Give me key business metrics and trends for the last week (Sept 15-22, 2026) - revenue, new customers, churn, or usage highlights
Basis: New Business customers, reacquisitions, churn and net Prepare revenue movements—Monthly ACV for Part, 15–22 September 2026, limited to dates with available booking movements. This figure does not apply the governed filter on omni_dbt__eds_all_accounts.is_suspended_dext, so it includes rows the standard report excludes.
Per-step detail — each LLM call, each Omni request, each rejected draft —
is traced to stdout only and is not stored, so it cannot be shown here.
Query attempts counts run_query executions, not model turns.
WITH movement_grain AS (
SELECT
omni_dbt__eds_calendar_day."DATE_DAY" AS "Date",
omni_dbt__eds_all_accounts."FINANCE_ACCOUNT_TYPE" AS "Finance Account Type",
omni_dbt__eds_bookings_changes."DERIVED_ACCOUNT_DAY_KEY" AS "Movement Key",
MAX(omni_dbt__eds_bookings_changes."PREPARE_BOOKINGS_MONTHLY_ACV_MOVEMENT") AS "Partner Detailed Movement",
MAX(omni_dbt__eds_bookings_changes."BASIC_PREPARE_BOOKINGS_MONTHLY_ACV_MOVEMENT") AS "Partner Basic Movement",
MAX(omni_dbt__eds_bookings_changes."PREPARE_BOOKINGS_MONTHLY_ACV_CHANGE_AMOUNT") AS "Partner Revenue Change",
MAX(omni_dbt__eds_bookings_changes."PREPARE_BOOKINGS_MRR_MOVEMENT") AS "Direct Detailed Movement",
MAX(omni_dbt__eds_bookings_changes."BASIC_PREPARE_BOOKINGS_MRR_MOVEMENT") AS "Direct Basic Movement",
MAX(omni_dbt__eds_bookings_changes."PREPARE_BOOKINGS_MRR_CHANGE_AMOUNT") AS "Direct Revenue Change"
FROM PROD."EDS_ALL_ACCOUNTS" AS omni_dbt__eds_all_accounts
INNER JOIN PROD."EDS_CALENDAR_DAY" AS omni_dbt__eds_calendar_day
ON omni_dbt__eds_calendar_day."DATE_DAY" >= omni_dbt__eds_all_accounts."VALID_FROM" AND omni_dbt__eds_calendar_day."DATE_DAY" <= omni_dbt__eds_all_accounts."VALID_TO"
LEFT JOIN PROD."EDS_BOOKINGS_CHANGES" AS omni_dbt__eds_bookings_changes
ON omni_dbt__eds_all_accounts."DERIVED_ACCOUNT_ID" = omni_dbt__eds_bookings_changes."DERIVED_ACCOUNT_ID" AND omni_dbt__eds_bookings_changes."CHANGE_DATE" = omni_dbt__eds_calendar_day."DATE_DAY"
WHERE omni_dbt__eds_calendar_day."DATE_DAY" >= '2026-09-15'
AND omni_dbt__eds_calendar_day."DATE_DAY" <= '2026-09-22'
AND omni_dbt__eds_all_accounts."FINANCE_ACCOUNT_TYPE" IN ('Accountant', 'Corporate')
AND COALESCE(omni_dbt__eds_all_accounts."IS_DEXT_DEMO", FALSE) = FALSE
AND omni_dbt__eds_all_accounts."FRANCHISE_NAME" IS NULL
AND (omni_dbt__eds_all_accounts."SALESFORCE_ACCOUNT_TYPE" <> 'Reseller' OR omni_dbt__eds_all_accounts."SALESFORCE_ACCOUNT_TYPE" IS NULL)
AND omni_dbt__eds_bookings_changes."DERIVED_ACCOUNT_DAY_KEY" IS NOT NULL
GROUP BY
omni_dbt__eds_calendar_day."DATE_DAY",
omni_dbt__eds_all_accounts."FINANCE_ACCOUNT_TYPE",
omni_dbt__eds_bookings_changes."DERIVED_ACCOUNT_DAY_KEY"
), daily AS (
SELECT
"Date" AS "Date",
COUNT(DISTINCT CASE WHEN "Finance Account Type" = 'Accountant' AND "Partner Detailed Movement" = 'New Business' THEN "Movement Key" END) AS "New Partners",
COALESCE(SUM(CASE WHEN "Finance Account Type" = 'Accountant' AND "Partner Detailed Movement" = 'New Business' THEN "Partner Revenue Change" END), 0) AS "New Partner Monthly ACV",
COUNT(DISTINCT CASE WHEN "Finance Account Type" = 'Accountant' AND "Partner Detailed Movement" IN ('Winback', 'Reactivation') THEN "Movement Key" END) AS "Reacquired Partners",
COUNT(DISTINCT CASE WHEN "Finance Account Type" = 'Accountant' AND "Partner Basic Movement" = 'Churn' THEN "Movement Key" END) AS "Churned Partners",
COALESCE(-SUM(CASE WHEN "Finance Account Type" = 'Accountant' AND "Partner Basic Movement" = 'Churn' THEN "Partner Revenue Change" END), 0) AS "Churned Partner Monthly ACV",
COALESCE(SUM(CASE WHEN "Finance Account Type" = 'Accountant' THEN "Partner Revenue Change" END), 0) AS "Net Partner Monthly ACV Change",
COUNT(DISTINCT CASE WHEN "Finance Account Type" = 'Corporate' AND "Direct Detailed Movement" = 'New Business' THEN "Movement Key" END) AS "New Direct Customers",
COALESCE(SUM(CASE WHEN "Finance Account Type" = 'Corporate' AND "Direct Detailed Movement" = 'New Business' THEN "Direct Revenue Change" END), 0) AS "New Direct MRR",
COUNT(DISTINCT CASE WHEN "Finance Account Type" = 'Corporate' AND "Direct Detailed Movement" IN ('Winback', 'Reactivation') THEN "Movement Key" END) AS "Reacquired Direct Customers",
COUNT(DISTINCT CASE WHEN "Finance Account Type" = 'Corporate' AND "Direct Basic Movement" = 'Churn' THEN "Movement Key" END) AS "Churned Direct Customers",
COALESCE(-SUM(CASE WHEN "Finance Account Type" = 'Corporate' AND "Direct Basic Movement" = 'Churn' THEN "Direct Revenue Change" END), 0) AS "Churned Direct MRR",
COALESCE(SUM(CASE WHEN "Finance Account Type" = 'Corporate' THEN "Direct Revenue Change" END), 0) AS "Net Direct MRR Change"
FROM movement_grain
GROUP BY "Date"
)
SELECT
MIN("Date") AS "First Available Date",
MAX("Date") AS "Last Available Date",
COUNT(DISTINCT "Date") AS "Days With Booking Movements",
SUM("New Partners") AS "New Partners",
SUM("New Partner Monthly ACV") AS "New Partner Monthly ACV",
SUM("Reacquired Partners") AS "Reacquired Partners",
SUM("Churned Partners") AS "Churned Partners",
SUM("Churned Partner Monthly ACV") AS "Churned Partner Monthly ACV",
SUM("Net Partner Monthly ACV Change") AS "Net Partner Monthly ACV Change",
MAX_BY("Date", "Net Partner Monthly ACV Change") AS "Strongest Partner Revenue Day",
MIN_BY("Date", "Net Partner Monthly ACV Change") AS "Weakest Partner Revenue Day",
SUM("New Direct Customers") AS "New Direct Customers",
SUM("New Direct MRR") AS "New Direct MRR",
SUM("Reacquired Direct Customers") AS "Reacquired Direct Customers",
SUM("Churned Direct Customers") AS "Churned Direct Customers",
SUM("Churned Direct MRR") AS "Churned Direct MRR",
SUM("Net Direct MRR Change") AS "Net Direct MRR Change",
MAX_BY("Date", "Net Direct MRR Change") AS "Strongest Direct Revenue Day",
MIN_BY("Date", "Net Direct MRR Change") AS "Weakest Direct Revenue Day"
FROM daily
LIMIT 1
No feedback linked to this request.
Cost is the LLM completion spend LiteLLM priced for each call, summed per
request.
Chandler is running on the Codex CLI, which draws ChatGPT plan quota
rather than per-token API billing, so this figure is not money paid —
it is what the same traffic would have cost on the API, priced from the
token counts Codex reports. Read it as the size of the bill avoided.
Two known limits: embedding spend is not recorded, so
retrieval and matching cost is missing, and because the figure is one sum
per request it cannot be split by model within a request — a
request's classifier and agent calls can use different models while
llm_model holds only one name.
Only authenticated calls are logged, USAGE_LOG_ENABLED can
switch logging off, and log writes are fail-soft — this is not a complete
record of traffic. Questions are grouped into sessions: a session is
exact when the caller echoed its id back to us and otherwise inferred from
a 30-minute gap in that user’s activity, so a grouping is only as
good as the source shown on the session itself. A call with no
attributable user gets no session at all; those questions are listed
separately rather than dropped.