/platform/data-tables) is the workspace for comparable metric extraction across a watchlist. You write one prompt describing the metrics you want, and the platform runs it against every entity, normalising the results into a sortable, filterable matrix.
When to use Data Tables vs other surfaces
| You want… | Use |
|---|---|
| An interactive, prose write-up for one obligor (tear sheet, memo section), with follow-up questions | Deep Dive. A multi-turn session, one obligor. |
| A comparable matrix of metrics across every obligor (e.g. revenue, expenses, DSCR by fiscal year) | Data Tables. One matrix, sortable rows × columns. |
The workspace
There’s one workspace per prompt. The sidebar lists every prompt you’ve authored. The main area has three sections:- Prompt panel: the prompt body. Editable inline.
-
Matrix: rows (typically entities) × columns (typically fiscal years or another comparable dimension). Every value is traceable: click a cell for its reference, source document, pages, and notes, or click an entity name to open a panel with two tabs:
- Documents: the source filings used for that entity.
- Notes: caveats, ambiguities, methodology, and restatements flagged during extraction, with links to the cited pages.
- Views and filters: switch between the three views and filter by entity, status, value type, period, and audit status.
Preview, then apply
Data Tables has a built-in two-step extraction flow:Preview on a few CUSIPs
Click Preview. The platform runs the prompt against a handful of sample CUSIPs from the watchlist so you can check it extracts what you expect, without touching the full list.
Tune the prompt
Adjust the prompt body until the preview cells look right. Previews are cheap and only cover the sample CUSIPs.
Options
Alongside the prompt, a few choices control what the extraction runs over:| Field | Description |
|---|---|
| Scope | Obligor-level produces one row per obligor in the watchlist, pooling every CUSIP under it. CUSIP-level produces one row per CUSIP, useful when bond-level detail matters (different liens, etc.). |
| Years Back | How many years of disclosure history to include (1, 2, 3, or 5). |
| Sample CUSIPs (preview only) | Which CUSIPs to run the preview against. Pick 1–3 representative names from the watchlist to check the prompt before applying to the full list. |
Views
The same extracted cells can be sliced three ways. Switch between them from the toolbar:| View | Rows × Columns | Shows |
|---|---|---|
| Snapshot | metrics × entities | Every entity side by side on each metric, for a single period. The default, best for ranking and comparison. |
| Trend by Entity | metrics × periods | One entity’s metrics over time. Pick the entity; columns become the periods (e.g. fiscal years) the prompt produced. |
| Trend by Row | entities × periods | One metric across every entity over time. Pick the metric; see how all entities move on it. |
Tips
- Be explicit about units and time bases. “Revenue in USD millions” and “Fiscal year ending June 30” beat “operating revenue” for sortable comparability.
- Pin sector idiosyncrasies in the prompt. For example, exclude entrance fees from DSCR for charter schools, or specify GASB vs FASB.
- Reuse existing prompts with
@. While writing the prompt, type @ to search your prompt templates and embed a reference to one, so you can build on prompts you’ve already tuned instead of rewriting them.
See also
- Prompt Templates → Writing better prompts: how to write prompts that extract clean, comparable values.
- Watchlists: the groups of entities a Data Table runs across.
- Surveillance: the event feed for new disclosures on those same watchlists.