Vega Research

Stale

northwind.onmicrosoft.com / sub-2290-vega · Azure AI Foundry · sub-2290-vega · eastus

3 applications, 7 workloads

From snapshot snap-2026-08-27-9d04, taken 2026-08-27

An application is the customer's named system; a workload is a distinct model-call pattern inside it. Identity comes from a fingerprint — the name is decoration on top, and renaming one never changes what was measured.

Knowledge Base

label · app=knowledge-base

read from a log label · 3 workloads

$20,222AFVega Researchsub-2290-vega

Document Summarisercomplex-agenticinferred from logs
wf-vg021c9 · confidence high
$19,272
MEASURED
Internal Searchmoderateinferred from logs
wf-vg4e918 · confidence medium
$792
MODELLED
Meeting Notessimpleinferred from logs
wf-vg68e71 · confidence high
$158
MODELLED

Customer Support

declared · declared by customer

the customer told us this name · 2 workloads

$3,564AFVega Researchsub-2290-vega

Support Triagesimpledeclared
wf-vg107e2 · confidence high
$2,376
MODELLED
Chat Assistantmoderatedeclared
wf-vg3b6f4 · confidence medium
$1,188
MODELLED

Catalogue

hash · sha256:4f1c…9ab2

derived from a fingerprint — no label existed · 2 workloads

$1,954AFVega Researchsub-2290-vega

Product Classifiersimpleinferred from logs
wf-vg2d3aa · confidence high
$1,584
MODELLED
Contract Extractortier unknown — we couldn't tellinferred from logs
wf-vg54c0d · confidence low
$370
ASSUMED