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 supportAITurn your website docs into a GPT-4.1-mini support chatbotStarts on an event in a connected app · 16 stepsPineconeCustomer supportAIValidate concert ticket bookings and orchestrate fan experienceStarts on another system calling it · 16 stepsGmailGoogle SheetsSlackCustomer supportAIWhatsApp customer support with Claude and Google DocsStarts on an incoming WhatsApp message · 16 stepsWhatsAppCustomer supportAIAnalyze pentest reports and create remediation ticketsStarts on another system calling it · 17 stepsSlackCustomer supportAIAnalyze support screenshots with UploadToURL and OpenAIStarts on another system calling it · 17 stepsJiraSlackZendeskCustomer supportAIAnswer Instagram FAQ DMs with Gemini and QdrantStarts on a clock · 17 stepsGoogle DriveQdrantCustomer supportAIAnswer infrastructure questions in Mattermost with OpenRouterStarts on an event in a connected app · 17 stepsMattermostQdrantCustomer supportAIAutomate ITSM ticket classification and resolution with GeminiStarts on someone opening a chat with it · 17 stepsQdrantCustomer supportAIDraft customer support email replies with GmailStarts on a clock · 17 stepsGmailGoogle DriveGoogle SheetsTelegramCustomer supportAIHandle chat support and escalate unresolved ticketsStarts on another system calling it · 17 stepsGmailCustomer supportAIRoute and triage support tickets with Claude and CRMStarts on another system calling it · 17 stepsEmailCustomer supportAIRoute urgent Gmail support emails and WhatsApp digestsStarts on a clock · 17 stepsGmailSupabaseWhatsAppCustomer supportAITriage and reply to multilingual support tickets with ClaudeStarts on another system calling it · 17 stepsEmailCustomer supportAITriage and route support tickets with Gemini and JiraStarts on another system calling it · 17 stepsGmailJiraSlackCustomer supportAIAI sentiment-driven priority classificationStarts on another system calling it · 18 stepsGoogle SheetsSlackCustomer supportAIAI voice chatbot with ElevenLabs and OpenAIStarts on another system calling it · 18 stepsGoogle DriveQdrantCustomer supportAIAutomate support ticket classification & routingStarts on a clock · 18 stepsHubSpotJiraCustomer supportAIDaily Jira ticket summarizer with OpenAI and Jira APIStarts on a clock · 18 stepsGmailJiraCustomer supportAIHandle WhatsApp customer service chats with GeminiStarts on an event in a connected app · 18 stepsGoogle SheetsCustomer supportAIPersonalized AI assistant with Claude and OpenAIStarts on someone opening a chat with it · 18 stepsAirtableGmailGoogle CalendarTelegramCustomer supportAIRun a multilingual WhatsApp support assistant with OpenAIStarts on an incoming WhatsApp message · 18 stepsGmailGoogle SheetsWhatsAppCustomer supportAISelf improving email receptionist (FAQ based) with OpenAIStarts on a clock · 18 stepsAirtableGmailCustomer supportAISmart Customer Support System with OpenAI and GmailStarts on an arriving email · 18 stepsGmailGoogle DriveGoogle SheetsPineconeCustomer supportAITurn any website into an AI support chatbot with OpenAIStarts on someone opening a chat with it · 18 stepsPinecone

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.