All workflows
Google Sheets logoBox logoAnthropic logoGoogle Docs logo

Summarise and index new documents in a Box folder

Business Operations

Checks a Box folder hourly and gives each new PDF its own summary document and one row in your index sheet.

Add to WorkspaceBrowse all workflows
Every hour4 apps8 steps

Apps it connects

Authenticate each one once and the workflow is ready to run.

Google SheetsBoxAnthropicGoogle Docs

What it does

Each integration step this workflow runs, in order, what it is for, and the conditions and loops that decide when it runs.

  1. 1Google SheetsRead columnReads column C of the index sheet to learn which Box file ids have already been summarised.
  2. 2BoxList folder itemsLists everything in the watched folder so new PDFs can be told apart from files already indexed.

  3. For each item

    1. 3BoxDownload fileDownloads each new PDF so its title, type, parties, dates, reference and amounts can be read out of it.

    2. If detailBlock is not empty

      1. 4AnthropicGenerate model responseAsks the AI to write a short filing note from the extracted details alone, adding nothing and guessing at nothing.
      2. 5Google DocsCreate documentCreates a summary document for each new PDF, titled 'Summary' followed by the document's own title or file name.
      3. 6Google DocsInsert headingPuts the document's title, or its file name if none was read, at the top of the summary as a heading.
      4. 7Google DocsAppend textWrites the note, the details read word for word, and the source file, Box id and date read into the summary.
      5. 8Google SheetsAppend rowAppends one index row per document: date read, file name, Box file id, what it is and a link to the summary.

How it works

What happens on each run, in plain English.

Every hour, the Box folder you point it at is listed, the PDFs it has not read before are worked out from your own index sheet, and each new one gets a summary document in Google Docs and one row in that index. Your index sheet is the record of what has already been read.

Each summary document holds a short note saying what the document is, who it involves and any dates or amounts, followed by the exact details read out of it so you can check one against the other. The index row holds the date, the file name, the Box file id, a one-line description and a link to the summary. The note is written from those details alone, and anything not found is left blank, so it cannot assert something the document does not say. Rows are only ever added, only PDFs are read, and one file that cannot be read does not stop the rest.

Before the first run you need an index sheet with five columns: date read, file name, Box file id, what the document is, and a link to the summary.

boxgoogle sheetsgoogle docsdocumentsextractionhourly

You May Also Be Interested In

Pull the contact details out of your notesReads a page of notes and adds a row for every name, email address and phone number actually written in it.Extract purchase orders from GmailReads each new purchase order email, looks its items up in your product list, and logs every line with name and price.Track a property market over timeSearches one property site each week, records the listings that are new to you, and logs how the record has changed.Weekly chart of how a metric has movedEvery Monday, charts the recent history of one metric from your sheet and emails you the chart with a note on what changed.

Start from a workflow that already works.

Add "Summarise and index new documents in a Box folder" to your workspace, connect its apps, and make it yours. No credit card required.

Get StartedSee Pricing

Free plan available · No credit card required