Chandler · usage
← Back to sessions ← Back to this session

Prompt

Total number of AI Assist suggestions created and applied to date (all time, global), and the number of partner practices and client businesses that have had at least one AI Assist suggestion.

Outcome
success
Cost
$67.8887
excludes embeddings
Latency
205.6 s
Query attempts
1
Rows returned
1
Tokens
8,286,137 / 33,274
in / out

Request

request_id
3a4dded7-ff96-4345-9f90-7c3ee19ddc5f
When
2026-09-27 14:51
Tool
ask
User
gerty.bester@dext.com · Gerty Bester
Identity
google
Session
f00d6c66-f511-4150-9295-0cce7ff2a5f3
Model
gpt-5.6-sol

Route taken

Topic
Product Usage - Users
Omni model
e407bba6-4fae-4079-ac4e-cd6cf8fdf6f8
Match method
agent loop
Nudge shown
—
Question shape
lookup
Caveat raised
—
Sharper question offered
—
Shown to user
Basis: AI Assist suggestions created and applied, plus partner practices and client businesses with at leas, all recorded history through the latest available account snapshot. Governed filters applied.

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.

SQL that ran

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 last_activity_date,
    SUM(omni_dbt__eds_prepare_account_user_event_activity."SUGGESTION_CREATED_VOLUME") AS suggestions_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."SUGGESTION_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,
    omni_dbt__eds_all_accounts."FINANCE_ACCOUNT_TYPE" AS finance_account_type,
    omni_dbt__eds_all_accounts."PARENT_ACCOUNT_CRN" AS parent_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."SALESFORCE_ACCOUNT_TYPE" <> 'Reseller'
    AND omni_dbt__eds_all_accounts."ACCOUNT_CRN" IS NOT NULL
),
eligible_activity AS (
  SELECT
    current_accounts.account_crn,
    current_accounts.finance_account_type,
    current_accounts.parent_account_crn,
    activity_by_account.first_activity_date,
    activity_by_account.last_activity_date,
    activity_by_account.suggestions_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 AI Assist Suggestion Date",
  MAX(eligible_activity.last_activity_date) AS "Latest AI Assist Activity Date",
  COALESCE(SUM(eligible_activity.suggestions_created), 0) AS "AI Assist Suggestions Created",
  COALESCE(SUM(eligible_activity.suggestions_applied), 0) AS "AI Assist Suggestions Applied",
  COUNT(DISTINCT CASE
    WHEN eligible_activity.suggestions_created > 0
      AND eligible_activity.finance_account_type = 'Accountant'
      THEN eligible_activity.account_crn
    WHEN eligible_activity.suggestions_created > 0
      AND eligible_activity.finance_account_type = 'Corporate'
      AND eligible_activity.parent_account_crn IN (
        SELECT account_crn
        FROM current_accounts
        WHERE finance_account_type = 'Accountant'
      )
      THEN eligible_activity.parent_account_crn
  END) AS "Partner Practices With At Least One Suggestion",
  COUNT(DISTINCT CASE
    WHEN eligible_activity.suggestions_created > 0
      AND eligible_activity.finance_account_type = 'Corporate'
      THEN eligible_activity.account_crn
  END) AS "Client Businesses With At Least One Suggestion"
FROM eligible_activity
LIMIT 1

Feedback

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.