| Last active | User | First match | Questions | Cost | Feedback |
|---|---|---|---|---|---|
| 2026-09-18 10:54 | yordan@dext.com | How many active accounts do we have? | 1 | $8.3274 | — |
| 2026-09-17 14:59 | yordan@dext.com | What is our average customer LTV (total MRR over customer lifetime to date)? | 1 | $34.4365 | — |
| 2026-09-15 13:27 | yordan@dext.com | Partners MRR by month, last 6 months | 2 | $68.7470 | — |
| 2026-09-08 06:55 | yordan@dext.com | MRR for the last 12 months, month over month | 1 | $0.6828 | — |
| 2026-09-04 20:01 | yordan@dext.com | ACV for Dext today | 4 | $6.8047 | — |
| 2026-09-04 13:15 | yordan@dext.com | What is our ARR (Annual Recurring Revenue) for the last 12 months, broken down month over month? | 9 | $10.9555 | — |
| 2026-09-01 13:53 | yordan@dext.com | Show me partner accounts (finance_account_type = Accountant) with their company name, CRN, netsuite account number, last login date, next invoice date, account manager, and any billing or invoice outstanding amounts | 1 | $1.1598 | — |
| 2026-09-01 13:08 | yordan@dext.com | Partner accounts with outstanding invoices including company name, NetSuite account number, company registration number, subsidiary, outstanding debt by aging buckets (current 15/7/2026-13/8/2026, 30 days 15/6/2026-14/7/2026, 60 days 16/5/2026-14/6/2026, 90 days before 16/5/2026, overdue over 90 days), total outstanding amount, account manager name, last login date, next invoice date | 1 | $0.8164 | — |
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.