Pulse AI

App · 14 actions

Read documents with Pulse AI: turn PDFs, scans, photos, spreadsheets and Office files into text, pull out named fields and tables, split long documents by topic, sort documents by kind, and fill or clear PDF forms.

Actions

ActionWhat it does
Cancel jobStop a Pulse job that is still waiting or running.
Classify documentTell which of the kinds of document you list a file is, from its first pages, for example to send invoices and contracts down different paths.
Clear formErase what was written or ticked on a PDF form, keeping the printed blank form, and save it.
Extract documentRead a document (PDF, scan, photo, spreadsheet, Word or PowerPoint file) and return its text as Markdown, tables included.
Extract fieldsPull named fields (an invoice number, a total, a name) out of a document 'Extract document' has read, with where each was found and how sure Pulse is.
Extract fields from a sectionPull named fields out of only the pages 'Split document' found for one topic.
Extract tablesRebuild the tables of a read document, keeping merged cells and headers that span columns.
Fill formFill in a PDF form from plain-language instructions, on real form fields or on a flat scan, and save the filled PDF.
Get jobRead a Pulse job's status, and what it produced once it has finished.
Get usageRead your plan's credits used and left this billing period, and how many documents, pages and credits were used between two dates (the last 30 days by default).
Read chartsTurn the line, bar, pie and scatter charts of a read document back into their numbers.
Read form fieldsFind the fields of a PDF form, filled in or blank, scanned or not, with what each one holds and which boxes are ticked.
Split documentFind which pages of a read document hold each topic you name, such as the financial statements of an annual report.
Start document extractionStart reading a document and go on at once, without waiting.

Cancel job

Stop a Pulse job that is still waiting or running. Pages read before it stops still count. A job that has already ended is left as it is.

Inputs

Job IDjob_idtextRequired
The job_id from 'Start document extraction' or any other step.

Outputs

canceledtrue/false
False when the job had already ended
job_idtext
The job's id
messagetext
Pulse's answer
Example output
{
  "canceled": true,
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "message": "Job cancelled successfully"
}

Classify document

Tell which of the kinds of document you list a file is, from its first pages, for example to send invoices and contracts down different paths. Always picks one, so include a catch-all. Uses 0.5 credits a page.

Inputs

FilefiletextRequired
The document: upload it, pick a file from an earlier step, or give a link Pulse can download. PDFs, images (JPG, PNG, TIFF and more), Word, PowerPoint, Excel, CSV and HTML files work. Uploads can be up to 100 MB.
Kinds of documentcategoriesobjectRequired
Each kind's name with what it looks like, for example {"invoice": "A bill asking for payment", "other": "Anything that is not an invoice"}.
Pagespagestext
The pages to look at, such as 1-3. Pulse's default is the first 5.

Outputs

classificationtext
The kind of document it is: one of your names
credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
job_idtext
The Pulse job that did the work
page_rangetext
The pages that were looked at
Example output
{
  "classification": "invoice",
  "credits_used": 1.0,
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "page_range": "1-2"
}

Clear form

Erase what was written or ticked on a PDF form, keeping the printed blank form, and save it. Must be turned on for your organization by Pulse. Uses 3 credits a page.

Inputs

PDF formfiletextRequired
The PDF form: upload it, pick a file from an earlier step, or give a link Pulse can download.
What to clearinstructionstext
Only clear these fields. Leave empty to clear them all.
Pagespagestext
Only these pages, such as 1-3,5. Leave empty for the whole document.

Outputs

content_typetext
The saved file's type (application/pdf)
credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
document_reftext
The saved PDF, for a later step to attach
fields_clearednumber
How many fields were emptied
filenametext
The saved PDF's name
form_idtext
The cleared form's id in Pulse
job_idtext
The Pulse job that did the work
page_countnumber
How many pages the PDF has
size_bytesnumber
The saved PDF's size in bytes
urltext
Where to download the saved PDF in Lodol
Example output
{
  "content_type": "application/pdf",
  "credits_used": 3.0,
  "document_ref": "doc_0123456789abcdef0123456789abcdef",
  "fields_cleared": 7,
  "filename": "pulse-form-f1b2a3d4.pdf",
  "form_id": "f1b2a3d4-0000-4000-8000-00000000000a",
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "page_count": 1,
  "size_bytes": 140815,
  "url": "/actions/core/serve-document/doc_0123456789abcdef0123456789abcdef"
}

Extract document

Read a document (PDF, scan, photo, spreadsheet, Word or PowerPoint file) and return its text as Markdown, tables included. Waits until Pulse has finished. The extraction_id it returns feeds the other steps. Uses 1 credit a page.

Inputs

FilefiletextRequired
The document: upload it, pick a file from an earlier step, or give a link Pulse can download. PDFs, images (JPG, PNG, TIFF and more), Word, PowerPoint, Excel, CSV and HTML files work. Uploads can be up to 100 MB.
Pagespagestext
Only these pages, such as 1-3,5. Leave empty for the whole document.
About the documentinstructionstext
Anything that helps Pulse read it, such as what kind of document it is or how to treat its numbers.
Double-checkrefinelist
Extra passes that correct what was read, for hard scans. Each one takes longer.One or more of: tables (Tables (structure, headers and cells)), text (Text (misread words, missing text and numbers)), formatting (Formatting (bold, italic, sub and superscript)), layout (Layout (reading order and page structure)).
Describe pictures and chartsdescribe_figurestrue/false
Write a description of each picture and chart into the text.
Cut the text into pieceschunk_typeslist
Also return the text cut into pieces, for search or AI steps: by meaning, by heading, by page or by size.One or more of: semantic (By meaning), header (By heading), page (By page), recursive (By size).
Piece sizechunk_sizenumber
The most characters in one piece, 100 to 10,000. Used with 'Cut the text into pieces'.From 100 to 10000.
Also return HTMLinclude_htmltrue/false
Return the document as HTML as well as Markdown.
Folder in Pulsefolder_nametext
Save the extraction in this folder of the Pulse Platform's library. It is made if it doesn't exist.

Outputs

chunksobject
The text cut into pieces, one list per way of cutting it that was asked for (semantic, header, page, recursive)
credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
extraction_idtext
The id of the saved extraction, for 'Extract fields', 'Split document', 'Extract tables' and 'Read charts'
extraction_urltext
Where to see the extraction in the Pulse Platform
failed_pageslist
Pages that could not be read, if any
htmltext
The document as HTML, when asked for
job_idtext
The Pulse job that did the work
markdowntext
The document's text, with headings and tables, as Markdown
page_countnumber
How many pages were read
warningslist
Notes from Pulse about the reading
Example output
{
  "chunks": {
    "page": [
      "# Account statement",
      "Closing balance: $980.10"
    ]
  },
  "credits_used": 2.0,
  "extraction_id": "e1b2a3d4-0000-4000-8000-000000000002",
  "extraction_url": "https://platform.runpulse.com/dashboard/extractions/e1b2a3d4-0000-4000-8000-000000000002",
  "failed_pages": [],
  "html": "",
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "markdown": "# Account statement\n\nOpening balance: $1,204.50",
  "page_count": 2,
  "warnings": []
}

Extract fields

Pull named fields (an invoice number, a total, a name) out of a document 'Extract document' has read, with where each was found and how sure Pulse is. Uses 1 credit a page.

Inputs

Extraction IDextraction_idtextRequired
The extraction_id from 'Extract document' (or from 'Get job' once a started extraction has finished).
Fields to extractfieldsobject
Each field's name with what it is, for example {"invoice_number": "The invoice number", "total": "The amount due"}. Give this or a JSON Schema.
JSON Schemajson_schemaobject
Instead of 'Fields to extract', a JSON Schema of the result, for numbers, lists and nested fields.
Instructionsinstructionstext
Anything else Pulse should know when reading the fields.
Take more carethoroughtrue/false
Reason through hard documents more carefully. Uses 6 credits a page instead of 1.

Outputs

citationsobject
Where in the document each value was found, by field name
confidenceobject
How sure Pulse is of each value, from 0 to 1, by field name
credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
job_idtext
The Pulse job that did the work
schema_idtext
The id Pulse saved these results under
valuesobject
Each field's value, by field name
Example output
{
  "citations": {
    "account_holder": [
      "txt-3"
    ],
    "closing_balance": [
      "tbl-1"
    ]
  },
  "confidence": {
    "account_holder": 0.98,
    "closing_balance": 0.95
  },
  "credits_used": 2.0,
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "schema_id": "5c1b2a3d-0000-4000-8000-000000000004",
  "values": {
    "account_holder": "Jo Bloggs",
    "closing_balance": "$980.10"
  }
}

Extract fields from a section

Pull named fields out of only the pages 'Split document' found for one topic. Uses 1 credit a page of that section.

Inputs

Split IDsplit_idtextRequired
The split_id from 'Split document'.
TopicsectiontextRequired
The topic to read, named exactly as in 'Split document'.
Fields to extractfieldsobject
Each field's name with what it is, for example {"invoice_number": "The invoice number", "total": "The amount due"}. Give this or a JSON Schema.
JSON Schemajson_schemaobject
Instead of 'Fields to extract', a JSON Schema of the result, for numbers, lists and nested fields.
Instructionsinstructionstext
Anything else Pulse should know when reading the fields.
Take more carethoroughtrue/false
Reason through hard documents more carefully. Uses 6 credits a page instead of 1.

Outputs

citationsobject
Where in the document each value was found, by field name
confidenceobject
How sure Pulse is of each value, from 0 to 1, by field name
credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
job_idtext
The Pulse job that did the work
schema_idtext
The id Pulse saved these results under
sectiontext
The section the fields were read from
valuesobject
Each field's value, by field name
Example output
{
  "citations": {
    "account_holder": [
      "txt-3"
    ],
    "closing_balance": [
      "tbl-1"
    ]
  },
  "confidence": {
    "account_holder": 0.98,
    "closing_balance": 0.95
  },
  "credits_used": 1.0,
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "schema_id": "5c1b2a3d-0000-4000-8000-000000000005",
  "section": "Summary",
  "values": {
    "account_holder": "Jo Bloggs",
    "closing_balance": "$980.10"
  }
}

Extract tables

Rebuild the tables of a read document, keeping merged cells and headers that span columns. Must be turned on for your organization by Pulse. Uses 0.25 credits a table.

Inputs

Extraction IDextraction_idtextRequired
The extraction_id from 'Extract document' (or from 'Get job' once a started extraction has finished).
Join tables split across pagesmerge_across_pagestrue/false
Join a table that runs onto the next page into one. Uses 0.5 credits a table.
Turn charts into tablescharts_to_tablestrue/false
Also make a table from each chart. 1 more credit a chart.
Formattable_formattext
An HTML table, or a list of columns and rows.One of: html (HTML table (default)), json (Columns and rows). Default: html.

Outputs

credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
job_idtext
The Pulse job that did the work
table_countnumber
How many tables were found
tableslist
The tables found
tables_idtext
The id Pulse saved these tables under
Example output
{
  "credits_used": 0.25,
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "table_count": 1,
  "tables": [
    {
      "citations": [
        "tbl-1"
      ],
      "from_chart": false,
      "table_content": "<table><tr><th>Date</th><th>Amount</th></tr></table>"
    }
  ],
  "tables_id": "7b1b2a3d-0000-4000-8000-000000000006"
}

Fill form

Fill in a PDF form from plain-language instructions, on real form fields or on a flat scan, and save the filled PDF. Must be turned on for your organization by Pulse. Uses 3 credits a page.

Inputs

PDF formfiletextRequired
The PDF form: upload it, pick a file from an earlier step, or give a link Pulse can download.
What to fill ininstructionstextRequired
The details to put on the form, in plain words.
Pagespagestext
Only these pages, such as 1-3,5. Leave empty for the whole document.

Outputs

content_typetext
The saved file's type (application/pdf)
credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
document_reftext
The saved PDF, for a later step to attach
fields_fillednumber
How many fields were changed
filenametext
The saved PDF's name
form_idtext
The filled form's id in Pulse
job_idtext
The Pulse job that did the work
page_countnumber
How many pages the PDF has
size_bytesnumber
The saved PDF's size in bytes
urltext
Where to download the saved PDF in Lodol
Example output
{
  "content_type": "application/pdf",
  "credits_used": 3.0,
  "document_ref": "doc_0123456789abcdef0123456789abcdef",
  "fields_filled": 7,
  "filename": "pulse-form-f1b2a3d4.pdf",
  "form_id": "f1b2a3d4-0000-4000-8000-000000000009",
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "page_count": 1,
  "size_bytes": 140815,
  "url": "/actions/core/serve-document/doc_0123456789abcdef0123456789abcdef"
}

Get job

Read a Pulse job's status, and what it produced once it has finished. Free.

Inputs

Job IDjob_idtextRequired
The job_id from 'Start document extraction' or any other step.

Outputs

created_attext
When the job was started (ISO 8601)
errortext
Why the job failed, when it did
extraction_idtext
For a finished document reading, the saved extraction's id
is_finishedtrue/false
True once the job has ended, however it ended
job_idtext
The job's id
markdowntext
For a finished document reading, the document's text
resultobject
Everything the finished job produced, as Pulse returns it
statustext
pending, processing, completed, failed, canceled or expired
updated_attext
When the job last changed (ISO 8601)
Example output
{
  "created_at": "2026-11-02T10:30:00Z",
  "error": "",
  "extraction_id": "e1b2a3d4-0000-4000-8000-000000000002",
  "is_finished": true,
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "markdown": "# Account statement",
  "result": {
    "extraction_id": "e1b2a3d4-0000-4000-8000-000000000002",
    "page_count": 2
  },
  "status": "completed",
  "updated_at": "2026-11-02T10:30:45Z"
}

Get usage

Read your plan's credits used and left this billing period, and how many documents, pages and credits were used between two dates (the last 30 days by default). Free.

Inputs

Fromfrom_datedate
The first day to count. Leave empty for 30 days ago.
Toto_datedate
The last day to count, included. Leave empty for today.
Break down bygroup_bytext
Count by day, week or month.One of: day (Day (default)), week, month. Default: day.

Outputs

billingobject
Where the current billing period stands
by_periodlist
What was read in each day, week or month (empty ones left out)
fromtext
Start of the period counted (ISO 8601)
group_bytext
How the period is broken down: day, week or month
totext
End of the period counted (ISO 8601)
totalsobject
What was read in the period counted
Example output
{
  "billing": {
    "credit_allowance": 50000.0,
    "credits_remaining": 37548.5,
    "credits_used": 12451.5,
    "limit_exceeded": false,
    "period_end": "2026-12-01T00:00:00+00:00",
    "plan_name": "Growth"
  },
  "by_period": [
    {
      "credits": 803.0,
      "documents": 130,
      "pages": 708,
      "period": "2026-11-01T00:00:00+00:00"
    }
  ],
  "from": "2026-10-03T00:00:00+00:00",
  "group_by": "day",
  "to": "2026-11-02T23:59:59.999999+00:00",
  "totals": {
    "credits": 4184.0,
    "documents": 611,
    "pages": 3720
  }
}

Read charts

Turn the line, bar, pie and scatter charts of a read document back into their numbers. Must be turned on for your organization by Pulse. Uses 1 credit a chart.

Inputs

Extraction IDextraction_idtextRequired
The extraction_id from 'Extract document' (or from 'Get job' once a started extraction has finished).
Pagespagestext
Only charts on these pages, such as 1-3,5.
Points per linedata_pointsnumber
How many points to read along each line, 2 to 500. Pulse's default is 20.From 2 to 500.

Outputs

chartslist
The charts, each with its data
charts_idtext
The id Pulse saved these charts under
countnumber
How many charts were read
credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
job_idtext
The Pulse job that did the work
Example output
{
  "charts": [
    {
      "confidence": 0.9,
      "id": "p2-chart-1",
      "page_number": 2,
      "series": [
        {
          "data": [
            [
              "Jan",
              410
            ]
          ],
          "name": "Spending"
        }
      ],
      "title": "Monthly spending",
      "type": "bar"
    }
  ],
  "charts_id": "8c1b2a3d-0000-4000-8000-000000000007",
  "count": 1,
  "credits_used": 1.0,
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001"
}

Read form fields

Find the fields of a PDF form, filled in or blank, scanned or not, with what each one holds and which boxes are ticked. Must be turned on for your organization by Pulse. Uses 1 credit a page.

Inputs

PDF formfiletextRequired
The PDF form: upload it, pick a file from an earlier step, or give a link Pulse can download.
Pagespagestext
Only these pages, such as 1-3,5. Leave empty for the whole document.

Outputs

credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
field_countnumber
How many fields were found
form_fieldslist
The fields found
form_idtext
The form's id in Pulse
job_idtext
The Pulse job that did the work
page_countnumber
How many pages the PDF has
Example output
{
  "credits_used": 1.0,
  "field_count": 1,
  "form_fields": [
    {
      "checkbox_details": [
        {
          "selected": true,
          "text": "Individual"
        }
      ],
      "page_number": 1,
      "text": "Individual C corporation",
      "type": "checkbox"
    }
  ],
  "form_id": "f1b2a3d4-0000-4000-8000-000000000008",
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "page_count": 1
}

Split document

Find which pages of a read document hold each topic you name, such as the financial statements of an annual report. Uses 2 credits a page.

Inputs

Extraction IDextraction_idtextRequired
The extraction_id from 'Extract document' (or from 'Get job' once a started extraction has finished).
TopicstopicsobjectRequired
Each topic's name with what belongs in it, for example {"Financials": "Balance sheet and income statement"}.

Outputs

credits_usednumber
Credits this step used (empty when your plan doesn't use credits)
job_idtext
The Pulse job that did the work
sectionslist
Each topic with its page numbers
split_idtext
The split's id, for 'Extract fields from a section'
splitsobject
Each topic's page numbers, by topic name
Example output
{
  "credits_used": 4.0,
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "sections": [
    {
      "name": "Summary",
      "pages": [
        1
      ]
    },
    {
      "name": "Transactions",
      "pages": [
        1,
        2
      ]
    }
  ],
  "split_id": "51b2a3d4-0000-4000-8000-000000000003",
  "splits": {
    "Summary": [
      1
    ],
    "Transactions": [
      1,
      2
    ]
  }
}

Start document extraction

Start reading a document and go on at once, without waiting. Follow it with 'Get job'. For very long documents. Uses 1 credit a page.

Inputs

FilefiletextRequired
The document: upload it, pick a file from an earlier step, or give a link Pulse can download. PDFs, images (JPG, PNG, TIFF and more), Word, PowerPoint, Excel, CSV and HTML files work. Uploads can be up to 100 MB.
Pagespagestext
Only these pages, such as 1-3,5. Leave empty for the whole document.
About the documentinstructionstext
Anything that helps Pulse read it, such as what kind of document it is or how to treat its numbers.
Double-checkrefinelist
Extra passes that correct what was read, for hard scans. Each one takes longer.One or more of: tables (Tables (structure, headers and cells)), text (Text (misread words, missing text and numbers)), formatting (Formatting (bold, italic, sub and superscript)), layout (Layout (reading order and page structure)).
Describe pictures and chartsdescribe_figurestrue/false
Write a description of each picture and chart into the text.
Cut the text into pieceschunk_typeslist
Also return the text cut into pieces, for search or AI steps: by meaning, by heading, by page or by size.One or more of: semantic (By meaning), header (By heading), page (By page), recursive (By size).
Piece sizechunk_sizenumber
The most characters in one piece, 100 to 10,000. Used with 'Cut the text into pieces'.From 100 to 10000.
Also return HTMLinclude_htmltrue/false
Return the document as HTML as well as Markdown.
Folder in Pulsefolder_nametext
Save the extraction in this folder of the Pulse Platform's library. It is made if it doesn't exist.

Outputs

job_idtext
The job's id, for 'Get job' and 'Cancel job'
messagetext
Pulse's note about the job
statustext
The job's status when started, usually pending
Example output
{
  "job_id": "c1b2a3d4-0000-4000-8000-000000000001",
  "message": "Document processing started",
  "status": "pending"
}

On this page