FAQ
Questions we get asked
Direct answers, including the ones where the answer is “not yet”. If something here is missing, ask us and we will add it.
The product
What is included in Semantic Scout Enterprise?
A catalog, a data-quality engine, and our AI metadata harvester — delivered together, so discovery, tests, and lineage arrive in one place rather than as three projects.
What do you mean by “full-fidelity, column-level lineage”?
We trace data flows from source to report at table and column level across jobs, SQL, and transformations — so you can see exactly which fields feed a metric, a dashboard, or a model, and what changed between two points in time.
How does the AI metadata harvester actually work?
It parses code, SQL, and pipeline configuration to generate metadata and column-level lineage, then summarises technical flows into plain language. Stewards review and approve the result rather than authoring it from scratch.
Which technologies and languages do you support?
Common SQL dialects, Python and Spark, dbt, orchestration tools such as Airflow, major cloud warehouses and lakes, BI tools, and mainframe assets including COBOL programs. Ask us about your stack if it is not listed.
Working with what you already have
Can we use Semantic Scout with our existing catalog or quality tool?
Yes. Run the plug-in alongside your current stack, or choose Semantic Scout Enterprise, which ships catalog, data quality, and the harvester pre-wired.
What if we already have parts of this?
Keep them. Semantic Scout runs as a plug-in that enriches an existing catalog or quality platform with deeper lineage and AI-assisted context.
Can we build custom adaptors?
Yes. Custom adaptors let you integrate niche or in-house systems, and the platform is built for interoperability through open standards and APIs.
Deployment and security
Where can we deploy Semantic Scout?
Self-managed, dedicated SaaS, private cloud (VPC), or fully on-premise. Choose what fits your security and data-residency requirements.
Do you use our business data to generate metadata?
No. No real business data is used in the process. Semantic Scout works from configuration, logs, and code — this is an architectural property, not a policy promise.
Do we need to modify our pipelines or workflows?
No. We read configuration, logs, and repositories through APIs. Runtime overhead is minimal and can be isolated from production workloads.
Can you meet data-residency requirements?
Yes. Deploy in-region and keep all metadata and logs within your chosen geography, including full EU residency.
Trust and accuracy
How accurate is the AI, and how do we approve what it generates?
Every suggestion is reviewable. Stewards accept, edit, or roll back AI-generated descriptions and lineage, and version history keeps the trail for audits.
Can this help with audits and regulation?
Yes. Verifiable lineage, change history, and ownership context shorten audit preparation and reduce compliance risk under BCBS 239, DORA, GDPR, and the EU AI Act.
Getting started
How fast can we see results?
Most teams see end-to-end lineage within hours on a representative repository or pipeline. Pilots typically reach broad coverage in days rather than months.
What does a typical pilot look like?
Week 1 connects key systems, and lineage and metadata begin filling in within hours. Weeks 2–3 expand coverage, add steward review, and prove value against the goals set at the start.
Is there a free trial?
Not yet. Semantic Scout deploys into your environment, so the honest entry point is a pilot on your own estate rather than a sandbox that proves nothing about it.
How is Semantic Scout priced?
Pricing is quoted per organisation and built from three inputs: packaging (plug-in or the Enterprise bundle), deployment model, and scale — asset count, connectors, and users. Premium scanners and AI summaries are optional add-ons.
See it on your own estate
A 30-minute demo shows the product. A pilot shows your own lineage, built from your own repositories.