Chandler · usage
← Back to sessions

Session

User
kathryn.buckley@dext.com · Kathryn Buckley
Started
2026-08-17 09:47
Last activity
2026-08-17 09:57
Questions
7
Grouping
backfill — reconstructed from timing by migration 011
session_id
e9ea0ef1-4633-4386-bdd5-66856f76b149

Transcript

  1. 2026-08-17 09:47 ask success $0.8667 154.7 s full detail →
    Using the same engagement definition as the Feature Adoption Omni dashboard (https://dext.omniapp.co/dashboards/feature-adoption), what is the percentage of Partner accounts and the percentage of Client accounts using Item Messaging, on average over the last 6 months?
    No answer recorded.
    Product Usage - Users
  2. 2026-08-17 09:48 ask success $0.0285 13.1 s full detail →
    What does the Feature Adoption Omni dashboard measure? What are the exact feature names, fields, and adoption/engagement definitions it uses (e.g. for Item Messaging, Paperwork Requests, WhatsApp communication)?
    No answer recorded.
  3. 2026-08-17 09:50 ask success $0.0235 10.5 s full detail →
    What is Item Messaging, Paperwork Requests, and WhatsApp communication in Dext? Are there usage/engagement measures or events tracking these features?
    No answer recorded.
  4. 2026-08-17 09:52 ask success $0.5751 93.4 s full detail →
    What percentage of Partner accounts used Item Messaging in the last 6 months, on average per month?
    No answer recorded.
    Product Usage - Accounts
  5. 2026-08-17 09:54 ask success $0.6242 142.3 s full detail →
    What percentage of Client accounts used the Paperwork Requests feature in the last 6 months, on average per month?
    No answer recorded.
    15 rows Product Usage - Accounts
  6. 2026-08-17 09:56 ask success $0.5181 123.4 s full detail →
    What percentage of accounts used WhatsApp communication in the last 6 months, on average per month, broken down by Partner vs Client account type?
    No answer recorded.
    Customer Support SLA Metrics
  7. 2026-08-17 09:57 ask success $0.0232 10.2 s full detail →
    List all topics, views, or fields in the data model related to messaging, paperwork requests, missing paperwork, or WhatsApp within Dext Prepare or the practice management product.
    No answer recorded.

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.