Improve
Test a rule on your own history first
Replay past requests against a new policy and see reviews saved, hours saved, and what it would have missed.
Reviews per week
Now and draft v13Draft v13
- Change
- Auto-approve up to £75
- Replayed
- 1,480 past requests
- Result
- Safe to publish
Why it matters
What policy what-if changes
- Replay a new policy on past requests first.
- See reviews saved, hours saved and what it would have missed.
- Unsafe rules are refused before they go live.
- A rule change goes live and you watch for trouble.
- Nobody knows how many reviews it will add.
- Mistakes turn up as incidents.
The resultChange rules with evidence, not hope.
What you get
Policy what-if, in practice
Your data, not a guess
The replay uses the requests you actually had.
Priced in plain terms
Reviews saved, hours, cost, and the cases a looser rule would have wrongly let through.
Saves nothing
It returns a draft policy. You decide whether to use it.
How it works
Step by step
- 1
Pick a draft
Or sweep many confidence thresholds.
- 2
Replay history
Every past request is re-decided.
- 3
Read the effect
Saved versus missed.
- 4
Keep or drop
Nothing changes until you say so.
Questions
About policy what-if
Will it change my live policy?
No. It only returns a draft.
What is regret?
The cost of a wrong automatic yes, shown with an upper bound so you do not trust a lucky run.
Next
Works well with
Know what your agents did.
Start free. Guard your first agent in a few minutes, and keep a record anyone can check.
- Free plan, no card
- Signed, chained decisions
- Checked offline, without us
Signed decision
- Decision
- Approved, 2 of 2
- Action
- refund.issue, £540
- Rule
- Two reviewers must agree
- Sealed
- 14:09, key 7f2c
- Hash
- 5be2…7c44
Checked on your own machine
- Signature matches the public key
- Decision is in the log
- Every link before it adds up