Automations, described by what they do

15,351 working automation workflows. Every description is composed from the workflow's own steps: what starts it, which services it touches, whether it hands judgement to a model, and how much there is to read.

Browse the libraryBrowse by job

Cleaned of credentials and personal data. Ready to import.

Running now3 steps

Send daily Mailchimp subscriber reports to Slack

Waiting for a trigger
Workflows15,351working automations
Call a model7,615hand a step to AI
Services60apps they connect
Small5,286readable in one sitting

What they're for

17 kinds of job

The library

60 found

AllContentAlerts and monitoringData collectionIntegrationsLead generationResearch and reportingAI assistantsSchedulingMoney adminDocuments and filesChat assistantsCustomer supportE-commerceCRMHiringSetup and learningStrategy and planningS3 ✕

Money adminAISummarize invoices with AWS Textract and GeminiStarts on someone submitting a form · 5 stepsS3SlackContentAITranscribe & translate audio between languages with OpenAIStarts on another system calling it · 7 stepsS3AI assistantsAIStore AI-generated images in AWS S3: OpenAI image creationStarts on an event in a connected app · 10 stepsS3ContentAIGenerate SEO-optimized PWA website with GeminiStarts on someone submitting a form · 12 stepsGmailS3AI assistantsAIGenerate marketing ad banners with LINE and GeminiStarts on another system calling it · 12 stepsS3AI assistantsAIInstant infographic generator with LINE and Nano Banana ProStarts on another system calling it · 12 stepsS3AI assistantsAIBuild a RAG chat system with Aryn DocParse and AWS S3Starts on someone opening a chat with it · 13 stepsPineconeS3Money adminAIPDF proposal knowledge base with OpenAI and Qdrant RAGStarts on someone opening a chat with it · 14 stepsQdrantS3ContentAIGenerate Instagram posts with OpenAI and RSSStarts on a clock · 16 stepsRSSS3TelegramChat assistantsAIHr policy retrieval with Slack and RAGStarts on an event in a connected app · 16 stepsS3Slackin-memory vectorsContentAIHuman-in-the-loop post designer with Mistral and ImageKitStarts on someone opening a chat with it · 16 stepsGmailLinkedInS3AI assistantsAICreate AI-generated books with OpenAI and DALL-EStarts on someone opening a chat with it · 18 stepsGoogle DriveS3Data collectionAISync OpenAI vector stores from Google Sheets with DriveStarts on a clock · 19 stepsGoogle DriveGoogle SheetsS3Money adminAIExpense organizer with Google Drive and GeminiStarts on someone submitting a form · 21 stepsGmailGoogle DriveS3Customer supportAICreate business partner in SAP from Jira service desk requestStarts on a clock · 22 stepsEmailJiraS3AI assistantsAIGenerate LinkedIn carousel images from text with MistralStarts on someone opening a chat with it · 26 stepsGoogle DriveS3ContentAIGenerate SEO-optimized blog content with Gemini and RSSStarts on an event in a connected app · 26 stepsRSSS3TelegramContentAIPublish brand-compliant Instagram posts with OpenAIStarts on a clock · 29 stepsGoogle SheetsS3Data collectionAIAutomate viral video generation with Shotstack, OpenAI, and S3Starts on a clock · 30 stepsS3SupabaseYouTubeContentAIHacker News to video content with OpenAI and DropboxStarts on an event in a connected app · 39 stepsDropboxGoogle DriveLinkedInS3Customer supportAIBuild an AI-powered SMS support system with Twilio and OpenAIStarts on another system calling it · 40 stepsGmailPostgresS3ContentAIPublish daily multi-platform social posts from live web researchStarts on a clock · 40 stepsNotionS3ContentAIViral videos into new content with Gemini and OpenAIStarts on an incoming WhatsApp message · 50 stepsGoogle SheetsS3WhatsAppDocuments and filesCreate transcription jobs with AWS TranscribeStarts on an event in a connected app · 3 stepsS3

Start small

A few you can read in one sitting

What we took out

Cleaned before anything was stored

These files carry more of whoever built them than is obvious. All of it is stripped, and every file was checked, not sampled. Where an author left a live document behind, it is replaced with the placeholder the careful ones used, so you can still see what belongs there.

Triggers

What starts them

  1. A clock4,166
  2. An event in a connected app3,946
  3. Another system calling it2,801
  4. An arriving email1,591
  5. Someone submitting a form1,545
  6. Someone opening a chat with it895
  7. A change in a Google Sheet216

Services

What they touch

Google Sheets5,229Gmail3,419Slack2,307Telegram1,809Google Drive1,540Email863Airtable554Google Calendar480Notion471RSS404Postgres306WhatsApp285

Read the workflows

Filter 15,351 automations by what they do, what they connect to and how big they are, and open the definition itself, ready to import.

Q&A

What are these?

Working automations: the definition of each, ready to import, with a description composed from its own steps.

Why are some descriptions unflattering?

Because they say what the workflow does. One that is four steps and a webhook is described as four steps and a webhook, so you can decide from the page whether it is worth your afternoon.

What was removed from the files?

Instance identifiers, canvas notes with personal links and email addresses, saved credential names, and live documents left in by their authors. Every file was checked, not sampled.

What do I need to run them?

A workflow automation tool that imports these definitions. Each imports as it is; you add your own credentials.