> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.cloudraker.com/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cloudraker.com/_mcp/server. # Extract data from documents A **Document understanding** action performs structured extraction. It reads each source document and pulls out structured fields. Turn on **grounding** in the action's [configuration](/workspace/actions/overview#the-output-choice) to get a **source citation** with every field. A citation links to the exact page and text, or to the point in an audio transcript. You can trace every value back to its source. Grounding is **off by default**. Enable it on the saved action. When grounding is on, every filled field carries at least one citation or is marked **not found**. A not-found field stays empty. The system does not guess a value. In the action's [configuration](/workspace/actions/overview#the-output-choice), set whether the extraction binds to a [record type](/workspace/data/record-types) ("Data object") or stays as **Schema only**. To launch a run, see [Run an action](/workspace/actions/run-an-action). ## The results grid When an extraction run finishes, the run page shows a **"Results"** grid. The grid has one row per extracted result. The output fields are columns, and a **"Source"** column is frozen on the left. The header summarizes the run, for example **"`{n}` extracted results"** or **"`{n}` extracted results · `{n}` failed."** Each row carries a status badge: | Badge | Meaning | | ------------- | ------------------------------------------ | | **Extracted** | A fresh result, not yet reviewed. | | **Edited** | You changed a value on this result. | | **Failed** | Extraction failed for this document. | | **Imported** | You added this result to Data as a record. | Cells show a **confidence** score. On grounded runs, cells also show a citation-count chip. The toolbar above the grid has these controls: * **"Export CSV"** — download every result. * **"Approve all clean (`{n}`)"** — approves the results that still need review and have no warnings. * **"Approve selected (`{n}`)"** — select rows first, then approve only those. * **"Retry failed (`{n}`)"** — re-run the documents that failed. * **"Clear"** — clear the current selection. An extraction run's Results grid with a Source column, confidence check marks, citation chips, and 'Extracted' status badges ## The review workspace Click a row to open the full-screen **review workspace**. The **source document sits on the left** with the selected citation shown in context. The citation appears as a highlighted bounding box on the PDF page, or as the audio transcript at the cited moment. The **fields sit on the right**. Each field lists its citations (**"Page `{n}`"**, **"Transcript"**, or **"Source"**), a confidence score, and any warnings. A field shows a **not found** marker when the value is not in the document. To correct a value, edit it inline and click **"Save changes."** An edit removes the value's evidence: **"Saving replaces the extracted value and removes its source citation."** Edit a value only after you verify it against the source. Every run has an editable window. After the window closes, the grid shows **"Editing is closed for this run. Results stay available."** You can still read and export results. You cannot change them. When a result is correct, click **"Approve & import this result"** in the review workspace. You can also approve in bulk from the grid. The extraction review workspace with the source invoice PDF and a highlighted total on the left, and the extracted fields with their page citations on the right ## Importing into Data When you approve results, they become [records](/workspace/data/records) in the space's **Data** tab. An import banner (**"Add to data"**) guides you through the import. It previews the results and offers **"Add `{n}` results to data"**. A **"View in data"** link appears after the import. If the run was not bound to a record type ("Schema only"), a **"Record type"** picker appears first. Choose the type to import into. The import ignores extracted fields that are not part of that record type. ## Reviewing inside a playbook The AI assistant can run an extraction as a step in a [playbook](/workspace/playbooks/overview). The same review then occurs through a post-action **"Output review"** card on the playbook run. A **"Review"** button opens the extraction review surface full-screen. Saves there only save your table edits. When you are done, click **"Approve & resume agent"**. Approval adds the extracted records to Data with every field marked approved. The agent then continues. See [Approvals and steering](/workspace/playbooks/approvals-and-steering). ## Where to go next #### [Records](/data/records) Work with the records your extractions produce. #### [Record types](/data/record-types) Shape the record type an extraction binds to. #### [Run an action](/actions/run-an-action) Launch an extraction over a space's files. #### [Approvals and steering](/playbooks/approvals-and-steering) Review extractions the AI assistant runs inside a playbook.