Of the AI Assist guidances that are currently active (switched on), what share were generated automatically by Dext (auto-generated from edit history) versus written by the customer? Also, of AI Assist suggestions applied since tracking began, what share were auto-applied versus manually accepted?
Basis: Available AI Assist guidance-created and suggestion-applied totals for currently eligible accounts;, Latest available account snapshot; AI Assist activity from the beginning of tracking through 28 Sep. Governed filters applied. Every row's «Auto-Applied Suggestion Share» came back empty. That is usually a wrong field or join rather than missing data.
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 activity_by_account AS (
SELECT
omni_dbt__eds_prepare_account_user_event_activity."ACCOUNT_CRN" AS account_crn,
MIN(omni_dbt__eds_prepare_account_user_event_activity."OCCURRED_DATE") AS first_activity_date,
MAX(omni_dbt__eds_prepare_account_user_event_activity."OCCURRED_DATE") AS latest_activity_date,
SUM(omni_dbt__eds_prepare_account_user_event_activity."GUIDANCE_CREATED_VOLUME") AS guidances_created,
SUM(omni_dbt__eds_prepare_account_user_event_activity."SUGGESTION_APPLIED_VOLUME") AS suggestions_applied
FROM PROD."EDS_PREPARE_ACCOUNT_USER_EVENT_ACTIVITY" AS omni_dbt__eds_prepare_account_user_event_activity
WHERE omni_dbt__eds_prepare_account_user_event_activity."OCCURRED_DATE" <= CURRENT_DATE()
AND (
omni_dbt__eds_prepare_account_user_event_activity."GUIDANCE_CREATED_VOLUME" > 0
OR omni_dbt__eds_prepare_account_user_event_activity."SUGGESTION_APPLIED_VOLUME" > 0
)
GROUP BY omni_dbt__eds_prepare_account_user_event_activity."ACCOUNT_CRN"
),
current_accounts AS (
SELECT DISTINCT
omni_dbt__eds_all_accounts."ACCOUNT_CRN" AS account_crn
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"
WHERE omni_dbt__eds_calendar_day."IS_LATEST_AVAILABLE_DATE" = TRUE
AND (omni_dbt__eds_all_accounts."IS_DEXT_DEMO" = FALSE OR omni_dbt__eds_all_accounts."IS_DEXT_DEMO" IS NULL)
AND omni_dbt__eds_all_accounts."IS_SUSPENDED_DEXT" = FALSE
AND omni_dbt__eds_all_accounts."ACCOUNT_CRN" IS NOT NULL
),
eligible_activity AS (
SELECT
activity_by_account.first_activity_date,
activity_by_account.latest_activity_date,
activity_by_account.guidances_created,
activity_by_account.suggestions_applied
FROM current_accounts
INNER JOIN activity_by_account
ON current_accounts.account_crn = activity_by_account.account_crn
)
SELECT
MIN(eligible_activity.first_activity_date) AS "First Available AI Assist Tracking Date",
MAX(eligible_activity.latest_activity_date) AS "Latest Available AI Assist Activity Date",
COALESCE(SUM(eligible_activity.guidances_created), 0) AS "Guidances Created Since Tracking Began",
CAST(NULL AS NUMBER) AS "Currently Active Guidances",
CAST(NULL AS NUMBER) AS "Auto-Generated Active Guidances",
CAST(NULL AS NUMBER) AS "Customer-Written Active Guidances",
CAST(NULL AS NUMBER(10, 4)) AS "Auto-Generated Guidance Share",
CAST(NULL AS NUMBER(10, 4)) AS "Customer-Written Guidance Share",
COALESCE(SUM(eligible_activity.suggestions_applied), 0) AS "Suggestions Applied Since Tracking Began",
CAST(NULL AS NUMBER) AS "Auto-Applied Suggestions",
CAST(NULL AS NUMBER) AS "Manually Accepted Suggestions",
CAST(NULL AS NUMBER(10, 4)) AS "Auto-Applied Suggestion Share",
CAST(NULL AS NUMBER(10, 4)) AS "Manually Accepted Suggestion Share"
FROM eligible_activity
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.