Queries · q167 · Head of Lifecycle Marketing · week 1, night 3

Loyalty and referral programme participation rate over time

“What share of our active customer base is enrolled in loyalty or has ever used a referral code, and is that share growing, flat, or shrinking over time?”

Fictional people at a fictional company, each played by a language-model agent. Who they are and what they are told

1. A business event lands on the Head of Lifecycle Marketing's desk

   Week 1; shared with Tobias Lindqvist, Chief Financial Officer

   Is the loyalty and referral programme worth it? Do members and referred customers behave differently from others, and what does the programme cost?

   One of the 35 events we wrote for the role play; it shaped the manager's first note. How events arise · All the events

2. Aisha Rahman writes to Ingrid Solberg

   The manager, at the start of week 1

   Subject: Loyalty & referral programme — what I need for Friday's memo

   Hi Ingrid,

   Welcome aboard — thank you for jumping on this in week one. Tobias and I need to give the leadership team a joint, evidence-based view on whether the loyalty and referral programme is paying for itself. The deliverable is your Friday memo, which Tobias and I will use to decide whether we expand the programme, leave it as is, or rework it. Given the slot budget, let's prioritize breadth of the right questions over depth on any one — we can always follow up next week.

   Here's what I'm trying to answer, in my own words:

   1. Do loyalty members actually buy differently? Compared with similar customers who aren't enrolled, do members order more often, spend more, or stick around longer? I want to know if membership correlates with genuinely better customer behavior, not just that our best customers happen to join.
   2. Do referred customers turn into good customers? When someone comes in through a referral, how do they behave in their first months compared to customers acquired other ways — do they buy, do they come back, do they stay?
   3. What is the programme actually costing us? I want a sense of the points/rewards and referral payouts we're giving out, ideally relative to the revenue those same members or referred customers generate, so we can see if the economics make sense.
   4. Is participation worth the overhead? How many of our customers are actually enrolled or have used a referral code, and is that share growing or flat? If take-up is small, the upside is capped no matter how good the behavior looks.
   5. Any red flags on how the programme is used? For example, signs that rewards are being redeemed without real repeat purchase behavior behind them, or that referral activity is concentrated in a way that looks more like gaming than genuine word-of-mouth.

   Given we only have a few report slots a night, I'd rank these in order 3, 1, 2 as the must-haves for Friday; 4 and 5 are nice-to-haves if slots allow. Please loop in whatever Tobias's analyst is already pulling on the finance side so we're not duplicating report requests.

   Thanks, Ingrid — happy to talk through any of this before you start drafting requests.

   Best, Aisha

   Show the whole note
   A note from the Chief Financial Officer, Tobias Lindqvist

   Subject: Finance angle on the loyalty/referral review

   Hi Ingrid,

   A few things I'd like us to cover as you scope this:

   1. What is the programme actually costing us net — points and referral rewards issued versus redeemed/liability outstanding — and how does that compare to the margin uplift (if any) from members? I don't want to judge this on engagement alone.
   2. Do members and referred customers carry a different refund/return profile than regular customers? If the programme is quietly skewing our refund rate, that matters for how we read "incremental" revenue.
   3. For the B2B side especially, are enrolled accounts paying on better terms — faster settlement, fewer overdue balances — or is that unrelated to the programme?

   Happy to look at a first cut together before it goes wider.

   Tobias

3. Ingrid Solberg plans the night

   The analyst · week 1, night 3, request 2 of 3

   Night 2 sharpened the picture. The tenure-controlled cut (Report 1) rules out the 'members are just newer accounts' explanation: at every tenure band members order less, spend less, and are refunded 2x more than non-members - and the refund gap actually widens with tenure (27% to 34% for members vs 20% down to 14% for non-members). So this isn't a cohort artifact; it's a persistent, worsening pattern. The before/after enrollment report (Report 2) came back with zero pre-enrollment orders for everyone - meaning enrollment essentially happens at or before a member's very first order (likely at signup), so there is no 'pre' baseline to diff against; that test was a dead end for isolating causality but confirms enrollment is immediate, not something people do after building a track record. Report 3 shows no smoking-gun concentration: redemption counts per referrer are almost all 1 (occasional 2), spread across dozens of tenants and referrers with normal-looking order histories (from near-zero to tens of thousands of EUR) - this looks like genuine light word-of-mouth, not gaming, though volume is tiny. For the last full night before the memo, I want to: (1) directly test Aisha's 'rewards redeemed without real repeat purchase' hypothesis by checking whether orders where points were actually redeemed show elevated refund rates versus other member orders - this could explain the mechanism behind the refund gap; (2) quantify participation and its trend for Aisha's #4; (3) close out Tobias's B2B payment-terms question, which is still untouched. I'm leaving one night in reserve for any necessary follow-up before Friday.

   Read the whole plan
   Loyalty and referral programme participation rate over time

   Question

   What share of our active customer base is enrolled in loyalty or has ever used a referral code, and is that share growing, flat, or shrinking over time?

   One row per

   calendar quarter from 2023-Q1 through 2025-Q4

   Columns

   • quarter
   • active_customers_cumulative
   • loyalty_members_cumulative
   • pct_customers_loyalty_members
   • referred_customers_cumulative
   • pct_customers_referred

4. Viktor writes the SQL

   The engineer · 1 dry run on the empty schema, then the submission

   Dry run 1 · STATUS: COMPILES (dry run on the empty schema, no data read)

   SELECT
     q.quarter AS quarter,
     (SELECT COUNT(DISTINCT o.user_id)
        FROM orders o
        JOIN users u ON u.id = o.user_id
       WHERE u.is_staff = false
         AND o.placed_at IS NOT NULL
         AND CAST(o.placed_at AS DATE) <= q.quarter_end) AS active_customers_cumulative,
     (SELECT COUNT(DISTINCT la.user_id)
        FROM loyalty_accounts la
        JOIN users u ON u.id = la.user_id
       WHERE u.is_staff = false
         AND CAST(la.enrolled_at AS DATE) <= q.quarter_end) AS loyalty_members_cumulative,
     ROUND(100.0 *
       (SELECT COUNT(DISTINCT la.user_id)
          FROM loyalty_accounts la
          JOIN users u ON u.id = la.user_id
         WHERE u.is_staff = false
           AND CAST(la.enrolled_at AS DATE) <= q.quarter_end)
       / NULLIF((SELECT COUNT(DISTINCT o.user_id)
                   FROM orders o
                   JOIN users u ON u.id = o.user_id
                  WHERE u.is_staff = false
                    AND o.placed_at IS NOT NULL
                    AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0)
     , 2) AS pct_customers_loyalty_members,
     (SELECT COUNT(DISTINCT rr.referred_user_id)
        FROM referral_redemptions rr
        JOIN users u ON u.id = rr.referred_user_id
       WHERE u.is_staff = false
         AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end) AS referred_customers_cumulative,
     ROUND(100.0 *
       (SELECT COUNT(DISTINCT rr.referred_user_id)
          FROM referral_redemptions rr
          JOIN users u ON u.id = rr.referred_user_id
         WHERE u.is_staff = false
           AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end)
       / NULLIF((SELECT COUNT(DISTINCT o.user_id)
                   FROM orders o
                   JOIN users u ON u.id = o.user_id
                  WHERE u.is_staff = false
                    AND o.placed_at IS NOT NULL
                    AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0)
     , 2) AS pct_customers_referred
   FROM (
     SELECT
       year_num,
       quarter_num,
       CONCAT(CAST(year_num AS VARCHAR), '-Q', CAST(quarter_num AS VARCHAR)) AS quarter,
       MAX(calendar_date) AS quarter_end
     FROM calendar_days
     WHERE year_num BETWEEN 2023 AND 2025
     GROUP BY year_num, quarter_num
   ) q
   ORDER BY q.year_num ASC, q.quarter_num ASC

   “Compiles cleanly with the expected columns. Submitting.”

   Submitted · the SQL of the last dry run, unchanged · Submitted to tonight's batch. Your work on this request is done.

   “Submitted. The report computes, for each of the 12 quarter-ends from 2023-Q1 through 2025-Q4, the cumulative distinct non-staff customers with an order, cumulative loyalty enrollees, and cumulative referred customers, plus their shares of the active base — aggregated platform-wide across all tenants since the question wasn't merchant-specific.”

5. The report comes back overnight

   As Ingrid Solberg saw it, from the small dataset the agents worked on

   quarter | active_customers_cumulative | loyalty_members_cumulative | pct_customers_loyalty_members | referred_customers_cumulative | pct_customers_referred
   --------+-----------------------------+----------------------------+-------------------------------+-------------------------------+-----------------------
   2023-Q1 |                        1047 |                        279 |                         26.65 |                             0 |                    0.0
   2023-Q2 |                        1795 |                        358 |                         19.94 |                             2 |                   0.11
   2023-Q3 |                        2421 |                        442 |                         18.26 |                             7 |                   0.29
   2023-Q4 |                        3401 |                        559 |                         16.44 |                            10 |                   0.29
   2024-Q1 |                        4004 |                        636 |                         15.88 |                            16 |                    0.4
   2024-Q2 |                        4654 |                        727 |                         15.62 |                            20 |                   0.43
   2024-Q3 |                        5269 |                        813 |                         15.43 |                            25 |                   0.47
   2024-Q4 |                        6314 |                        975 |                         15.44 |                            38 |                    0.6
   2025-Q1 |                        6963 |                       1092 |                         15.68 |                            43 |                   0.62
   2025-Q2 |                        7632 |                       1217 |                         15.95 |                            50 |                   0.66
   2025-Q3 |                        8377 |                       1344 |                         16.04 |                            57 |                   0.68
   2025-Q4 |                        9640 |                       1546 |                         16.04 |                            67 |                    0.7
   (12 rows)

6. What came of it

   The memo and the queries that followed; links found by title, so inferred

   Later queries that build on this report:

   • q169Loyalty and referral programme reach by merchant vertical

   It builds on:

   • q160Loyalty points and referral reward cost by month

7. It becomes benchmark query q167

   Changed only where the benchmark needs the same result on every system

   • numericsdocs/NUMERICS.md: rounding removed; results keep full precision
   • numericsdocs/NUMERICS.md: rounding removed; results keep full precision
   • determinismthe standard leaves the place of NULLs in a sort to the implementation: NULLS LAST ascending, NULLS FIRST descending, as in the reference results (2×)
   The benchmark text, against the submitted SQL

   SELECT  q.quarter AS quarter,  (SELECT COUNT(DISTINCT o.user_id)     FROM orders o     JOIN users u ON u.id = o.user_id    WHERE u.is_staff = false      AND o.placed_at IS NOT NULL      AND CAST(o.placed_at AS DATE) <= q.quarter_end) AS active_customers_cumulative,  (SELECT COUNT(DISTINCT la.user_id)     FROM loyalty_accounts la     JOIN users u ON u.id = la.user_id    WHERE u.is_staff = false      AND CAST(la.enrolled_at AS DATE) <= q.quarter_end) AS loyalty_members_cumulative,  ROUND(100.0 *    (SELECT COUNT(DISTINCT la.user_id)       FROM loyalty_accounts la       JOIN users u ON u.id = la.user_id      WHERE u.is_staff = false        AND CAST(la.enrolled_at AS DATE) <= q.quarter_end)    / NULLIF((SELECT COUNT(DISTINCT o.user_id)                FROM orders o                JOIN users u ON u.id = o.user_id               WHERE u.is_staff = false                 AND o.placed_at IS NOT NULL                 AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0)  , 2) AS pct_customers_loyalty_members,  100.0 *(SELECT COUNT(DISTINCT la.user_id) FROM loyalty_accounts la JOIN users u ON u.id = la.user_idWHERE u.is_staff = false  AND CAST(la.enrolled_at AS DATE) <= q.quarter_end)/ NULLIF((SELECT COUNT(DISTINCT o.user_id)          FROM orders o          JOIN users u ON u.id = o.user_id         WHERE u.is_staff = false           AND o.placed_at IS NOT NULL           AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0) AS pct_customers_loyalty_members,  (SELECT COUNT(DISTINCT rr.referred_user_id)     FROM referral_redemptions rr     JOIN users u ON u.id = rr.referred_user_id    WHERE u.is_staff = false      AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end) AS referred_customers_cumulative,  ROUND(100.0 *    (SELECT COUNT(DISTINCT rr.referred_user_id)       FROM referral_redemptions rr       JOIN users u ON u.id = rr.referred_user_id      WHERE u.is_staff = false        AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end)    / NULLIF((SELECT COUNT(DISTINCT o.user_id)                FROM orders o                JOIN users u ON u.id = o.user_id               WHERE u.is_staff = false                 AND o.placed_at IS NOT NULL                 AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0)  , 2) AS pct_customers_referred  100.0 *(SELECT COUNT(DISTINCT rr.referred_user_id) FROM referral_redemptions rr JOIN users u ON u.id = rr.referred_user_idWHERE u.is_staff = false  AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end)/ NULLIF((SELECT COUNT(DISTINCT o.user_id)          FROM orders o          JOIN users u ON u.id = o.user_id         WHERE u.is_staff = false           AND o.placed_at IS NOT NULL           AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0) AS pct_customers_referredFROM (  SELECT    year_num,    quarter_num,    CONCAT(CAST(year_num AS VARCHAR), '-Q', CAST(quarter_num AS VARCHAR)) AS quarter,    MAX(calendar_date) AS quarter_end  FROM calendar_days  WHERE year_num BETWEEN 2023 AND 2025  GROUP BY year_num, quarter_num) qORDER BY q.year_num ASC, q.quarter_num ASCORDER BY q.year_num ASC NULLS LAST, q.quarter_num ASC NULLS LAST

   As each system received it; highlighted, the parts spelled for that system

   DuckDB · Hyper · GizmoSQL · CedarDB · pg_duckdb · PostgreSQL · DataFusion · Firebolt · ClickHouse · chDB · clickhouse_brew

   SELECT
     q.quarter AS quarter,
     (SELECT COUNT(DISTINCT o.user_id)
        FROM orders o
        JOIN users u ON u.id = o.user_id
       WHERE u.is_staff = false
         AND o.placed_at IS NOT NULL
         AND CAST(o.placed_at AS DATE) <= q.quarter_end) AS active_customers_cumulative,
     (SELECT COUNT(DISTINCT la.user_id)
        FROM loyalty_accounts la
        JOIN users u ON u.id = la.user_id
       WHERE u.is_staff = false
         AND CAST(la.enrolled_at AS DATE) <= q.quarter_end) AS loyalty_members_cumulative,
     100.0 *
   (SELECT COUNT(DISTINCT la.user_id)
    FROM loyalty_accounts la
    JOIN users u ON u.id = la.user_id
   WHERE u.is_staff = false
     AND CAST(la.enrolled_at AS DATE) <= q.quarter_end)
   / NULLIF((SELECT COUNT(DISTINCT o.user_id)
             FROM orders o
             JOIN users u ON u.id = o.user_id
            WHERE u.is_staff = false
              AND o.placed_at IS NOT NULL
              AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0) AS pct_customers_loyalty_members,
     (SELECT COUNT(DISTINCT rr.referred_user_id)
        FROM referral_redemptions rr
        JOIN users u ON u.id = rr.referred_user_id
       WHERE u.is_staff = false
         AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end) AS referred_customers_cumulative,
     100.0 *
   (SELECT COUNT(DISTINCT rr.referred_user_id)
    FROM referral_redemptions rr
    JOIN users u ON u.id = rr.referred_user_id
   WHERE u.is_staff = false
     AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end)
   / NULLIF((SELECT COUNT(DISTINCT o.user_id)
             FROM orders o
             JOIN users u ON u.id = o.user_id
            WHERE u.is_staff = false
              AND o.placed_at IS NOT NULL
              AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0) AS pct_customers_referred
   FROM (
     SELECT
       year_num,
       quarter_num,
       CONCAT(CAST(year_num AS VARCHAR), '-Q', CAST(quarter_num AS VARCHAR)) AS quarter,
       MAX(calendar_date) AS quarter_end
     FROM calendar_days
     WHERE year_num BETWEEN 2023 AND 2025
     GROUP BY year_num, quarter_num
   ) q
   ORDER BY q.year_num ASC NULLS LAST, q.quarter_num ASC NULLS LAST

   • Fireboltno result within 30 s
   • DataFusionThis feature is not implemented: Physical plan does not support logical expression ScalarSubquery(<subquery>)

   Scale factor 1000, c8a.24xlarge, after the last load. q167 on the start page, with every configuration.

8. Everything, as recorded

   The agents' own records, as the role play wrote them; only the personal data of the person who ran it is redacted

   Viktor's whole session, 7 turns

   • The request, as Viktor received it

     Report request from Ingrid Solberg (analyst for the Head of Lifecycle Marketing):
     
     Title: Loyalty and referral programme participation rate over time
     Question: What share of our active customer base is enrolled in loyalty or has ever used a referral code, and is that share growing, flat, or shrinking over time?
     Grain: one row per calendar quarter from 2023-Q1 through 2025-Q4
     Columns:
     - quarter
     - active_customers_cumulative
     - loyalty_members_cumulative
     - pct_customers_loyalty_members
     - referred_customers_cumulative
     - pct_customers_referred
     Details: For each quarter end date (2023-03-31, 2023-06-30, ... 2025-12-31), compute cumulative counts as of that date: active_customers_cumulative = distinct users (is_staff = false) with at least one order placed_at on or before the quarter end; loyalty_members_cumulative = distinct users with a loyalty_accounts.enrolled_at on or before the quarter end; pct_customers_loyalty_members = loyalty_members_cumulative / active_customers_cumulative as a percentage; referred_customers_cumulative = distinct referred_user_id in referral_redemptions with redeemed_at on or before the quarter end; pct_customers_referred = referred_customers_cumulative / active_customers_cumulative as a percentage. Use calendar_days to get correct quarter-end dates. Order by quarter ascending.
     
     Check your query with the warehouse's dry_run tool, then hand it in with submit.

   • Viktor calls dry_run

     SELECT
       q.quarter AS quarter,
       (SELECT COUNT(DISTINCT o.user_id)
          FROM orders o
          JOIN users u ON u.id = o.user_id
         WHERE u.is_staff = false
           AND o.placed_at IS NOT NULL
           AND CAST(o.placed_at AS DATE) <= q.quarter_end) AS active_customers_cumulative,
       (SELECT COUNT(DISTINCT la.user_id)
          FROM loyalty_accounts la
          JOIN users u ON u.id = la.user_id
         WHERE u.is_staff = false
           AND CAST(la.enrolled_at AS DATE) <= q.quarter_end) AS loyalty_members_cumulative,
       ROUND(100.0 *
         (SELECT COUNT(DISTINCT la.user_id)
            FROM loyalty_accounts la
            JOIN users u ON u.id = la.user_id
           WHERE u.is_staff = false
             AND CAST(la.enrolled_at AS DATE) <= q.quarter_end)
         / NULLIF((SELECT COUNT(DISTINCT o.user_id)
                     FROM orders o
                     JOIN users u ON u.id = o.user_id
                    WHERE u.is_staff = false
                      AND o.placed_at IS NOT NULL
                      AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0)
       , 2) AS pct_customers_loyalty_members,
       (SELECT COUNT(DISTINCT rr.referred_user_id)
          FROM referral_redemptions rr
          JOIN users u ON u.id = rr.referred_user_id
         WHERE u.is_staff = false
           AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end) AS referred_customers_cumulative,
       ROUND(100.0 *
         (SELECT COUNT(DISTINCT rr.referred_user_id)
            FROM referral_redemptions rr
            JOIN users u ON u.id = rr.referred_user_id
           WHERE u.is_staff = false
             AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end)
         / NULLIF((SELECT COUNT(DISTINCT o.user_id)
                     FROM orders o
                     JOIN users u ON u.id = o.user_id
                    WHERE u.is_staff = false
                      AND o.placed_at IS NOT NULL
                      AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0)
       , 2) AS pct_customers_referred
     FROM (
       SELECT
         year_num,
         quarter_num,
         CONCAT(CAST(year_num AS VARCHAR), '-Q', CAST(quarter_num AS VARCHAR)) AS quarter,
         MAX(calendar_date) AS quarter_end
       FROM calendar_days
       WHERE year_num BETWEEN 2023 AND 2025
       GROUP BY year_num, quarter_num
     ) q
     ORDER BY q.year_num ASC, q.quarter_num ASC

   • The warehouse answers

     STATUS: COMPILES (dry run on the empty schema, no data read)
     COLUMNS: quarter, active_customers_cumulative, loyalty_members_cumulative, pct_customers_loyalty_members, referred_customers_cumulative, pct_customers_referred

   • ViktorCompiles cleanly with the expected columns. Submitting.
   • Viktor calls submit

     SELECT
       q.quarter AS quarter,
       (SELECT COUNT(DISTINCT o.user_id)
          FROM orders o
          JOIN users u ON u.id = o.user_id
         WHERE u.is_staff = false
           AND o.placed_at IS NOT NULL
           AND CAST(o.placed_at AS DATE) <= q.quarter_end) AS active_customers_cumulative,
       (SELECT COUNT(DISTINCT la.user_id)
          FROM loyalty_accounts la
          JOIN users u ON u.id = la.user_id
         WHERE u.is_staff = false
           AND CAST(la.enrolled_at AS DATE) <= q.quarter_end) AS loyalty_members_cumulative,
       ROUND(100.0 *
         (SELECT COUNT(DISTINCT la.user_id)
            FROM loyalty_accounts la
            JOIN users u ON u.id = la.user_id
           WHERE u.is_staff = false
             AND CAST(la.enrolled_at AS DATE) <= q.quarter_end)
         / NULLIF((SELECT COUNT(DISTINCT o.user_id)
                     FROM orders o
                     JOIN users u ON u.id = o.user_id
                    WHERE u.is_staff = false
                      AND o.placed_at IS NOT NULL
                      AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0)
       , 2) AS pct_customers_loyalty_members,
       (SELECT COUNT(DISTINCT rr.referred_user_id)
          FROM referral_redemptions rr
          JOIN users u ON u.id = rr.referred_user_id
         WHERE u.is_staff = false
           AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end) AS referred_customers_cumulative,
       ROUND(100.0 *
         (SELECT COUNT(DISTINCT rr.referred_user_id)
            FROM referral_redemptions rr
            JOIN users u ON u.id = rr.referred_user_id
           WHERE u.is_staff = false
             AND CAST(rr.redeemed_at AS DATE) <= q.quarter_end)
         / NULLIF((SELECT COUNT(DISTINCT o.user_id)
                     FROM orders o
                     JOIN users u ON u.id = o.user_id
                    WHERE u.is_staff = false
                      AND o.placed_at IS NOT NULL
                      AND CAST(o.placed_at AS DATE) <= q.quarter_end), 0)
       , 2) AS pct_customers_referred
     FROM (
       SELECT
         year_num,
         quarter_num,
         CONCAT(CAST(year_num AS VARCHAR), '-Q', CAST(quarter_num AS VARCHAR)) AS quarter,
         MAX(calendar_date) AS quarter_end
       FROM calendar_days
       WHERE year_num BETWEEN 2023 AND 2025
       GROUP BY year_num, quarter_num
     ) q
     ORDER BY q.year_num ASC, q.quarter_num ASC

   • The warehouse answers

     Submitted to tonight's batch. Your work on this request is done.

   • ViktorSubmitted. The report computes, for each of the 12 quarter-ends from 2023-Q1 through 2025-Q4, the cumulative distinct non-staff customers with an order, cumulative loyalty enrollees, and cumulative referred customers, plus their shares of the active base — aggregated platform-wide across all tenants since the question wasn't merchant-specific.

   Not shown here: 240 KB of context the agent was given, its instructions and the schema documentation; it is in the raw transcript.

   Viktor's transcript (274 KB) · Ingrid Solberg's transcript (906 KB) · Aisha Rahman's transcript (261 KB) · the night's plan (6 KB) · the night's reports (5 KB) · the week's memo (4 KB)