Grounding a Big-Four AI programme in the firm's own knowledge.
A firm-wide knowledge and generation platform for one of the Big Four, grounded in decades of engagement libraries with the audit trail regulators expect.
Client
EY
Sector
Professional Services
Duration
18 months (ongoing)
Team
9 (senior AI engineers, product engineers, retrieval specialists, an advisory partner)
Where EY was when we started.
EY's engagement teams sit on hundreds of thousands of prior workpapers, methodologies, regulatory interpretations, and industry playbooks. The intellectual capital is real; the retrieval is not. Practitioners rely on personal networks and Slack channels to find the paragraph they need, and the firm — like every professional-services firm — is looking at generative AI as both an opportunity and a live regulatory question.
The problem, unvarnished.
- Institutional knowledge spread across SharePoint, engagement-management systems, methodology repositories, and personal drives
- Client confidentiality and engagement segregation are non-negotiable — retrieval must respect the permission model
- Generative outputs going to clients or regulators must carry citations; hallucination is a career risk, not just a UX one
- The firm needed a single AI platform pattern rather than a hundred practice-level experiments
How we scoped and sequenced the work.
01
Permission-aware indexing
We built the ingestion layer to respect the firm's existing IAM model. A retrieval request only surfaces documents the requesting user is allowed to read — engagement-team scope, client scope, and firm scope enforced at query time, not at post-processing.
02
Grounded generation with citations
Every generated paragraph carries a citation into the source document and the specific passage. Reviewers can jump to the excerpt in one click. Uncited claims are refused by the system, not softened by policy.
03
Evaluation as a first-class product surface
The AI platform team owns retrieval quality dashboards, evaluation runs, and the feedback loops that catch drift. Generation quality is measured continuously against a growing golden set of firm-approved answers.
04
Firm-wide rollout with practice-level adaptation
One platform, multiple practices. Assurance, Tax, Advisory, and Consulting each get retrieval scopes, prompt patterns, and evaluation sets tuned to their subject matter — without forking the platform.
What we shipped.
A permissioned knowledge and generation platform standing between the firm's document estate and its practitioners. Retrieval respects the IAM model; generation carries citations; evaluation is continuous. Deployed to Assurance and Advisory first, with a rollout path to Tax and Consulting following the same platform pattern.
The numbers that matter.
12M+
Documents under continuous index
SharePoint, methodology repos, engagement libraries, and prior workpapers — indexed with permission enforcement.
72%
Reduction in first-draft author-hours
For controls documentation, prior-work summaries, and regulatory-response drafts, measured over the first three quarters of production.
100%
Answers cite their sources
Uncited generation is a system-level refusal, not a policy request. Every reviewer can jump to the underlying passage.
What we built it on.
“The retrieval quality is what changed the internal conversation about AI. Once we could show partners a paragraph with the source paragraph next to it, the question stopped being 'is this safe' and started being 'where else can we ship this'.”
Bring us your professional services brief.
Book a 30-minute discovery call. A senior practitioner from the same practice that shipped this engagement will scope yours.
or email contact@headify.com