Skip to main content
ThinkscoopEngineering
EngagementsCapabilitiesWorkApproachNotesAboutStart a build
EngagementsCapabilitiesWorkApproachNotesAboutStart a build

Thinkscoop Engineering

Senior engineers, AI augmented. Not AI washed.

Engagements

  • AI MVP Sprint
  • AI Integration Pod
  • Agentic Workflow Build
  • Embedded AI Pod
  • All four, with prices

Capabilities

  • Retrieval and context
  • Evaluation and quality gates
  • Agent orchestration
  • Guardrails and escalation
  • Observability, cost and drift
  • Product and platform engineering

The practice

  • Engineering home
  • Delivered work
  • How we work
  • Engineering notes
  • About the practice
  • Questions we get asked
  • Start a build

Reach us

contact@thinkscoopinc.com

Other practices

  • Business Applications
  • Growth
  • Thinkscoop, the parent company

Legal

  • Privacy policy
  • Terms
  • Cookies
Thinkscoop Technologies LLPTeam based in India. Clients across the US, Australia and the UAE.
Engineering/Work/EY (Ernst & Young)

AI Risk & Audit Documentation System for EY

Professional Services12 weeks
72%Report prep time saved
50+Concurrent engagements
<2%Escalation rate
0Hallucination incidents

What this engagement is evidence of

Citation first output in a regulated setting, inside the client's own cloud tenancy, with confidence routing to a named human reviewer and an immutable record behind every claim. This is the evaluation and guardrails problem at its strictest, because the reader is a partner signing their name to it.

The situation

Big 4 audit practices live under unrelenting regulatory pressure. Every engagement demands exhaustive documentation - risk matrices, compliance cross-references, workpapers, and partner-ready summaries - before a single judgment call can be made. At EY, that documentation work was falling on senior auditors who should have been spending their hours on the high-stakes reasoning that clients pay for. The problem wasn't a shortage of talent. It was that talent was buried under assembly work.

What was breaking

  • Senior auditors spending 40+ hours per engagement on manual document assembly across 8 disconnected systems
  • Risk assessment drafts taking 24–36 hours before a partner could begin review - compressing decision windows during busy season
  • No single source of truth: compliance frameworks lived in PDFs, spreadsheets, and two separate legacy databases
  • Existing rule-based tools generated uncited outputs, making AI-assisted drafts unusable for regulated client work
  • Seasonal spikes (year-end audit season) created a 3× workload surge that existing headcount couldn't absorb

Trustability first. Speed second.

Every prior attempt at AI in audit had failed for the same reason: hallucinated outputs that auditors couldn't trust or cite. Our core design principle was citation-first - every claim the system makes must link directly to a source document, regulatory reference, or data record. We spent the first two weeks not building software, but mapping exactly which document types lived where, who was authorised to access what, and what a 'good enough to hand to a partner' draft actually looked like. We then designed a human-in-the-loop architecture where AI handles assembly and cross-referencing, and every human touch is on judgment - not data retrieval.

  • Built evaluation harnesses before building the product - defined what 'correct' looked like with audit experts upfront
  • Chose LangGraph over a simple prompt chain to give each reasoning step an explicit, auditable state graph
  • Operated entirely inside EY's existing Azure tenancy - zero data left EY's perimeter at any point
  • Designed escalation triggers: if confidence on any claim fell below threshold, the agent flagged for human review rather than guessing

A multi-agent audit intelligence system

The system is a LangGraph-based multi-agent pipeline with four specialised agents: a Data Retrieval Agent that queries all 8 source systems via secure API connectors, a Regulatory Mapping Agent that cross-references extracted data against IFRS, SOX, and local GAAP frameworks stored in a structured knowledge base, a Draft Generation Agent that writes sections of the risk assessment with inline citations, and a Review Routing Agent that scores output confidence and routes low-confidence sections directly to a named partner queue. Everything is logged to an immutable audit trail in Azure Blob Storage.

Data connectors

Secure REST connectors to all 8 source systems - ERPs, legacy workpaper tools, and the firm's proprietary client data platform - with field-level access control per engagement team.

Regulatory knowledge base

Structured vector store of IFRS, SOX, and 12 local GAAP frameworks with versioning, so the system always cites the correct year of the standard and flags when a referenced standard has been updated since last engagement.

Citation engine

Every sentence in a generated draft carries a citation ID linking back to a specific source document and page. Reviewers click any sentence to see its evidence chain instantly.

Confidence routing

Any output section scoring below the defined confidence threshold is automatically routed to the relevant human reviewer with the agent's uncertainty reasoning pre-populated - so partners see exactly why the AI wasn't sure.

Audit trail

Every agent decision, API call, and human override is written to an immutable log in Azure Blob Storage. The entire decision history for a client report can be exported as a single compliance record.

What it produced

The numbers only tell part of the story. The bigger shift was cultural: auditors started treating AI output as a first draft they refined, not a risk they managed around.

72% reduction in report preparation time. Zero hallucination incidents. 50+ concurrent engagements handled across 6 countries with full audit trails.

What we would tell the next team

L1

Citation architecture is the product

We thought the hard part would be getting accurate AI outputs. The real challenge was building a citation system trustworthy enough that a senior partner would stake their sign-off on it. Every architectural decision - from the knowledge base schema to the confidence thresholds - was driven by that requirement.

L2

Change management is as important as the build

The first version of the system was technically solid but adoption was slow. Auditors didn't distrust the technology - they distrusted change during the highest-stakes period of their year. We ran structured onboarding sessions, kept human override frictionless, and made the first two months a 'co-pilot mode' where auditors could see AI drafts alongside their manual work. Adoption accelerated sharply once they had direct comparison evidence.

L3

Evaluation harnesses are non-negotiable in compliance

We built a suite of 200+ test cases before shipping to production - covering edge cases in regulatory cross-referencing, ambiguous jurisdiction overlaps, and known failure modes from previous AI attempts at EY. This harness now runs on every model update, giving the engineering team and EY's risk team a shared quality gate.

“This system handles the most time-consuming part of our audit cycle. What used to take two senior staff three days now takes hours - with full traceability. Our partners now spend their time on the work that actually requires their judgment.”

Senior Audit Director, EY

Vitals

  • Client: EY (Ernst & Young)
  • Sector: Professional Services
  • Duration: 12 weeks

Disciplines exercised

  • Guardrails and escalation
  • Evaluation and quality gates
  • Retrieval and context
  • Agent orchestration

Platform and tooling

  • LangGraph
  • Azure OpenAI
  • Azure Blob Storage
  • TypeScript
  • Node.js
  • React
Start a build

Model versions are deliberately not listed. The architecture treats the provider as a configuration decision, and a version printed on a page is out of date within the quarter.

$engineering / other engagements

Five more, and what each one cost to learn.

68%Booking.comA LangGraph reasoning agent with live access to booking APIs, a RAG knowledge base over 500,000+ policy documents, and direct payment system integration - with confidence-based escalation that assembles full context for human agents before routing.10 weeks · Travel & eCommerce78%Global FinTech (Confidential)A multi-step LangGraph reconciliation agent that reasons over discrepancy reports, queries source systems via API, and drafts resolution actions for human review - with a full evaluation harness measuring accuracy and escalation rate weekly.10 weeks · Financial Services4.2minHindustan Unilever LimitedA unified AI knowledge assistant with RAG over 200,000+ internal documents, role-based access control tied to SSO, full audit logging, and citation-grounded answers - operating entirely within HUL's Azure environment.14 weeks · FMCG / Enterprise3×SAMCoA real-time portfolio intelligence platform with live market data feeds, AI risk modelling, and a natural language query interface - so managers get cited answers to risk exposure questions in seconds, not a day later.8 weeks · Financial Services35%PixisA multi-touch attribution engine with AI-assisted causal inference, processing 5M+ events daily across Google, Meta, and TikTok - giving marketing teams a defensible, explainable model for budget decisions.6 weeks · MarTech / AI Marketing

Is your constraint the same as this one?

Send the task, the data it runs on and the systems it has to touch. You get a written read from an engineer within a working day.

Start a build