Energy

Comparing supplier contracts against a clause library

Buyers import their clause library, upload contracts from several suppliers and get a matrix comparing each contract clause by clause, with an editable executive summary and Excel and Word export. The use case is being piloted with the procurement department.

Talk to an engineer

Illustrative mock-up: the names, values and documents shown are fictitious.

Context

The procurement department of a large energy group negotiates supply contracts for heavy equipment with several manufacturers.

The problem

Manually comparing contracts running to several hundred thousand characters against an internal library of 77 clauses is slow and prone to omissions.

What we built

A contract analysis module: import of the clause library (77 clauses, 14 categories), upload of several PDF or Word contracts, category-by-category analysis with streaming, comparison matrix, discussion of the matrix with sourced answers, server-side Excel export and a Word report.

Steps

01Import of the clause library
02Upload of one or more supplier contracts
03Category-by-category analysis (a few minutes per contract)
04Matrix, editable executive summary, exports

Hosting and models

OVHcloud private cloud in France (managed Kubernetes, PostgreSQL, S3 storage, Gravelines data centre). Main model Qwen3.5-397B served by OVHcloud AI Endpoints. The platform gateway also declares Claude models via AWS Bedrock (EU and US regions).

Services involved

AI in your applications · Forward Deployed Engineers

We name a client only with their written agreement. The budgets and detailed results of our engagements remain confidential.