Projects

Vega research copilot

Vega Sciences · R. Mehta · Research · window 2026-06-20 2026-07-25 · no residency constraint

Scope

Resolved from the filter, pinned to sealed snapshots

Knowledge BaseCustomer SupportCatalogue

Excluded: gpt-4.1-ft-vega014,532 calls removed from every figure here.

1 project in this assessment

Each carries its own scope; the budget above covers all of them

Vega Research Copilot

2026-06-202026-07-25 · excluding gpt-4.1-ft-vega01

Accounts
1
Workloads
7
Spend / 30d
$25,740

Knowledge Base

label · app=knowledge-base

read from a log label · 3 workloads

  • 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

  • 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

  • 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

Run configurations

Set up once, executed on a schedule

What a run does

Three stages — A to C already happened on the connectors

  1. 1

    Recommendation

    Turning each classified workload into a concrete target configuration.

  2. 2

    Replay

    Re-running real traffic against the proposal and judging the output.

  3. 3

    Cost report

    Pricing today, three alternative futures, and writing it down.