Summarise a batch of documents into one digest
Reads each Google Doc you list, summarises it with AI, and appends every summary to one digest document.
Apps it connects
Authenticate each one once and the workflow is ready to run.
What it does
The integration steps this workflow runs, in the order it first runs them.
- 1Google DocsGet document text
- 2OpenAIQuery model
- 3Google DocsAppend text
How it works
Everything the template sets up, and what to fill in before the first run.
Turns a list of documents you would otherwise have to open one by one into a single dated digest. You paste the links of the Google Docs you need to get through, name one Google Doc to collect the results in, and each document is read, summarised against your own instructions, and added to the digest under its own source link.
The summaries are appended, so every run adds a dated block rather than replacing what is already there and the digest becomes a running record you can search later. A document that cannot be opened - a bad link, a file the connected account has no access to, an empty page - is listed at the bottom of the digest under 'Could not be read' and the rest of the batch still goes through, so one broken link never costs you the whole run.
Set it up by pasting your links into the 'documentLinks' step (one per line, either full Google Docs links or bare document ids) and the destination link into the 'digestDocumentLink' step. Two things are worth tuning: 'summaryInstructions' controls what each summary contains - change it to ask for risks, action items or decisions instead - and 'maxCharactersPerDocument' caps how much of a long document is sent to the model, which is what keeps the cost of a large batch predictable. The model is set to GPT-5.4 mini because summarising is cheap work at volume; switch it on the step if you want a more capable one.
This reads Google Docs. Files that are not Docs - PDFs, spreadsheets, images sitting in the same folder - have no text to read and are listed as skipped.
You May Also Be Interested In
Answer channel questions from what was already saidAnswers a question posted in Slack using only the messages that channel already contains, in a thread.
Answer Telegram questions from the web, with sourcesAnswers questions asked in a Telegram chat by searching the web, and replies with the answer and the pages it came from.
Summarise and index new documents in a Box folderChecks a Box folder hourly and gives each new PDF its own summary document and one row in your index sheet.
Turn a multi-page scan into readable textRuns OCR over a scanned PDF, then writes each page as clean text into a Google Doc you can search, quote and edit.
Start from a workflow that already works.
Add "Summarise a batch of documents into one digest" to your workspace, connect its apps, and make it yours. No credit card required.
Free plan available · No credit card required