Agents / AI Centre of Excellence

Use-Case Matching Agent

Reads an incoming use-case request, searches the catalogue and answers whether a model, dataset or agent already does the job, so no business unit builds a duplicate.

InternalAggregated onlyAgent runMinimal riskGovernance · BU Restricted · 214 runs / 30dOwner AI Centre of Excellence

Runs, last 30 days

214

Tools

4

Data scopes

3

Human checkpoints

1

About this agent

Reads an incoming use-case request, searches the catalogue and answers whether a model, dataset or agent already does the job, so no business unit builds a duplicate. Where nothing fits, it files the request in the use-case pipeline with the evidence the Use-Case Sizing Agent needs.

Tools4

  • Catalogue search index
  • Use-case request ledger
  • Reuse matching rubric
  • Use-case pipeline writer

Data access scope3

  • Read-only: published catalogue metadata and usage metrics
  • Read-only: failed searches and denied access requests
  • Write: use-case records and match scores only

Guardrails3

  • Never marks a use case as already served below 0.8 match confidence; ambiguous matches are listed for the requester to confirm
  • Cannot commit budget or change a pipeline rank set by the Group AI Steering Committee
  • Requester identity is masked in aggregated demand signals

Human-in-the-loop1

  • Group AI Steering Committee ranks and funds the use-case pipeline each month

Live demo run

Watch the agent execute a real scenario step by step, every tool call, validation, and human checkpoint is traced and auditable. Typical run: ~5.1s.

Used in workflows

Retiring this asset would require these chains to be re-pointed first.

Audit

Updated 2026-07-26. Run traces retained 24 months for audit under the platform governance policy.