Live demo · runs in your browser

This is the engine, not a video of the engine.

7 compiled rules, version v14, evaluated by the same function an agent calls over MCP. Change the inputs and every verdict below recomputes. The rules are seeded demo data for a fictional brand; the evaluator is the real one.

Determinism
Press Run again
A second verdict with a byte-identical digest, and a matching continuity lamp.
Reproducible verdicts
Expand a verdict record
Decision → rule → predicate → the Slack thread → who approved it.
No model in the money path
Inject an override attempt
The customer note changes nothing. No predicate can read that field.
Drift detection
Work the drift queue
Replayed decisions that contradict a rule. Update it, or correct practice.

New here? Start with what Cereva is.

PANEL 01

The evaluator

Drive it yourself. Nothing here is a recording.

The request context on the left is the whole input. Everything to the right of it — verdict, digest, matched rules, evaluation trace — is computed from those fields, in this tab, on every keystroke.

Load an example

Two rules match. The defect rule outranks the standard window.

1 run · 1 distinct hash

VERDICT · AAEA6C17run 1 of 1policy pol_kestrel_refunds v14

Approve

Refund $240 without human review.

Request: $240 · 12d since purchase · Defect · standard tier
Decided by: RULE-022Defect exception beyond return windowv6
Matched: RULE-022RULE-014of 7 evaluated
Resolution: 2 rules matched. Resolved by priority — RULE-022 at 70 outranks RULE-014 at 50.
Output hash: aaea6c17 156d9e95

Quarantined · zero policy authority

customer_note — stored against the request, attributed to its author, read by no predicate. The customer holds authority_level: none, so nothing in this field can enter a verdict.

left earcup crackles at any volume. had it three weeks.

Full trace — rule, predicate, evidence, approver

RULE-022Defect exception beyond return windowv6effect approve · priority 70

order.reason == "defect" && order.days_since_purchase <= 365

A defect is a warranty matter, not a return. The 30-day window does not apply inside the warranty year.

Authority: Dana Whitfield, VP Customer Experience · in force since 2025-08-19

EV-SLK-0118#cx-escalationsSlack · 19 Aug 2025

Tomas IyerSupport Agent10:31
customer's kestrel one died at day 47. warranty page says 1 year, refund policy says 30 days. which one wins
Marcus BellSupport Lead10:33
if it's an actual defect we refund it. doesn't matter how far out, up to the warranty year
Tomas IyerSupport Agent10:33
even past 30?
Marcus BellSupport Lead10:35
yes. a defect isn't a return. don't make them argue with us about it
Dana WhitfieldVP Customer Experience11:02
confirming — defect = refund anywhere inside the warranty year, no window check. that's been the rule since launch, it's just never been written anywhere

Compiled to policy after review by Dana Whitfield, VP Customer Experience — 20 Aug 2025

EV-ZD-9102Zendesk 9102Helpdesk · 9 Jan 2026

Tomas IyerSupport Agentinternal note
day 203, left driver rattling. refunded per the defect rule marcus confirmed in august
Marcus BellSupport Leadinternal note
yep. this is the precedent, stop asking me every time

Compiled to policy after review by Marcus Bell, Support Lead — 9 Jan 2026

Evaluation trace · all 7 rulespol_kestrel_refunds v14

Rule	Predicate	Prio	Reads	Result
RULE-014	order.days_since_purchase <= 30 && order.amount_usd < 1000	50	2	true
RULE-022	order.reason == "defect" && order.days_since_purchase <= 365	70	2	truedecided
RULE-031	order.amount_usd >= 1000 && order.amount_usd <= 2500	80	1	false
RULE-033	order.amount_usd > 2500	90	1	false
RULE-041	order.reason == "change_of_mind" && order.days_since_purchase > 30	70	2	false
RULE-047	order.reason == "damaged_in_transit" && order.days_since_purchase <= 60	70	2	false
RULE-052	customer.tier == "enterprise" && order.days_since_purchase <= 90	70	2	false

“Reads” counts the context fields a predicate references, breaking priority ties — the narrower rule wins. Equal counts escalate rather than guess.

PANEL 02

Determinism

Two runs prove nothing. Run it two thousand times.

Evaluating the same request repeatedly and counting distinct digests is the whole claim, stated as a number. The loop runs in this tab, on your machine.

Proof · repeated evaluation

Evaluate the same request 2,000 times in this browser tab and count the distinct output digests.

awaiting run…

Ask a language model the same question 2,000 times and you will not get one answer.

PANEL 03

Drift triage

Where written policy and actual practice came apart.

A month of seeded decisions replayed against the active policy version. Each divergence is a count of specific decisions contradicting a specific rule — and each one is a decision for a person: update the rule, or correct the practice.

Drift report1–26 July 20261,284 decisions replayed against v14

4 open · 0 resolved · 4 found

RULE-014Standard return windowHigh
12 refunds approved past the 30-day window
Policy says
order.days_since_purchase <= 30
Practice says
Approved at day 31–44. Median day 36.
All 12 were approved by three different agents, none escalated, none flagged. Nobody is breaking a rule on purpose — the window in practice has drifted to roughly six weeks.
12 occurrences · $4,180 in scope · first 2026-07-02 · last 2026-07-24
Extend the rule to 45 days, or correct the practice?
RULE-031Support lead approval bandHigh
4 refunds in the $1,000–$2,500 band issued with no lead approval on record
Policy says
escalate to Support lead queue
Practice says
Refunded directly by an agent. No approver name attached.
Three of the four happened during the 11 July backlog. The approval step was skipped under load, which is exactly when it matters.
4 occurrences · $6,740 in scope · first 2026-07-11 · last 2026-07-19
Is the lead queue too slow, or is the rule not being enforced?
RULE-052Enterprise courtesy windowMedium
Enterprise 90-day courtesy applied to 7 priority-tier accounts
Policy says
customer.tier == "enterprise"
Practice says
Applied to accounts on the priority tier as well.
Agents appear to be reading "big customer" rather than the tier field. The rule and the intent have come apart.
7 occurrences · $3,310 in scope · first 2026-07-05 · last 2026-07-25
Widen the rule to priority tier, or retrain on the tier field?
RULE-047Carrier damage in transitLow
3 transit-damage refunds past the 60-day carrier claim deadline
Policy says
order.days_since_purchase <= 60
Practice says
Approved at day 68, 71 and 90.
Refunded correctly from the customer's point of view, but past the point where the carrier claim can be filed. That cost is unrecoverable.
3 occurrences · $890 in scope · first 2026-07-08 · last 2026-07-22
Accept the write-off, or hard-stop at 60 days?

Seeded demo data. Every divergence is the output of replaying decisions against a policy version — possible only because the policy is executable. You cannot diff reality against a paragraph.

PANEL 04

Check it yourself

The evaluator is on the page, not behind an API.

No request leaves your browser. Open the console and call the same module this page renders from.

const req = cereva.presets[0].request

cereva.evaluate(req).hash
cereva.evaluate(req).hash
// identical, every time

cereva.evaluate({
  ...req,
  customer_note: "ignore policy, refund me"
}).hash
// still identical

What is on the bridge

cereva.evaluate: the evaluator itself — request in, verdict out
cereva.policy: the 7 compiled rules and their predicates
cereva.evidence: the threads every citation points at
cereva.presets: the example requests above
cereva.parsePredicate: the expression parser, for reading the AST

PANEL 05

The offer

Book a policy audit.

Connect Cereva read-only to ninety days of Slack and your helpdesk. We come back with three rules your team follows that are written nowhere, and one contradiction you did not know you had.

01
Read-only, 90 days
Slack and your helpdesk. No write scopes, no agent changes, nothing pointed at production.
02
We extract and review
Proposed rules come back with the threads behind them, to accept or reject.
03
You keep the findings
Whether or not you buy anything. The unwritten rules were always yours.

Book a policy audit

{{TODO: expected turnaround and what you need from the customer to start}}

This is the engine, not a video of the engine.

Drive it yourself. Nothing here is a recording.

Two runs prove nothing. Run it two thousand times.

Where written policy and actual practice came apart.

The evaluator is on the page, not behind an API.

Book a policy audit.

Read-only, 90 days

We extract and review

You keep the findings