A pattern engine your agent can call.
Finder searches tables for drivers, anomalies, and segment interactions before the report gets written. Use it today in the Unsupervised CLI or the enterprise Cloud platform.
Inputs
One table, local files, dbt context, warehouse exports, or notes your agent can read.
Run
Statistical sweeps rank drivers, anomalies, and segment interactions worth investigating.
Outputs
Structured findings, caveats, open questions, and artifacts the agent can turn into a report.
It does the search work.
Agents are good at queries and summaries. Finder handles the combinatorial part: testing plausible cuts, ranking useful ones, and returning evidence the agent can use.
Driver discovery
Identify which dimensions, measures, and changes explain the movement in a KPI.
Segment interactions
Search for combinations that disappear in univariate summaries and dashboard rollups.
Anomaly exploration
Flag changes worth investigating and preserve the caveats your agent needs for follow-up work.
Report-ready evidence
Return scale, effect size, context, open questions, and source-backed findings.
Available today in CLI and Cloud.
Use Finder in the CLI
Install the Unsupervised CLI to launch Claude Code with Finder, DeepWork, and data-analysis defaults.
Use Finder in Cloud
Run Finder inside the enterprise platform for governed workflows, shared KPI definitions, writeback, auditability, and controls.
Start locally. Use Cloud when teams need governance.
The CLI gives Claude Code access to Finder, DeepWork, and analytics guidance.
Cloud gives teams managed runs, governed workflows, writeback, and enterprise controls.
Enterprise deployment support is available when data cannot leave your environment.
Access Finder
Use Finder today through the Unsupervised CLI, or through the enterprise Cloud platform for governed team use.
Example output
See how a full Medicaid spending analysis turns raw rows into patterns and open questions.
Proof
Customer outcomes, market research, and technical writing behind the direction.