Questions we get asked

A context layer sits between your data and the AI agents that use it, and turns raw data into meaning an agent can act on: what a figure means, where it comes from, and whether it can be trusted. Semantic Scout’s is evidence-backed — it builds that context from how your data is actually made, from mainframe to cloud, and every fact cites the file and line behind it.

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. Where a path depends on what the code decides at run time, the lineage reflects that too, rather than listing everything that might have contributed.

Code repositories, configuration and copybooks, documents and logs — plus common SQL dialects, Python, Spark, dbt and orchestration tools, cloud warehouses and BI tools, and mainframe assets including COBOL programs. If a source matters to you and is not listed, we build the connector.

Yes. Agents query the same lineage and meaning your people do, over MCP and A2A, with the evidence attached — so an agent’s answer can be traced the same way a person’s can.

A platform’s own context sees what runs on that platform, and learns largely from how data is used there. Most estates span several platforms — and, in the large Nordic banks, a mainframe. Semantic Scout builds context across all of it, from the code that produces the data, with evidence on every fact.

A catalog learns what data means from how it is used: query history, dashboards, documentation. Scout derives it from what produces the number — the code and what ships with it — which is why the trail does not stop where the warehouse stops. We are not a catalog replacement; we sync to the one you run.

Yes. Custom adaptors let you integrate niche or in-house systems, and the platform is built for interoperability through open standards and APIs.

Self-managed, dedicated SaaS, private cloud (VPC), or fully on-premise. Choose what fits your security and data-residency requirements.

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.

Yes. Deploy in-region and keep all metadata and logs within your chosen geography, including full EU residency.

Every suggestion is reviewable. Stewards accept, edit, or roll back AI-generated descriptions and lineage, and version history keeps the trail for audits.

Against a benchmark of graded cases, including cases withheld from development. A wrong attribution counts as a failure rather than a near miss, because it is the kind of error a reader cannot spot without going back to the code.

Quickly, and without a long integration project first. Point Scout at a representative repository or pipeline and end-to-end lineage starts appearing from the first run, then deepens as coverage widens. Pilots reach broad coverage well inside the pilot window.

Week 1 connects key systems, and lineage and metadata begin filling in from the first run. Weeks 2–3 expand coverage, add steward review, and prove value against the goals set at the start.

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.

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.