AI for procurement and ESG, with evidence behind every number
OceanLab builds AI into spend and sustainability data: cleaning supplier records, classifying spend and building carbon inventories. The AI sorts and suggests; analysts review and sign off. Every example below is a product we built.
OceanLab product builds
AI products we designed and built in this industry. Each one is a full case study with screens, scope and the rules it was built for.
Soroban - Group Spend Analytics Across Four ERPs
Designed and built a clickable spend analytics platform for an Osaka trading and manufacturing group with companies in Japan, Thailand and Vietnam: messy vendor records from four ledgers folded into supplier families, every line classified to UNSPSC and converted to yen, and one spend cube to slice it by category, supplier, entity and period.
Kolmila - GHG Inventory and Sustainability Reporting Platform with Evidence Behind Every Number
Designed and built a clickable sustainability data platform for a Swedish manufacturer of hydraulic cylinders, steel fabrications and castings: site data collection with evidence, two-step review, a versioned emission factor library and a Scope 1, 2 and 3 inventory under the GHG Protocol, built to feed an ESRS sustainability statement and limited assurance.
Where AI earns its place
Each use case names the builds that did it.
Supplier families
Messy vendor records from four ERPs folded into supplier families, so spend adds up per real supplier.
Spend classification
Every spend line classified to a standard category code and converted to one currency, in one spend cube to slice.
Carbon inventory
Site data collected with evidence, a two-step review and a versioned emission factor library behind a Scope 1, 2 and 3 inventory.
What to plan for
The rules that shape AI in this industry. General information, not legal advice: check with your own counsel.
Evidence behind every number
Two people check
Version the factors
Reporting rules
Frameworks our AI builds here cite
From one workflow to production
- 01
Pick the workflow
We start from one workflow your team wants off its plate and agree what a working result looks like.
- 02
Clickable AI prototype
Your team tries the flow on a clickable prototype before any production code is written.
- 03
Production build
We build the production version, with the approval steps and records your industry needs.
- 04
Launch and improve
It goes live in your team's hands, and we tune it as real work runs through it.
Priced either way, whichever suits the work: outcome-based, paid per milestone, or hourly at $30-50 depending on role and seniority. More on AI automation →
Questions teams ask
What can AI do for procurement and ESG teams?
Fold messy supplier records into real suppliers, classify every spend line, and build a carbon inventory with evidence and a second review behind every number. Each of these is a product OceanLab built.
Can AI numbers go into an audited report?
Only with the evidence and review behind them. In our ESG build every figure has its evidence, a two-step review and the factor version that produced it.
How is it priced?
Either way, whichever suits the work: outcome-based, where you pay per milestone, or hourly at $30-50 depending on role and seniority.
Keep exploring
Are you an AI lab looking for human training or evaluation data? That is a separate offer, OceanLab Labs.
