Harbridge & Quill (fictional demo) Alterspective
Sharedo AuditSnapshot · 2026-07-01
Engagement · harbridge-quill-demo

Provenance

Data & sources.

Every figure in this report is computed directly from the synthetic demonstration corpus below — a fictional firm's book, generated to exercise every lens with a known, verifiable ground truth.

What was analysed

Corpus elementCount
Matters30,000
Instructions8,000
Parties60,046
Connections150,666
Keydates110,587
matters = 30,000Matters30,000instructions = 8,000Instructions8,000parties = 60,046Parties60,046connections = 150,666Connections150,666keydates = 110,587Keydates110,587
The synthetic demonstration corpus, by element.

How it was computed

Method

  • Configuration & lifecycle — form-field fill rates, phase ages, and standards alignment computed via pandas over the corpus CSVs (the productised pipeline: insights.audit).
  • Matter taxonomy & universe — all-MiniLM-L6-v2 sentence embeddings, UMAP 3D projection, KMeans clustering, cluster labels from a local LLM (SGLang) — all on-premise.
  • Entity resolution, limitation triage, workload, conflict radar — direct queries over the corpus, proven on a live client engagement and being generalised into the productised pipeline.
On real engagements: client data never leaves a controlled environment — analysis runs on-premise, and only aggregates and evidence trails appear in deliverables. This report is entirely synthetic data; no client information is represented anywhere in it.