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.