Audit every claim against your expense policy, evidence each flag with the receipt, card line and rule behind it, and route it to a named reviewer — the agent never rejects a claim itself.
Normalise merchant, date, currency and category, and read the claimant's grade and entitlement.
Reason
03
Test each line against the policy version in force on the date the money was spent.
04
Read receipt, claim and card line together to find duplicates, split claims and missing evidence.
05
Check mileage, per-diem overlaps and VAT/GST reclaim eligibility against the rules for that country.
Decide
06
Raise a flag carrying the rule, the evidence and a reason written for the person being flagged.
07
Rank flags so reviewers see the defensible ones first, and pass the rest through unflagged.
Out
08
Retain the rule version, evidence, reviewer decision and the reason the reviewer gave for it.
09
Write the flag and its evidence only — clearing, rejecting and reimbursing stay with people.
→Product statement
The agent flags and evidences inside the boundaries agreed during implementation; rejecting a claim, and anything that follows from it, stays with a named human.
Example workflow
One expense claim, end to end
AgentHuman
1Claim receivedExpense platform, card feed, mileage log or receipt capture
2Evidence gatheredReceipt, card line, prior claims, and the claimant's grade and entitlement
3Policy evaluatedLimits, categories, class of travel, per-diem and mileage rates
4Duplicate and pattern checksThe same spend across cycles or across card and cash, and split amounts
No human action required
Stages 1 to 4 run without a person in the loop — nothing reaches the claimant or their manager before the gate.
5DecisionSplits on the confidence threshold
High confidence
Passes with no flag raised.
Low confidence
Held as a flag for review.
Human review
The claim is held with the rule it tripped, the evidence and a reason the claimant can read.
Clear · Uphold · Ask the claimant
Decided — handed back▼
6Expense platform updatedThe reviewer's decision and its reason, where write access allows it
7Outcome evaluatedFlag precision, flags overturned in review, and rates by team
Overturns
Flags cleared in review are counted, by team and by grade.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Rejecting a claim or withholding reimbursement.
Calling a claim fraudulent.
Referring a person to HR or an investigation.
Granting or recording a policy exception.
Automation boundaryAgent acts unaided
✓Read the claim, the receipt and the matching card line together.
✓Test each line against the policy version in force.
✓Detect duplicates, split claims and per-diem overlaps.
✓Raise a flag carrying its rule, its evidence and a written reason.
Write actions run only inside the approval boundaries agreed during implementation. Rejecting a claim is not one of them.
Overriding a grade, per-diem or mileage entitlement.
Changing the expense policy or its thresholds.
First claims from a new joiner.
Any flag the claimant contests.
Example output
One expense claim, annotated
Every flag is attached to the line it came from and the rule it was tested against.
Audit output · single claim lineIllustrative example
Merchant
Category
Amount
Flag raised
Confidence
Routed to
Hotel, overseas trip
Accommodation
$412.00
Nightly cap exceeded
92%
The claimant's approving manager
As receivedTaken from the expense platform and the card line it settled on — nothing on this side is inferred.
Evidence usedItemised receiptCard settlement lineCity cap for that date
Why this flagThe city cap in the policy version in force that night — not a judgement about anyone.
ActionClearUpholdAsk the claimant
What the score decidesAbove the threshold the flag reaches a reviewer with its evidence. A human clears or upholds it.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
All expense claimsFrom every submission channel
03Policy checks
Apply client-specific context
Use the policy version in force, grade entitlements and per-diem tables.
01Approved path
Check the population, not a sample
Every claim is tested against every rule, not the percentage a sampling audit draws.
02Human review
Send people only defensible flags
Reviewers get ranked, evidenced flags with a reason attached, rather than a queue of claims to read in full.
04Build an evidence trail
Retain the rule version, evidence, confidence, evaluator result and the reviewer's decision and reason — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
A low overall flag rate can hide a few claim cohorts that carry most of the flags a reviewer later overturns — and one cohort flagged far more often than the rest. Nestack reports performance by slice, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Overseas multi-currency trips
5.4%
3.4×
Review
Card-and-cash claim pairs
4.2%
2.6×
Review
New joiners' first claims
3.0%
1.9×
Watch
Routine domestic claims
1.1%
0.7×
Normal
Bar: overturn lift vs. domestic-claim baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
A wrong flag retires the rule behind it
Each cycle retires a rule that flagged the wrong people and keeps the claim that proved it, and the flag-rate comparison is re-run before it ships.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Overturn rates rise, or one team's flag rate pulls away from the rest.
02Diagnose
Traced to a rule, a policy version, a receipt read or a card-feed join.
03Improve
The rule or its threshold is re-approved with finance and version-linked.
04Verify
Re-run on held-out claims, then re-checked for flag rates by team.
05Learn
The overturned claim becomes a regression case; the reason is rewritten.
Learn → DetectThe return edge. Every rule that flagged the wrong person leaves a test behind.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, policy encoding, detection logic, evaluation and fairness testing, integration, then a shadow cycle and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and automation-boundary definition.
02Expense-platform and card-feed assessment.
03Expense-policy encoding and rule library.
04Claim, receipt and card-feed ingestion.
05Duplicate, split-claim and per-diem detection.
06Mileage and VAT/GST reclaim checks.
07Confidence scoring and flag ranking.
08Flag explanations written for claimants.
09Reviewer workflow and contested flags.
10Evaluation suite, regression and fairness testing.
11Expense-platform and GL integration.
12Shadow cycle, deployment and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.
Capability✓ in scope · — not at this tierPilotOne policy, one entityProductionProduction integrationAdvancedMultiple entities / countries
Introduced at Pilot
Policy checks and flags✓✓✓
Human decision on every flag✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Duplicate and split-claim checks—✓✓
Card-feed reconciliation—✓✓
Claimant-facing flag reasons—✓✓
Fairness reporting by slice—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Per-diem, mileage and VAT checks——✓
Multi-country policy and currency——✓
Enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on policy complexity, integrations, claim volume, the number of countries and deployment requirements.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01Your expense policy and its past versions→Expense-policy encoding, version history and the rule libraryWeek 1
02A representative sample of submitted claims and receipts→Claim, receipt and card-feed ingestion, and the duplicate-detection baselineWeek 2
03Corporate-card feeds and access to the expense platform→Expense-platform and card-feed assessment, then integration setupWeek 2
04Employee grade, entitlement and cost-centre data→Grade-entitlement, per-diem and mileage rate checksWeek 3
05Who decides a flag, and who hears a contested one→Automation-boundary definition, reviewer workflow and contested flagsWeek 4
06Claims you have previously upheld and previously waived→Evaluation suite, regression cases and fairness testingWeek 4
07Named reviewers and a team willing to run a shadow cycle→Flag explanations for claimants, then the shadow cycle and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Week 5 runs the agent in shadow against a live expense cycle while evaluation is still open.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Workflow discovery, policy-version mapping and the automation boundaryW2Claim, receipt and card-feed ingestion, and the detection baselineW3Detection logic, confidence scoring and flag explanationsW4Evaluation suite, fairness testing and the reviewer workflowW5Expense-platform integration and a shadow run on live claimsW6Shadow flags decided by named reviewers, verified, then handover
Reading the bandBars cover only the weeks their work is named in. Evaluation stays open into week 5 because the shadow run is what tests it.
At the end of W6One expense cycle has been flagged in shadow and every flag decided by a named reviewer, then Agent Care takes over monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Accounting AI agent
Build an expense-audit agent around your policy and your people.
Show us your expense policy, your card feeds and who decides a contested flag. We'll encode one version of the policy, test it against claims you have already settled and compare the flags.
