Run document extractions using AI and review the results
- Infer the fields
- Extraction works in three steps: infer (the AI reads the document and infers which columns matter), correct (you review and edit anything wrong in Data Studio), and remember (every correction becomes a reusable pattern).
- Correct the values
- Select one or more files and press Ctrl+Enter, or use the Extract button. Results appear as an editable table. For whole batches, select files and use Add to job to build a named Extraction job (Hobby and above), then press Run job. Hobby permits 25 files per job, 10 active jobs, and unlimited runs. Each document is extracted on its own into a View Extractions folder named after the job.
How the infer → correct → remember loop works
How does Dynamite Docs extract fields and line items without a supplier template?
Dynamite Docs proposes fields and table rows from each document. You compare them with the source, correct mistakes, and save confirmed corrections as patterns for similar layouts.
Extraction works in three steps: infer (the AI reads the document and infers which columns matter), correct (you review and edit anything wrong in Data Studio), and remember (every correction becomes a reusable pattern).
Select one or more files and press Ctrl+Enter, or use the Extract button. Results appear as an editable table. For whole batches, select files and use Add to job to build a named Extraction job (Hobby and above), then press Run job. Hobby permits 25 files per job, 10 active jobs, and unlimited runs. Each document is extracted on its own into a View Extractions folder named after the job.
Each page successfully processed with a hosted model costs 1 page-equivalent (PE). Failed extractions cost 0 PE.
BYOK is available on every plan. BYOK on Free and Hobby uses the monthly PE allowance; BYOK on Pro and Ultra is unlimited. A run counts as BYOK only when it uses your own provider API key.
Each plan caps hosted pages per document. BYOK has no per-document tier cap, though Free and Hobby BYOK still uses monthly PE and provider and file-size limits still apply.
Each successfully processed hosted or local no-AI page costs 1 page-equivalent. Failed pages cost 0, and own-key processing follows the allowance rules of the active plan.
Related workflows and guides
- Inspect and edit extracted table values side-by-side with source scans in the Data Studio review guide.
- Connect external models for unlimited processing on Pro and Ultra using our AI providers and BYOK guide.
- Convert multi-page PDF tables directly into structured workbooks with our PDF to Excel converter.
Open the document extraction app, browse document input and export integrations, or compare PE, storage, and API limits.
- 01Infer the fields
- 02Correct the values
- 03Remember the pattern
- Infer the fields
- Extraction works in three steps: infer (the AI reads the document and infers which columns matter), correct (you review and edit anything wrong in Data Studio), and remember (every correction becomes a reusable pattern).
- Correct the values
- Select one or more files and press Ctrl+Enter, or use the Extract button. Results appear as an editable table. For whole batches, select files and use Add to job to build a named Extraction job (Hobby and above), then press Run job. Hobby permits 25 files per job, 10 active jobs, and unlimited runs. Each document is extracted on its own into a View Extractions folder named after the job.
- Remember the pattern
- Each page successfully processed with a hosted model costs 1 page-equivalent (PE). Failed extractions cost 0 PE.