GUIDED TOUR

Seven stages, from a CSV to a deployed model.

The workbench walks through the same seven stages whether you bring a spreadsheet or a production database.

STEP 1

Connect

Register a Postgres or MySQL database, a CSV file or an HTTP JSON endpoint. OSDBstore profiles every column and catalogs the result with lineage.

osdbstore

Tour: Connect, Sources page1400 x 1000 pxDelete this block and drop in an Image or Video widget

osdbstore

Tour: Pipelines, pipeline canvas with a finished run1400 x 1000 pxDelete this block and drop in an Image or Video widget

STEP 2

Raw data moves through staging, core and aggregate layers as durable workflows, with data-quality gates that stop bad loads.

STEP 3

Train a model on a table you own, read its health in plain language, then score new rows. Retrain automatically when the data drifts.

osdbstore

Tour: Models, Health tab with ROC AUC1400 x 1000 pxDelete this block and drop in an Image or Video widget

osdbstore

Tour: Search, hybrid search results1400 x 1000 pxDelete this block and drop in an Image or Video widget

STEP 4

Documents are chunked and embedded as they arrive. Queries fuse dense vector and keyword ranking, and answers cite their sources.

STEP 5

Run a LangGraph agent and read every step it took, what it cost and which prompt version it used.

osdbstore

Tour: Agents, a traced agent run1400 x 1000 pxDelete this block and drop in an Image or Video widget

osdbstore

Tour: Studio, a dashboard Studio built1400 x 1000 pxDelete this block and drop in an Image or Video widget

STEP 6

Describe the dashboard you want. Studio plans charts against your real datasets, models and graph, and grounds every column.

STEP 7

Flip a table from hot Postgres to Iceberg object storage and back. Queries return identical results and models can still train on it.

osdbstore

Tour: Tiers, a table moved to cold storage1400 x 1000 pxDelete this block and drop in an Image or Video widget

The guided tour runs inside the console, on sample data, in a few minutes.