{
  "skill_name": "affiliate-payout-audit",
  "evals": [
    {
      "id": 1,
      "prompt": "I'm closing out the February payout for our Thistlewood Home affiliate program and I want a second pair of eyes before I hit release on Friday. Our network export shows 1,904 conversions on a 7-day attribution window, our own in-house tracker shows 1,671 on a 30-day window, so I've been reporting 3,575 conversions to the exec team. Proposed payout is $31,406.18. My own spreadsheet estimate came to $28,500 but that's only about $2,900 off, which feels like normal tracking noise for us. I calculate the run and I release it myself since we're a four-person team. Anything I should tighten up?",
      "expected_output": "An audit response that refuses to sum the two tracking sources, applies a comparability gate, treats the $2,900 gap as unexplained variance that must be resolved line by line rather than accepted, flags the missing maker-checker separation, and returns findings in the payout audit report shape.",
      "files": [],
      "expectations": [
        "Refuses to treat 3,575 as a conversion count and states the two sources cannot be summed",
        "Names the differing attribution windows (7-day vs 30-day) and differing dedup identity as the reason the two counts are not additive populations",
        "Applies a comparability gate before computing any total, covering event definition, date basis, time window, timezone, currency, counting method, and dedup identity",
        "Requires one canonical source be declared per conversion with the other reconciled against it, never a union of the two lists",
        "Treats the roughly $2,900 gap as unexplained variance that must be explained line by line rather than attributed to tracking noise",
        "Rejects 'close enough' or 'within noise' as a basis for approving the run",
        "Flags the absence of maker-checker separation: the person who calculated the run must not be the person releasing the funds",
        "States that maker-checker is the gate never dropped, and names a concrete second reader despite the four-person team size",
        "Recommends a shared idempotency key across the two trackers as the structural fix, flagged even though these duplicates were caught manually",
        "Produces a payout audit report containing Scope, Checks, Findings with severity and dollars at risk, Exceptions, Variance, Cleared, and Sign-off",
        "Shows the variance working: gross difference, the findings that explain it, and a residual that is either zero or itself a written-down finding"
      ]
    },
    {
      "id": 2,
      "prompt": "Two partners have kicked off about last quarter's commissions on our Kestrel Analytics program and I need to re-audit that run. Our written rate card says 20% on referred volume up to $10,000, 25% from $10,000 to $25,000, and 30% above $25,000, and there is no wording anywhere about how the bands combine. Partner Brightpath Media referred $26,000 of volume in the period and the platform paid her $7,800. Another partner, Onda Digital, landed at exactly $25,000 and got $6,250. We also refreshed the rate card two weeks ago. I don't have code access to any of this, the network only gives me a PDF statement. Are these numbers right?",
      "expected_output": "A recomputation showing both partners were paid on a retroactive reading, marginal recomputation of $6,050 and $5,750, the boundary-operator ambiguity at $25,000 raised as a structure finding, and a coverage method chosen for a no-code environment.",
      "files": [],
      "expectations": [
        "Recomputes Brightpath Media on the marginal (incremental) method as $6,050, showing 20% x 10,000 + 25% x 15,000 + 30% x 1,000 = 2,000 + 3,750 + 300",
        "Identifies the $7,800 paid figure as the retroactive, back-to-dollar-one reading of 30% x 26,000",
        "States the gap between the two readings for that partner as $1,750",
        "Requires the written structure to specify which method governs rather than choosing one by preference, and notes most programs use marginal to preserve margin",
        "Recomputes Onda Digital on the marginal method as $5,750",
        "Treats the exactly-at-breakpoint line as a boundary-operator question and recomputes it under both >= and > at the $25,000 threshold",
        "Raises the written structure's silence at the breakpoint as a finding against the structure's ambiguity, not as a math error",
        "Warns that retroactive tiers create cliffs and quantifies one around the $25,000 breakpoint (roughly $6,249.75 just below versus $7,500.30 just above)",
        "Requires 100% review of every line sitting near a retroactive breakpoint",
        "Recomputes against the contract terms in force at the original transaction date rather than the refreshed rate card",
        "Deletes full-population recompute from the coverage menu because no code can be executed over a PDF statement, rather than listing it as an available option",
        "Names risk-based stratified sampling as the leading coverage method in this situation and rejects random-only sampling as a rung"
      ]
    },
    {
      "id": 3,
      "prompt": "Two things landed on my desk this morning for the Wrenfield Supply affiliate program. Order 88412 was a $1,240 order at our flat 12% rate, refunded on Feb 19, but that commission locked on Feb 10 and the money went out on Feb 20, and the platform won't let me touch the record. Separately, affiliate PineRidge Deals had $3,110 of commission paid in January on orders we now know were returned. She has stopped promoting us entirely and her balance is zero. Our platform's own terms say that once commissions are paid to a partner they cannot be taken back under any circumstances. Finance has nobody free to co-sign anything this cycle. Do I just eat these?",
      "expected_output": "A remediation decision that books the post-lock refund as a forward-period negative adjustment, deletes the rungs the constraints rule out instead of ranking them lower, reports the churned partner's balance as absorbed, and names forward controls.",
      "files": [],
      "expectations": [
        "States that locked means the record cannot be reversed on-platform, not that the amount is no longer owed",
        "Books the post-lock refund as a forward-period negative adjustment carried against future earnings rather than dropping the line",
        "Establishes whether the platform carries negative partner balances at all before recommending an offset",
        "Checks whether the published terms authorize reclaiming a paid commission",
        "Checks whether the partner is still earning enough for an offset to actually land",
        "Deletes the offset rung for PineRidge Deals because she has churned out with no future earnings, rather than ranking it lower on the menu",
        "Deletes direct recovery outright, citing both the terms forbidding reclaim and the absence of a finance co-signer this cycle",
        "Reports the $3,110 as absorbed and quantified, never as recovered",
        "Presents absorb-and-document and fix-it-forward as the remaining menu, naming concrete forward controls such as a longer validation window, a reserve or holdback, a shared idempotency key, or a repriced rate card",
        "Promotes fix-it-forward to the top when post-lock refunds are routine rather than exceptional, or when the same finding class appears in two consecutive runs",
        "Computes the order 88412 commission at risk as $148.80 from the stated $1,240 order and 12% rate",
        "Ranks the remediation options by value recovered per unit of effort and relationship capital spent, not by the nominal dollar amount at stake"
      ]
    },
    {
      "id": 4,
      "prompt": "Auditing March's partner payout for Calyx Ops before release, 412 lines, $48,712.40 proposed. We pay 20% recurring revenue share capped at 12 months, and our terms give a 30-day validation window. A few things I noticed but I'm not sure any of them matter. Partner Halden Group has lines for accounts they referred back in January 2025 that are still billing monthly. One account, Meridian Freight, downgraded from the $900/month plan to the $400/month plan on Feb 10 and its commission line reads $180. Three accounts are commissioned on plan list price even though those customers are on a 20%-off annual promo. We bought out partner Sable Works' recurring stream with a $12,000 lump sum in December but I still see lines for their accounts. And two trials converted 18 days ago are already marked approved. What's the verdict?",
      "expected_output": "A per-line verdict identifying the duration-cap overpay as systematic, correcting the commission base to settled invoice amounts, voiding the bought-out partner's recurring lines, and holding the lines still inside the validation window.",
      "files": [],
      "expectations": [
        "Flags Halden Group's January-2025 accounts as past the 12-month duration cap, where month 13 onward earns zero",
        "Classifies the duration-cap breach as a systematic, compounding overpay rather than an isolated line error",
        "Identifies the $180 Meridian Freight line as 20% of the pre-downgrade $900 base and corrects it to the settled, prorated downgraded amount",
        "Requires the commission base to be the settled billing amount rather than the plan list price",
        "Corrects the three promo accounts to the discounted invoice amount actually paid by the customer",
        "Flags every remaining recurring line for Sable Works as an overpay because the buyout lump sum ended the commission stream",
        "Holds the two trial conversions from 18 days ago because the 30-day validation window has not elapsed",
        "Notes that auto-approval is a common default, so an 'approved' status is not evidence that the window elapsed or that a human reviewed the line",
        "Verifies that churned subscriptions stopped generating commission lines the cycle they lapsed",
        "Verifies proration is applied in both directions, and checks mid-cycle seat removals against the program's stated policy rather than assuming a credit",
        "Notes that B2B SaaS platforms often read the billing system directly, which collapses the reconciliation check to a spot-check, and verifies that is actually true here before collapsing it",
        "Delivers the payout audit report with per-finding severity, dollars at risk, affected lines, and a recommended action per finding"
      ]
    },
    {
      "id": 5,
      "prompt": "Running the audit on our Northbeam Outfitters network payout for the period 1 to 31 March. A couple of oddities. The export tool offered three date options, transaction date, validation date and amendment date, and I just took the default, which turned out to be validation date, then I manually moved 22 lines into March so the count would match our order database. Our network reports in UTC, our order database stamps Europe/Berlin, and my program calendar runs on America/Chicago. I set the window as 1 March 00:00 through 31 March 23:59:59. Fourteen order IDs in this run also appear in February's run because we re-exported after a late batch came in. Total proposed is $27,880. Good to go?",
      "expected_output": "A refusal to clear the run until scope is frozen: re-pull on a declared date basis rather than hand-moving lines, a single normalized timezone, a half-open window, and removal of the fourteen straddling keys.",
      "files": [],
      "expectations": [
        "Rejects hand-moving the 22 lines and requires re-pulling the export on the declared date basis instead of adjusting numbers manually",
        "Requires the date basis to be declared in run scope and held for the entire run, never mixed inside one run",
        "Recommends transaction date for reconciling to the order database, reserving validation date for what became payable this period",
        "Requires one timezone fixed in run scope with every timestamp normalized to it before the cutoff is applied",
        "Names the three-clock disagreement between network, order database, and program calendar as a cutoff risk to resolve rather than a rounding detail",
        "Replaces the closed window with a half-open window of the form period_start <= t < period_end, running 1 March 00:00 to 1 April 00:00",
        "Explains that a closed window double-counts the boundary instant",
        "Treats the 14 order IDs also present in February's run as an imminent double payment and removes them before totaling",
        "Requires diffing this run's key set against the prior run's key set as a standing check rather than a one-off fix",
        "Flags late-submitted conversions re-dated by the platform to their submission date, and any line whose event date differs from its order date, as cutoff-risk lines",
        "Requires test-mode and sandbox transactions to be excluded explicitly and verified not to have leaked into the live export",
        "Refuses to clear the run for release until run scope - period boundaries, timezone, and date basis - is frozen and unambiguous"
      ]
    },
    {
      "id": 6,
      "prompt": "Our Quill and Hearth apparel affiliate program pays 8% CPA and I have the April run ready, $52,140 proposed. Our validation window is 7 days because affiliates were complaining about waiting for their money. Customers have 30 days to return anything. Reversal rate over the last three runs was 19%, then 22%, then 24% of transaction value. There are 41 reversals in this run and roughly half of them have an empty note field. Also 63 lines in the export went from pending straight to paid, I think our platform auto-approves. Tell me what to fix.",
      "expected_output": "Findings that size the validation window to the return curve, place the reversal rate far above planning bands, require reason codes on every reversal, and hold the lines that skipped lifecycle states.",
      "files": [],
      "expectations": [
        "Flags the 7-day validation window as shorter than the 30-day customer return window and requires it be sized to the reversal curve rather than to affiliate impatience",
        "States that high-return verticals such as apparel need 30 or more days of validation",
        "Compares the 19%, 22% and 24% reversal rates against planning bands of roughly 2-8% for CPA programs and states the program runs far above band",
        "Treats the above-band reversal rate as a trigger to lengthen the validation window or tighten qualification before payout, not merely a metric to report",
        "Flags every reversal carrying no documented reason code as a finding, on the grounds that uncoded reversals are unauditable and fuel partner disputes",
        "Names usable reversal reason codes such as invalid card, return or cancellation, duplicate order, customer fraud, affiliate fraud, non-qualified lead, and test transaction",
        "Escalates any reversal coded affiliate fraud out of this audit to fraud review, verifying only the arithmetic of the reversal here",
        "Flags the 63 pending-to-paid lines as records that skipped the approved and locked states",
        "States that auto-approval means unreviewed lines approve themselves, so approved status is not evidence of review",
        "Holds every line still inside its validation window rather than releasing it with a note",
        "Tracks run-over-run KPIs including payout accuracy rate, exception value as a share of run value, reversal or clawback rate against the band, post-payout correction rate, and dispute rate"
      ]
    },
    {
      "id": 7,
      "prompt": "Verdanta Labs partner payouts, May run, 318 lines, three currencies (USD, EUR, GBP) all settled out to USD, about $44K total. Two things bug me. First, I cannot find anywhere in the platform docs which exchange rate date they use, and when I spot-checked one EUR line the platform's rate was about 1.8% off the ECB rate for that day, consistently in the same direction on the four other EUR lines I checked. Second, I ran the numbers myself and I am $3.87 off the platform overall, with basically every individual line off by a cent or two. Third, four payees are sitting at $148.22 combined, all under our $50 minimum, and last month's export shows two of them at a similar level but they are not in this month's file at all. Our materiality threshold is $250.",
      "expected_output": "A verdict treating the FX strike date as an unverified per-platform item, judging rounding drift at run level against materiality, and investigating the missing sub-threshold carry-forward.",
      "files": [],
      "expectations": [
        "Treats the FX strike date as a per-platform verification item rather than assuming one",
        "Names the three candidate strike dates: conversion date, approval date, and payout date",
        "Proposes inferring the strike date empirically by recomputing one known line at each candidate date, or asking the platform directly",
        "States that a run mixing lines converted at different strike dates fails the comparability gate",
        "Treats the consistent 1.8% spread against the reference rate as a finding, while noting it may be a disclosed platform margin to verify and document",
        "Judges the $3.87 rounding drift at run level against the $250 materiality threshold rather than per line",
        "States that per-line cent-level drift is expected and legitimate because payouts cannot split cents",
        "Requires rounding to 2 decimals at the end of the calculation rather than at each step",
        "Verifies a single rounding policy applies to every line, treating mixed truncation and rounding as evidence of two calculation paths and a root-cause finding",
        "Treats the two sub-threshold payees missing from this month's file as a carry-forward failure to investigate, requiring their balances to reappear intact",
        "States that sub-threshold balances roll forward to the next run and must never be dropped or applied as an exclusion",
        "Books the $3.87 as a below-materiality finding with its value rather than omitting it, because materiality decides whether a residual blocks release, never whether it is written down"
      ]
    },
    {
      "id": 8,
      "prompt": "Before I release the June run for Larkfield Systems ($71,300 across 96 payees) I want a check. Our payee list is 31 US individuals, 12 US LLCs, 38 EU-based publishers (mostly VAT-registered companies), and 15 elsewhere. A handful of issues: one US payee never returned a W-9 but is owed $4,800, a French publisher's form is dated 2022, and our finance lead says we should withhold nothing and sort the paperwork out after payment since these are small amounts anyway. Our network generates the publishers' invoices on their behalf. And PayPal fees are being deducted from the commission line before it even shows up in the export. Should I release?",
      "expected_output": "A payee-scoped hold for the missing and expired forms, backup withholding applied, reverse-charge and self-billing verification for the EU publishers, and a finding on fees netted into the commission line.",
      "files": [],
      "expectations": [
        "Blocks release for the payee with no W-9 on file rather than paying now and collecting the form afterwards",
        "Applies backup withholding to a US payee who failed to provide a valid W-9, and flags a run paying such a payee gross as a finding",
        "Treats the 2022-dated French publisher form as expired and therefore missing",
        "Names the correct form per payee class: W-9 for US payees, W-8BEN for foreign individuals, W-8BEN-E for foreign entities",
        "Scopes the hold to the affected payees rather than holding the entire run",
        "Rejects the pay-now-paperwork-later instruction on the grounds that releasing without valid forms is a filing problem, not only a money one",
        "Identifies cross-border EU B2B affiliate commission as a marketing service falling under the reverse charge, invoiced at 0% with the buyer self-accounting",
        "Requires the invoice to cite the reverse-charge basis and a VIES-verified VAT number",
        "Recognizes the network-generated publisher invoices as self-billing and verifies each self-billed invoice matches the audited commission total for the period",
        "Determines whether the program runs merchant-of-record or agent-of-record before judging whose ledger must carry the tax",
        "Flags the PayPal fees netted into the commission line: the audit verifies the gross commission, and downstream fees must be disclosed in the program terms rather than silently netted",
        "Treats US 1099 reporting thresholds as legislation-dependent and re-verifies them for the applicable tax year rather than stating a fixed figure as permanent"
      ]
    },
    {
      "id": 9,
      "prompt": "The payout run has to go out Thursday, it is Tuesday afternoon, and I have maybe six hours total. Ashgrove Media affiliate program, 1,930 lines, $88,400 proposed. I can export CSVs from the network but I cannot run scripts against them, I am in spreadsheets only. Our structure changed on 1 May: we moved from a flat 12% to a tiered card, and this run covers 15 April to 15 May. Nobody in finance can look at this before Thursday. Which checks do I actually run, and which do I skip?",
      "expected_output": "A triage that gives an explicit errors-per-hour ordering of the gates, promotes rate/tier recompute for the mid-period structure change, refuses to drop maker-checker, and picks a coverage method compatible with spreadsheets only.",
      "files": [],
      "expectations": [
        "Names dedup as the highest errors-caught-per-hour gate, ahead of reconciliation and comparability, lifecycle window, rate and tier recompute, and currency, tax and thresholds",
        "Distinguishes the efficiency ordering from the value ordering, in which reconciliation and comparability lead",
        "States the numbered audit sequence is a dependency order, not a priority order",
        "Refuses to drop maker-checker despite the deadline, calling it the gate never dropped, and finds a second reader outside finance rather than skipping the sign-off",
        "Promotes rate and tier recompute to the front of the order because the commission structure changed mid-period",
        "Recomputes each line against the terms in force on its own transaction date, splitting the run at 1 May rather than applying one card across the whole period",
        "Deletes full-population recompute from the coverage menu because scripts cannot be executed over the export",
        "Names risk-based stratified sampling as the leading coverage method available here",
        "Defines the stratified sample as 100% of high-value lines, high-reversal partners and top earners, plus a random sample of the remainder sized against materiality",
        "Rejects random-only sampling as a rung because it costs the same hours as risk-based and finds fewer dollars",
        "Warns that a top-earner spot-check is blind to long-tail systematics and is acceptable only under a hard deadline",
        "Recommends a reusable recompute script as the compounding fix, noting full-population recompute drops to near-zero effort on every run once the script exists"
      ]
    },
    {
      "id": 10,
      "prompt": "Hollowbrook Goods, monthly affiliate run, 2,184 lines, $31,400 proposed. Our analytics dedupe on transaction ID and 17 lines came through with the transaction ID field blank. They have all been rolled up into a single record in the report so I cannot tell what any one of them is worth. Separately, 12 orders exist in our order database with no matching record in the network, and 9 records exist in the network with nothing behind them in the order database. And one affiliate, DealVault, has 140 conversions all from the same three IP ranges inside about 40 minutes, all on our highest-value SKU. I would like to just estimate the 17 blank ones at the average line value and move on.",
      "expected_output": "A refusal to estimate quarantined lines, a two-direction exception queue with a default action per direction, stable-ID matching discipline, and escalation of the burst pattern to fraud review without ruling on it here.",
      "files": [],
      "expectations": [
        "Rejects estimating the 17 blank-key lines at an average line value",
        "Quarantines the empty or malformed dedup keys and requires manual resolution before any total is computed",
        "Explains that deduping on a blank key collapses many conversions into one record, or splits one conversion into many payable lines",
        "Requires one deterministic dedup key per conversion, paid at most once per commission event",
        "Splits the one-sided records into an exception queue carrying a direction and a default action per record",
        "Classifies the 9 network-only records as possible over-credit: hold the lines and investigate before approving",
        "Classifies the 12 order-database-only records as untracked sales, anticipates an inbound partner dispute, and requires the credit policy be decided and documented explicitly",
        "Matches records on stable identifiers only - order ID, transaction ID, customer ID, subscription ID - never on partner or customer display names",
        "Applies the zero/one/many rule: zero matches go to the exception queue, exactly one resolves, more than one stops for explicit human disambiguation rather than an auto-pick",
        "Escalates the DealVault burst pattern to fraud review without ruling on its legitimacy inside this audit",
        "Continues to verify the arithmetic of the DealVault lines and holds them, treating fraud escalation as running in parallel to a remediation action rather than replacing one"
      ]
    }
  ],
  "trigger_queries": [
    { "query": "Audit this month's affiliate payout run before we release it", "should_trigger": true },
    { "query": "Can you check our commission payout for accuracy before I hit send?", "should_trigger": true },
    { "query": "We think we overpaid two affiliates last quarter, can you re-audit that run?", "should_trigger": true },
    { "query": "I need a pre-disbursement review of our partner commission run", "should_trigger": true },
    { "query": "Our network export and our order database disagree by about $3K, what do I hold?", "should_trigger": true },
    { "query": "Reconcile the affiliate platform export against our billing system", "should_trigger": true },
    { "query": "A partner says her tier was applied wrong, I need to verify last quarter's commissions", "should_trigger": true },
    { "query": "How do I know the commission numbers the platform handed me are actually right?", "should_trigger": true },
    { "query": "Something is off in our payout file and I release it Friday", "should_trigger": true },
    { "query": "We paid the same order twice across two affiliate trackers, how do I find the rest?", "should_trigger": true },
    { "query": "Check whether our commissions were calculated on marginal or retroactive tiers", "should_trigger": true },
    { "query": "I need to verify 800 commission lines before payday", "should_trigger": true },
    { "query": "payout accuracy review for our partner program", "should_trigger": true },
    { "query": "A refund came in after the commission locked, what happens to that money?", "should_trigger": true },
    { "query": "Our clawbacks are not being applied before payout, can you review the run?", "should_trigger": true },
    { "query": "Double-check our affiliate payouts for duplicate conversions", "should_trigger": true },
    { "query": "Can you look over this commission run and tell me what to hold back?", "should_trigger": true },
    { "query": "We are about to pay $60K to affiliates and I want a sanity check first", "should_trigger": true },
    { "query": "Review our partner commission calculations for errors", "should_trigger": true },
    { "query": "Some affiliates say they were underpaid last month", "should_trigger": true },
    { "query": "How do I check that our validation window was actually respected before lines got approved?", "should_trigger": true },
    { "query": "Verify our recurring revenue share commissions against the billing system", "should_trigger": true },
    { "query": "commission reconciliation for March", "should_trigger": true },
    { "query": "Our payout total does not match my spreadsheet and I cannot find the difference", "should_trigger": true },
    { "query": "I think we have been paying commission past the 12-month cap", "should_trigger": true },
    { "query": "Does anyone need to sign off before I release affiliate payments?", "should_trigger": true },
    { "query": "Set up a review process so we stop overpaying partners every month", "should_trigger": true },
    { "query": "Audit the affiliate commission file", "should_trigger": true },
    { "query": "What checks should I run before disbursing partner commissions?", "should_trigger": true },
    { "query": "We just noticed month-13 commissions going out on a 12-month program", "should_trigger": true },
    { "query": "Our affiliate payouts include orders that were returned, how do I fix this run?", "should_trigger": true },
    { "query": "Find the errors in our partner payout before the money moves", "should_trigger": true },
    { "query": "Which lines in this commission run should I not pay yet?", "should_trigger": true },
    { "query": "Currency conversion on our affiliate payouts looks wrong to me", "should_trigger": true },
    { "query": "An affiliate was under the minimum threshold and their balance just vanished", "should_trigger": true },
    { "query": "I need a report showing what is cleared and what is held in this payout", "should_trigger": true },
    { "query": "Can you sanity check a commission run for a B2B SaaS partner program?", "should_trigger": true },
    { "query": "Our ecommerce affiliate network payout has 2,000 lines, how do I sample it?", "should_trigger": true },
    { "query": "Confirm the commission rate applied matches the contract in force at the time of the sale", "should_trigger": true },
    { "query": "affiliate payment run review", "should_trigger": true },
    { "query": "Somebody needs to check my math on this partner payout", "should_trigger": true },
    { "query": "The same conversion shows up in both January's and February's payouts", "should_trigger": true },
    { "query": "We are paying affiliates who have no tax forms on file, how bad is this?", "should_trigger": true },
    { "query": "Our finance team wants evidence that partner commissions were reviewed before release", "should_trigger": true },
    { "query": "Is this commission run safe to release?", "should_trigger": true },
    { "query": "I need to explain a $2,900 gap between our tracker and the network before payday", "should_trigger": true },
    { "query": "Recompute the commissions for our top five partners", "should_trigger": true },
    { "query": "Half our reversals have no reason recorded, does that matter for this payout?", "should_trigger": true },
    { "query": "Rounding differences across hundreds of commission lines, should I care?", "should_trigger": true },
    { "query": "How do I stop paying the same affiliate conversion twice?", "should_trigger": true },
    { "query": "Make sure our partner payouts are correct before the wire goes out", "should_trigger": true },
    { "query": "Audit a payout run for a program where the rate card changed mid-period", "should_trigger": true },
    { "query": "affiliate commission accuracy check", "should_trigger": true },
    { "query": "Design the commission tiers for our new affiliate program", "should_trigger": false },
    { "query": "What rate should we pay affiliates on a $49/month SaaS plan?", "should_trigger": false },
    { "query": "Should we use flat CPA or revenue share for our program?", "should_trigger": false },
    { "query": "How long should our cookie attribution window be?", "should_trigger": false },
    { "query": "Set the clawback and validation window policy for a program we are launching", "should_trigger": false },
    { "query": "One of our affiliates is cookie stuffing, how do I prove it?", "should_trigger": false },
    { "query": "Build the rule set to flag fraudulent affiliate traffic", "should_trigger": false },
    { "query": "Is this coupon partner actually driving incremental sales or just stealing credit?", "should_trigger": false },
    { "query": "We have a self-referral ring in the program, what do I do about it?", "should_trigger": false },
    { "query": "Draft the terms and conditions affiliates accept when they join", "should_trigger": false },
    { "query": "Write the clause that lets us terminate an affiliate for brand bidding", "should_trigger": false },
    { "query": "What should our affiliate agreement say about clawback rights?", "should_trigger": false },
    { "query": "Build a dashboard for our affiliate program metrics", "should_trigger": false },
    { "query": "What KPIs should we track for affiliate performance?", "should_trigger": false },
    { "query": "Define the formula for affiliate-attributed revenue in our BI tool", "should_trigger": false },
    { "query": "Set reward caps and cooldowns for our refer-a-friend program", "should_trigger": false },
    { "query": "Customers are gaming our referral rewards with fake accounts", "should_trigger": false },
    { "query": "How much should we give for a customer referral, account credit or cash?", "should_trigger": false },
    { "query": "Model the unit economics of our biggest reseller", "should_trigger": false },
    { "query": "Is our partner CAC better than our direct CAC?", "should_trigger": false },
    { "query": "Negotiate usage rights and rates with a creator we want to sign", "should_trigger": false },
    { "query": "Does this TikTok caption meet FTC disclosure rules?", "should_trigger": false },
    { "query": "Our affiliate blog post does not say it is sponsored, is that a problem?", "should_trigger": false },
    { "query": "Build a quarterly scorecard for our channel partners", "should_trigger": false },
    { "query": "Our gold partner missed targets two quarters running, what is the process?", "should_trigger": false },
    { "query": "Write the outreach email we use to recruit new affiliates", "should_trigger": false },
    { "query": "Where do I find affiliates for a B2B SaaS product?", "should_trigger": false },
    { "query": "Design the onboarding emails for newly approved affiliates", "should_trigger": false },
    { "query": "How many tiers should our channel program have?", "should_trigger": false },
    { "query": "Set the criteria to promote a partner from silver to gold", "should_trigger": false },
    { "query": "Write our deal registration policy", "should_trigger": false },
    { "query": "A direct rep and a partner are both claiming the same deal", "should_trigger": false },
    { "query": "Plan a co-marketing launch with our integration partner", "should_trigger": false },
    { "query": "Which cloud marketplaces should we list on?", "should_trigger": false },
    { "query": "Map our full partner ecosystem", "should_trigger": false },
    { "query": "What should we pay a channel manager?", "should_trigger": false },
    { "query": "How do I break into partnerships from customer success?", "should_trigger": false },
    { "query": "Reconcile our Stripe payouts against our bank statement", "should_trigger": false },
    { "query": "Audit our AWS bill for unused instances", "should_trigger": false },
    { "query": "Run a payroll audit before this month's pay cycle", "should_trigger": false },
    { "query": "Review our SOC 2 evidence before the auditor arrives", "should_trigger": false },
    { "query": "Check our revenue recognition treatment for annual contracts", "should_trigger": false },
    { "query": "Audit our expense reports for policy violations", "should_trigger": false },
    { "query": "Reconcile the general ledger to the subledger for Q1", "should_trigger": false },
    { "query": "Our sales reps' commission plan payouts look wrong this quarter", "should_trigger": false },
    { "query": "Set quotas and accelerators for the AE comp plan", "should_trigger": false },
    { "query": "Audit our vendor invoices for duplicate payments", "should_trigger": false },
    { "query": "Review our Google Ads spend for wasted budget", "should_trigger": false },
    { "query": "Check our influencer campaign results against the media plan", "should_trigger": false },
    { "query": "Build the measurement plan before we launch the creator campaign", "should_trigger": false },
    { "query": "Draft a creative brief for the creator we just signed", "should_trigger": false },
    { "query": "Shortlist creators for our spring campaign", "should_trigger": false },
    { "query": "Which partner categories should we add next year?", "should_trigger": false }
  ]
}