every badge is auditable back to its evidence.
Derived from reports, the model registry, and time decay. Recomputed on every new report, on model release, and nightly. A stored badge could drift from its evidence. Derived state can’t lie.
A Doestepper’s standing is computed from their report history with a weighted function. Gameable only by doing real work, and re-tunable later with no data migration.
The badge, up close
This is something no tutorial site, GitHub repo, or Discord has. Here’s what each part of it says.
The states
Same object everywhere: on the site, in a README, in a tweet. Mono for the data, status color for the fact.
Built in from day one, because honesty is the brand.
Join the first Doesteppers and be there when the next model ships.