ForgeTrack
Start free
A Method

From session to substantiation.

Every number on every ForgeTrack report is traceable back to the events that produced it — recorded, not reconstructed. The pipeline has five stages, and every stage operates against the same append-only event log conforming to the GAAIM specification.

01 The five stages

Each stage has a single responsibility, a fixed input, and a fixed output. Failures are contained at the stage that caused them.

01 · Capture

Ingest every event.

AI provider sessions, VCS commits, pull requests, deploys, manual work notes, explicit architectural decisions. Events arrive via webhooks, SDK clients, or direct API calls, and each one is timestamped, hashed, and written to the append-only store.

Multi-provider · webhooks · SDK
02 · Score

Classify and weight.

Each event is classified by kind (session, commit, decision, etc.), tagged to a work item, and weighted against its benchmark category. The classifier is deterministic and versioned — re-running on the same inputs yields the same outputs.

Classifier v1 · benchmark DB
03 · Measure

Convert to equivalent weeks.

The Effort Engine applies expertise multipliers, confidence intervals, and human corrections to produce equivalent engineering-week values per work item. Every derived number is a pure function of the recorded events plus the engine version.

Effort engine · HITL calibration
04 · Document

Assemble narratives.

The document assembler composes the outputs the audience expects: four-part test narratives for IRS substantiation, engineering summaries for investor decks, work papers for CPAs. All derived from the same underlying measurements — no duplication, no drift.

SQL-first assembly · 22 locales
05 · Publish

Seal and export.

Reports are rendered to PDF, XLSX, CSV, and JSON, hashed with SHA-256, signed, and written to tenant storage. Post-generation tampering is detectable via hash comparison. Every published artifact is independently verifiable.

PDF · XLSX · CSV · JSON · SHA-256
02 Integrity

Integrity across stages

The same event log feeds every report. The same benchmark database anchors every measurement. The same document assembler produces every artifact. That is not a design preference — it is the only way a CPA or auditor can trust a report they did not watch being generated.

If two reports disagree on any number, the logs are the tiebreaker. If the logs themselves are challenged, the SHA-256 hashes are the tiebreaker. If the hashes are challenged, GAAIM is the tiebreaker. There is always a document that wins the argument.