Energy
Business travel spend analysis
The team uploads exports from its booking and expense tools; the tool derives data coverage, savings levers, a forecast, the carbon footprint and an action plan, with every figure traced back to its source rows. The use case is being piloted.
Context
A large multi-site group wants to manage its travel spend using exports from its booking and expense tools.
The problem
Exports from several tools are heterogeneous, large and hard to consolidate into verifiable savings levers.
What we built
A travel analysis module: reading of several heterogeneous workbooks with a status per file, deduplication, categorisation, analysis by traveller and by route, levers and savings, forecast, carbon footprint, action plan, sourced discussion and exports.
Steps
- 01Upload of booking and expense exports
- 02Reading, checking and consolidation of rows
- 03Calculation of indicators, levers, forecast and carbon
- 04Sourced discussion and exports
Hosting and models
OVHcloud private cloud in France. Qwen3.5-397B via OVHcloud AI Endpoints, a self-hosted 27B Qwen model, and small self-hosted models on a dedicated L40S GPU for vectorisation, reranking and image description, plus OCR.
Services involved
AI in your applications · Agentic platforms
We name a client only with their written agreement. The budgets and detailed results of our engagements remain confidential.