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

485 found

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

Customer supportAIAnswer questions from documents with RAG and SupabaseStarts on someone opening a chat with it · 19 stepsGoogle DriveSupabase vectorsCustomer supportAICreate Linear tickets from Notion content with OpenAIStarts on someone submitting a form · 19 stepsLinearNotionCustomer supportAIMine pharma complaint trends and trigger CAPA alertsStarts on a clock · 19 stepsSlackCustomer supportAISmart chat routing system with Gemini and NotionStarts on someone opening a chat with it · 19 stepsNotionCustomer supportAISync website FAQs to Pinecone weekly with OpenAIStarts on a clock · 19 stepsPineconeCustomer supportAIAnswer Facebook Messenger product questions with OpenAIStarts on an event in a connected app · 20 stepsGoogle SheetsCustomer supportAIHandle omni-channel customer support with OpenRouterStarts on someone opening a chat with it · 20 stepsEmailn8n data tableCustomer supportAIMicrosoft Outlook AI email assistant with AirtableStarts on a clock · 20 stepsAirtableOutlookCustomer supportAIRoute SaaS helpdesk chats with SoterAI and GroqStarts on someone opening a chat with it · 20 stepsPineconeCustomer supportAIRoute multilingual support requests with DeepL and OpenAIStarts on someone submitting a form · 20 stepsGmailCustomer supportAIRun a Telegram RAG support chatbot with OpenAI and PineconeStarts on an incoming Telegram message · 20 stepsGoogle SheetsTelegramCustomer supportAIRun an AI student helpdesk with OpenAI and Google SheetsStarts on someone opening a chat with it · 20 stepsGmailGoogle SheetsSlackCustomer supportAISmart email assistant: automate customer support with SupabaseStarts on an arriving email · 20 stepsGmailGoogle DriveSupabaseSupabase vectorsCustomer supportAITelegram AI voice agent - multiple language supportStarts on an incoming Telegram message · 20 stepsGoogle SheetsTelegramCustomer supportAIAnswer HR and IT policy questions on Telegram with OpenAIStarts on an incoming Telegram message · 21 stepsTelegramCustomer supportAIAutomate multi-channel customer support with GmailStarts on an incoming Telegram message · 21 stepsGmailGoogle SheetsTelegramCustomer supportAIAutomate support QA reviews with Intercom and OpenAIStarts on another system calling it · 21 stepsGoogle SheetsCustomer supportAIAutomated Slack IT helpdesk with OpenAI and SupabaseStarts on someone submitting a form · 21 stepsSlackSupabase vectorsCustomer supportAIBuild a Telegram AI assistant with MemMachine and OpenAIStarts on an incoming Telegram message · 21 stepsGmailGoogle CalendarGoogle SheetsTelegramCustomer supportAIGenerate GEO-optimized support replies from GmailStarts on an arriving email · 21 stepsGmailSlackCustomer supportAIHR & IT helpdesk chatbot with OpenAI and TelegramStarts on an incoming Telegram message · 21 stepsTelegramCustomer supportAIRun a customer support RAG chatbot with OpenAIStarts on someone opening a chat with it · 21 stepsGoogle DriveTelegramin-memory vectorsCustomer supportAITriage support emails with EmailConnect and Notion KBStarts on another system calling it · 21 stepsEmailNotionCustomer supportAIWhatsApp support bot with Google Drive RAG and OpenAIStarts on an incoming WhatsApp message · 21 stepsGoogle DriveSupabase vectorsWhatsApp

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.