Projects
In Progress2024-Q3

AI-Powered Smart Sourcing & Contract Analysis

LLM-driven system that ingests procurement contracts, flags risk clauses, benchmarks supplier terms, and surfaces anomalous spend patterns — turning procurement from reactive to predictive.

20 min

Target Review Time

2,000+

Contracts/Year

60%

Risk Detection Uplift

LLMContract AIProcurementAzure
Azure OpenAIAzure Document IntelligencePythonLangChainPostgreSQLPower BI

Overview

Procurement teams at large energy companies manage thousands of supplier contracts with significant financial and operational risk buried in dense legal language. This system uses large language models to read, extract, and reason over contract text — dramatically reducing the time analysts spend on contract review.

Problem Statement

Shell India processes 2,000+ procurement contracts annually. Key risk clauses, non-standard terms, and pricing anomalies are frequently missed in manual reviews. The goal: reduce contract review time from 4 hours to 20 minutes per document, while increasing risk detection coverage.

Solution Architecture

A multi-stage pipeline:

  1. Ingestion: PDF contracts parsed via Azure Document Intelligence
  2. Extraction: LLM extracts structured fields — parties, values, terms, obligations, penalty clauses
  3. Risk Scoring: Clause-level risk scoring against Shell's contract standards library
  4. Benchmarking: Supplier terms compared against historical contract database
  5. Alerting: High-risk contracts flagged for human review with highlighted clauses

Current Status

In active development. Pilot running with the indirect procurement category.