Studio · TAPECRACK
Operate the governed pipeline with full backend control.
This studio uses live backend routes for datasets, workstreams, user identity, and execution outputs. Every stage is visible and auditable.
Run Order
Confirm user profile and active dataset
Analyze schema and profile shape
Preview recipe and inspect warnings
Approve + run transformation
Download CSV or export table
UploadCSV · TXT · XLSX
Drop a file or browse
CSV, TXT, TSV, or Excel
Guided Templates0 recommendations
Keep UI simple: detect the best stream from your real file, apply, then run guided preview/approval.
No recommendations yet
Upload/select a dataset and click detect to create agentic template options.
Saved Workstreams0 streams
Save modular crack streams per user, recognize known templates on new datasets, and rerun.
Data contextlive schema
Null revenue—
Distinct dates—
Distinct regions—
ColumnTypeNulls
Loading schema…——
Sample rowstool: sample_rows
Recipe buildertool: propose_recipe
—
No recipe yet
waitingRun a preview to generate steps.
Program intent
Validationtool: validate_recipe
No validation warnings yet.
Preview & approvaltool: preview_recipe
MetricBeforeAfter
Rows——
Row delta0%—
No approval required
ExportSQL Server
Dataset: none
Tool call log0 events
Waiting for tool calls…
Storyboard the program lifecycle
Guardrails are enforced at every frame, every run.
Frame 01
Ingest + detect drift
Schema fingerprints block mismatched inputs.
get_schema · profile_columnsFrame 02
Draft recipe
LLM proposes a deterministic program.
propose_recipeFrame 03
Validate + preview
Row loss and schema changes are flagged.
validate_recipe · preview_recipeFrame 04
Approve + run
Runs execute in Temporal with lineage.
request_approval · run_recipe