CK Rock AI / Selected work / tokenledger

Public reference release in preparation

tokenledger / By Chandler Klose

One activity stream.
Every reported
number reproducible.

A reference implementation for AI businesses that meter tokens and seats. Report a business metric, explain a change, and reproduce the original result.

Built from the SOX-controlled subscriber-metrics work I ran at SiriusXM for 19 years.

The demonstration, explained

Follow one number through a change.

The local demonstration uses synthetic data on DuckDB. This page describes that workflow; it is not a live connection to the database.

  1. 01 / Report

    Start with July’s token yield.

    Calculate recognized revenue per million tokens. Retain the inputs and definition needed to reproduce the result.

  2. 02 / Explain

    A late invoice arrives.

    Revenue changes while the token denominator stays fixed. A bridge explains the movement between the two results.

  3. 03 / Reproduce

    Replay the original receipt.

    Recover the earlier answer using its original evidence and definition, even though the system now knows more.

The model

Keep the events. Make the rules explicit.

A fourteen-column activity envelope carries event identity, timing, and JSON feature data. Typed query-time projections give those features meaning. New reporting questions can reuse the same stream while retaining explicit definitions and evidence.

  1. 01 / PersistActivity streamSource events + JSON features
  2. 02 / InterpretTyped projectionsQuery-time structures
  3. 03 / CalculateVersioned definitionsRules + reporting cutoffs
  4. 04 / ReportReported resultMetrics + explanatory bridges
  5. 05 / ReproduceReceiptInputs + calculation identity
Conceptual architecture of the reporting path. One source stream does not eliminate query work, temporary execution state, or retained evidence artifacts.

Scope

Local execution. Cloud evidence. Explicit limits.

What has been built

  • A small, synthetic DuckDB demonstration.
  • Versioned metric definitions and original-result replay.
  • Source reconciliation and receipt-backed reporting evidence.
  • A retained comparison with an independent BigQuery baseline.

What still needs to be assessed

The BigQuery comparison has resource trade-offs; it does not establish a general speed or cost advantage. Comparative agent accuracy and token efficiency remain unmeasured.

Reproducibility alone does not prove source completeness, approval of an accounting policy, or SOX operating effectiveness.

For people and their agents

Make the work assessable.

The reference release is being prepared around three paths: run the small example, understand how the result is derived, and assess it through an open-book reproduction exercise.

Questions for an evaluator

  • Can you reproduce the reported token yield?
  • Can you explain the late-invoice bridge?
  • Can a metric definition change without erasing the old answer?
  • Does incomplete source evidence hold publication?

Release status

The implementation is currently private. Public installation instructions, executable tasks, and retained measurement evidence will be linked here when the reference release is published.

The overview on this page is available now. It is not a substitute for running and checking the release.

What would your team ask next?

The interesting work begins with your source contracts, customer identities, reporting policy, and the people who own the number.

Discuss the approach More work from CK Rock AI