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/Hindustan Unilever Limited

AI Knowledge Assistant for HUL's 15,000-Person Supply Chain Organisation

FMCG / Enterprise14 weeks
4.2minAverage query resolution
15,000+Users across 8 countries
200k+Documents indexed
100%Document access compliance

What this engagement is evidence of

Retrieval across the systems a large organisation actually keeps its knowledge in, with access control following the document into the index. At this scale the engineering risk is permissions and freshness rather than reasoning.

The situation

Hindustan Unilever Limited operates one of the most complex supply chains in Asia - thousands of SKUs, hundreds of suppliers, manufacturing sites across multiple countries, and a regulatory surface that spans 8 different jurisdictions. Within that complexity, institutional knowledge is both an organisation's greatest asset and its most fragile one. At HUL, a question about a supplier specification, a compliance document, or a process standard could take 2+ days to answer - not because the answer didn't exist, but because it was buried somewhere in Confluence, SharePoint, a regional SharePoint instance, or a legacy proprietary database that only two people knew how to search. The cost wasn't just the 2-day wait. It was every decision made without the right information.

What was breaking

  • 2+ days average to locate a compliance document, supplier specification, or process standard - waiting on email chains across departments
  • Knowledge siloed by region and seniority: India teams couldn't access Southeast Asia process docs and vice versa, even when the content was relevant to both
  • 12 separate internal systems with different search interfaces, login requirements, and document formats - making unified search impossible
  • No version awareness: teams regularly acted on outdated specification documents because the latest version lived in a different system they didn't know to check
  • Compliance team spent 20+ hours per week manually fulfilling internal document requests that employees couldn't locate themselves

Access control first. Search quality second.

The obvious starting point was to build a search engine. We argued the starting point had to be access control architecture. A knowledge assistant that surfaces documents a user isn't authorised to see isn't a useful tool - it's a compliance incident waiting to happen. We spent the first three weeks mapping HUL's existing permission structures across all 12 systems, designing a unified RBAC model that could express the combined access rules from Confluence, SharePoint, and the proprietary databases in a single enforcement layer. Only once that architecture was validated by HUL's security team did we begin indexing documents and building the retrieval layer.

  • Access control architecture validated by HUL's security team before any document was indexed - no document surfaced to a user who wasn't authorised in the source system
  • Citation-first retrieval: every answer includes the source document, section, and effective date - so users can verify and access the original
  • Freshness monitoring: automated pipelines detect when source documents are updated and trigger re-indexing within 24 hours - preventing stale retrieval
  • Human escalation path: when no sufficiently confident document match exists, the system routes to the appropriate subject matter expert with context pre-assembled

A unified knowledge layer across 12 systems for 15,000 users

The system is a RAG-based knowledge assistant running entirely within HUL's Azure tenancy. A custom indexing pipeline crawls Confluence, SharePoint (global and regional instances), and the proprietary procurement database on a nightly schedule, chunking documents into semantically meaningful sections and storing embeddings in Pinecone with rich metadata (department, region, document type, effective date, access tier). The retrieval layer enforces per-user access control at query time - every retrieval request is filtered against the user's Azure AD groups before any document chunk is returned. The response generation layer uses a hosted model with a strict citation prompt: every sentence in a response must reference a specific document chunk, and the answer includes clickable links back to the source document in its original system.

Multi-system indexing pipeline

Custom connectors for Confluence Cloud API, SharePoint REST API (three tenancies), and a proprietary procurement database via direct DB read replica. Documents are chunked by semantic section, enriched with metadata (region, department, document type, effective date, access tier), and embedded with text-embedding-3-large. Nightly freshness checks flag modified documents for re-indexing.

Role-based access enforcement

Every Pinecone query is filtered at retrieval time against the querying user's Azure AD group memberships, mapped to HUL's document access tier structure. A user in 'India Sourcing' cannot retrieve documents tagged 'SEA Compliance Restricted' regardless of search intent - the document is invisible at query time.

Citation-grounded response generation

The model generates answers under a strict prompt contract: every factual claim must cite a specific retrieved chunk by ID. The response renders inline citations with clickable deep links back to the source document in its original system - Confluence, SharePoint, or the procurement portal.

Freshness and version awareness

When a source document is updated, the old version's chunks are deprecated in Pinecone and new chunks are indexed with an incremented version tag. If a user asks a question and the most relevant document was updated in the last 7 days, the response includes a freshness notice - preventing decisions based on recently superseded content.

Full audit trail

Every query, every document retrieved, every response generated, and every user access event is logged to Azure Monitor with the user's identity, their AD group memberships at query time, and the document access tier of each retrieved chunk. HUL's compliance team has a real-time dashboard of all knowledge assistant activity across all 8 countries.

What it produced

The 4.2-minute average resolution time is the headline. The operational shift underneath it - from knowledge as a bottleneck to knowledge as an accelerator - is the real outcome.

Query resolution time dropped from 2 days to 4.2 minutes. 15,000+ users across 8 countries. Zero data security incidents. Document access compliance at 100%.

What we would tell the next team

L1

Permission mapping is the longest part of the project

We scoped permission mapping as two weeks of work. It took five. HUL's access structures had evolved organically over a decade - different regions had different SharePoint permission models, Confluence had space-level and page-level restrictions in conflict with each other, and the procurement database had a bespoke access model that had never been formally documented. Mapping this comprehensively before indexing any content added time to the project but prevented what would have been a serious compliance incident if we'd shipped fast and corrected later.

L2

Freshness is a first-class feature, not a maintenance task

In the first month after launch, two users received responses citing documents that had been updated since the last index run. Neither was a compliance issue, but both eroded trust. We moved freshness monitoring from a nightly batch job to an event-driven pipeline that detects document edits via webhook (Confluence) and change notification (SharePoint) and re-indexes within 2 hours. The lesson: in regulated environments, knowledge freshness is as important as knowledge accuracy.

L3

Adoption requires executive sponsorship at the team level, not just the project level

Top-down endorsement from the digital transformation programme secured the budget but didn't drive adoption. What drove adoption was team leads in each region actively using the tool in team meetings - demonstrating that 'ask the assistant first' was a behaviour change they personally endorsed. We ran four regional launch sessions with team lead demonstrations, and adoption in regions where a team lead participated was 3× higher at 30 days than regions where we only sent onboarding emails.

“Before this, a compliance question could take two days to answer across three email chains. Now my team gets the answer with source citations in under five minutes. The access control architecture gave our security team full confidence from day one.”

VP Supply Chain Technology, Hindustan Unilever Limited

Vitals

  • Client: Hindustan Unilever Limited
  • Sector: FMCG / Enterprise
  • Duration: 14 weeks

Disciplines exercised

  • Retrieval and context
  • Product and platform engineering
  • Observability, cost and drift

Platform and tooling

  • Pinecone
  • Azure OpenAI
  • SharePoint API
  • Confluence API
  • Node.js
  • React
  • Azure AD
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.

72%EY (Ernst & Young)A multi-agent AI system operating entirely within EY's Azure environment that ingests audit data, cross-references regulatory frameworks, and generates source-cited draft reports for human partner review.12 weeks · Professional Services68%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 Services3×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