Legalstart
Ten data sources pulled into one warehouse, and documents arriving by email handled without anyone touching them.
Context
Legalstart handles large volumes of documents for thousands of customers. Business data sat across a dozen tools with nowhere to cross-reference it. At the same time, part of the work stayed manual: pulling documents out of email, identifying them, filing them. That kind of task never shows up in a P&L, but it takes up teams every single day.
The problem
- Business data spread across a dozen separate tools.
- Document collection done by hand, at a real cost.
- A support workload made heavier by that handling.
- No shared basis for making decisions from numbers.
Solution
- Connected 10 sources into BigQuery with Airbyte.
- Orchestrated the pipelines with Airflow.
- Built Metabase dashboards for the business teams.
- Built a document ingestion pipeline in n8n that picks up files arriving by email.
- Added AI-assisted OCR to read, extract and route each document into the data lake.
Our approach
Inventory
Listing the sources, what each one actually holds, and which decisions are waiting on reliable numbers.
Foundation
Connecting the 10 sources into BigQuery with Airbyte, orchestrated by Airflow.
Reporting
Metabase dashboards built with the teams who would use them.
Document automation
n8n pipeline and AI-assisted OCR for documents arriving by email.
Results
Business data now lives in one place and teams reach it themselves. Documents arriving by email are read, identified and filed automatically, which is 10,000 € a month no longer spent on manual handling.
Start with Compass
In 2 weeks, you know what your data can actually do for you. A structured audit, a prioritised roadmap, before you spend anything else.
A similar project?
We take 30 minutes to understand what you need. You leave with a clear opinion, even if we end up not working together.
Let’s work together
Share your need, we will get back with you quickly.