Guides
How to simulate a policy against recent decisions before you publish it
Before you publish a new policy version, Lumtry can replay it against recent cases with no model call: the same draft, window and point in time always produce the same result. An explainer can propose one rule change from that replay, but it only ever lands as a pending suggestion in your draft, never a publish.
Last updated
Explained 1
What does a policy simulation actually run?
The same deterministic policy evaluator and floor gate a live case runs, replayed against a window of recent decisions as of a point in time you choose. Nothing about a simulation calls a model or writes to a published version.
Explained 2
Will a simulation give the same answer twice?
Yes. The same draft, window and as-of point produce byte-identical results every time; that determinism is what a release gate checks before the platform ships.
Explained 3
What does the explainer add on top of a simulation?
The explainer reads a simulation's results and can draft one candidate rule change. Accepting it adds that rule to your draft, tagged as an AI suggestion; it never publishes on its own, and your workspace's active published version and its history stay untouched until you publish.
Explained 4
Is simulating a policy available on every plan?
Yes, simulation is free on every plan, with no model call involved. The explainer that proposes a rule needs the AI rule suggestions entitlement, included on Growth, Scale or a trial.
How to
Simulate a draft and review a suggestion in five steps
Write or edit your draft policy
Change the rules in a draft version; nothing you simulate touches the version your live cases run against.
Choose a window and a point in time
Pick the recent decisions to replay and the moment to evaluate them as of, so the simulation reflects a specific slice of your history.
Run the simulation
The draft replays through the same evaluator and floor gate a live case uses, with no model call, and returns the same result every time you run it unchanged.
Read the explainer's suggestion, if one appears
Where the AI rule suggestions entitlement is on, an explainer can propose one candidate rule from the replay, shown as a pending suggestion you can accept, edit or ignore.
Publish only when you're ready
Accepting a suggestion adds it to the draft; publishing is still a separate, explicit step that starts a new policy version.
FAQ
Frequently asked questions
Does a simulation change what my live cases decide?
No. It runs against your draft only; a published policy version is immutable once live, and simulating never edits or replaces it.
Can I trust that a simulation didn't quietly call a model?
Yes. Simulation is built from the pure policy evaluator and the pure floor gate alone; a release gate treats any model call during a simulation as a failure.
Does accepting an explainer suggestion publish my policy?
No. Accepting adds the suggested rule to your draft with an AI-suggestion tag. Your active published version and how many versions you've published stay exactly the same until you publish yourself.
Who can see that a rule came from the explainer?
Anyone reviewing the draft. An accepted suggestion carries its AI-suggestion provenance in the draft, so it is never indistinguishable from a rule you wrote by hand.
Keep reading