← All case studies

Engine B · CLA · 2025

An AI-first substantive testing platform for a global consultancy

I led the design of an AI-first substantive testing platform inside a global consulting firm, standardising how audits are executed across teams and geographies. Working as the first product designer, I established the product design practice, partnered closely with engineering and audit SMEs, and designed a scalable agent ecosystem that preserved human judgment while improving consistency and audit quality. The platform reduced fragmented workflows to a single global standard and saved an estimated 30 to 40 thousand auditor hours.

30–40kAuditor hours saved
6 to 8 → 1Approaches unified into one global standard
1,000+Auditors on the platform

Deep integration with CLA's core PFX system was compelling: seamless data flow, role-aware experiences across associates, managers, and partners. But CLA's data architecture had grown organically across many external vendors and stacks; the surrounding infrastructure was too fragmented to merge safely within our constraints.

We chose momentum with integrity: a robust, auditable agent ecosystem with limited manual round-tripping, built so deeper integration could layer in once the broader data architecture matured.

Integration engineIngests & normalises core financial data — trial balances, general ledgers
Extraction agentsOCR + LLM pull artefacts like invoices at scale, without retaining data unnecessarily
Substantive Agent EngineReusable core across accounts receivable, payable, and investments
01

Auditor selects a client & engagement

02

Agent generates a truly random, methodology-approved sample

03

Missing artefacts extracted & fed back automatically

04

Auditor reviews, confirms, and finalises the test

Sandbox & SME review
100 auditors, production
1,000 users
Org-wide rollout

Try the AR substantive testing flow. Select accounts, run an inquiry, and review analytics.

Role
Lead Product Designer
Year
2025
Focus
AI · SaaS · Enterprise