FlatClaw, Private AI Platform
All use case spotlights
Estimating & QuotingAnalytics & ReportingLogistics

European logistics group

≈ $2B revenue · 6,000+ employees · 50+ countries

Quote control tower over forwarding systems

Quotes that track fuel prices, routing and political risk across the group's forwarding systems, assembled by agents over the company's own data lake and handed to the desk with the reasoning attached.

Organization
European freight forwarding and logistics group
Inputs
Fuel prices, routing, political risk, forwarding systems
Runs on
The group's cloud tenancy over its data lake
Scope
A quote control tower for three internal consumers
The situation

Where they started.

Quotes depend on inputs that change daily, fuel above all, and on data scattered across forwarding systems and a partner's API. Finance, operations and an innovation team each wanted a different view of the same facts, and a data-lake program was already underway that the agent could sit on top of rather than replace.

What FlatClaw does

What was built.

  • FlatClaw as a consumer of the group's data lake: a control tower that reads the forwarding systems and the partner API through governed connectors.
  • Agents assemble quotes that track fuel, routing and risk, and hand them to the desk with the reasoning attached rather than a number alone.
  • Three front doors onto one brain: finance asks about margin, operations about exceptions, the innovation team about what to build next.
  • Cited answers grounded in the lake, so a quote can be defended a month later.
Results

What changed.

  • Margin analysis that took a week becomes a conversation.
  • Quotes carry their assumptions, so they can be challenged and corrected.
  • The data-lake investment gains an interface people actually use.
  • One governed system instead of three departmental tools.
Why private

Pricing logic and customer contracts are the business. They stay in the group's own tenancy, and the model never sees them from outside it.

Runs on

The group's cloud tenancy

The stack

Components involved.

FlatClaw PortalAgent harness (Pi core)Forwarding-system and partner-API connectorsData-lake retrievalPrivate inference on a dedicated GPU
Your workflow

Have one like it?

Every spotlight started as a conversation about a process nobody liked doing, under a data-locality constraint.