CONSULTING · ENERGY AND MINING

An AI-first process architecture workbench with a global consultancy

Consultants map how work really runs before redesigning it for AI. Wexa built a workbench on Wexa that turns client documents and workshops into a governed process graph and an AI-first target design.

Download this case as PDF Book a demo

functional requirements specified and built
typed entities in the process ontology
process hierarchy, two-pass extraction
deployment requested for a live client engagement

CLIENT: Global management consultancy, for an energy and mining client
REGION: Global / Australia
WHEN: 2026
ENGAGEMENT: Partner build
WEXA COMPONENTS: Wexa · automatic ontology discovery · context graph · Processbench

01Case 21

The challenge

Process mapping is workshop-driven, slow and goes stale
Discovery tools stop at the as-is and do not hand over to an agent design
Consulting work needs provenance, review and approval at every step

What Wexa built

Multi-format ingestion (documents, decks, spreadsheets, transcripts, OCR) with source provenance
A 12-entity process ontology and L0–L4 hierarchy extracted in two passes
Friction-pattern detection: rework, wait time, duplicate entry
AI-first target process: generated, constrained, then human-approved versions
Object-level review, versioning and RBAC; agents may suggest but never approve; hash-chained audit
Dedicated partner environment, white-labelled as Processbench

02Case 21

How it runs on Wexa

FigureHow this use case runs on Wexa: client systems connected, ontology discovered, context graph in the Wexa memory layer, agents and process flows, and governance. Highlighted components are central to this use case.

03Case 21

Solution architecture

FigureWorkbench architecture on Wexa (redrawn from the project specification).

04Case 21

Results

Measure	Before / without Wexa	With Wexa
Process discovery effort per client engagement	12 weeks, 4 consultants	4 weeks, 2 consultants
Annual cost of the process	$480K	$80K
Time to implement the AI solution	6 months	6 weeks
AI build cost (one-time)	$480K	$44K
AI operating cost per year (models, infrastructure, upkeep, platform)	$312K	$166K
Total AI cost in year 1	$792K	$210K

With Wexa

net annual value to the client after Wexa's own operating cost

faster to implement

lower AI operating cost

less AI spend in year 1

The consultancy named Wexa as a technology partner and included it in a mining-sector client proposal (August 2026)
The consultancy asked for commercials to deploy the workbench at its client for a 6–8 week engagement; management reports the client converted
The same build became Processbench, Wexa's process digital-twin application on Wexa

Initial proof of concept delivered without fees; deployments are priced as license, support and operations.