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 supportTriage support tickets with OpenAI and HubSpotStarts on another system calling it · 20 stepsGmailGoogle SheetsSlackCustomer supportLog low-rating cleanliness complaints from Google Maps reviewsStarts on an event in a connected app · 21 stepsAirtableCustomer supportSync Zendesk tickets to Pipedrive contact ownersStarts on a clock · 21 stepsPipedriveZendeskCustomer supportAuto-reply to FAQs on WhatsApp with PostgresStarts on an incoming WhatsApp message · 22 stepsPostgresWhatsAppCustomer supportPower WhatsApp Business chat support with OpenAI and QdrantStarts on another system calling it · 22 stepsGoogle DriveWhatsAppCustomer supportRoute support tickets with SLA and SlackStarts on another system calling it · 22 stepsGmailSlackCustomer supportRoute website chat visitors to Calendly booking, FAQs, and GmailRun by hand · 24 stepsGmailCustomer supportAnswer FAQs and route Telegram users to support with PostgresStarts on an incoming Telegram message · 29 stepsPostgresTelegramCustomer supportVoiceflow demo support chatbot with AirtableStarts on another system calling it · 29 stepsAirtableGoogle CalendarGoogle SheetsCustomer supportAutomate B2B SaaS renewal risk management with CRMStarts on a clock · 30 stepsGmailHubSpotJiraPipedriveCustomer supportAdvanced Telegram bot, ticketing system, liveChat, userStarts on an incoming Telegram message · 31 stepsRedisTelegramCustomer supportWhatsApp to Chatwoot message forwarder with Postgres and RedisStarts on an event in a connected app · 31 stepsPostgresRedisCustomer supportEscalate overdue and blocked Jira tickets with GmailStarts on a clock · 33 stepsGmailJiraCustomer supportAIAI Auto Reply for Customer Questions with OpenAIStarts on another system calling it · 3 stepsCustomer supportAIAI Customer Support Auto Reply with OpenAIStarts on another system calling it · 3 stepsCustomer supportAIAutomated Ticket Processing and Routing Agent with DeepSeekStarts on someone opening a chat with it · 4 stepsCustomer supportAIPower website support chat with OpenAIStarts on someone opening a chat with it · 4 stepsCustomer supportAIAI-powered WhatsApp support bot with 2Chat and OpenAIStarts on an event in a connected app · 5 stepsCustomer supportAIAnswer research questions with OpenAIStarts on someone opening a chat with it · 5 stepsCustomer supportAIAutomated WhatsApp customer support agent (free WhatsApp server)Starts on another system calling it · 5 stepsCustomer supportAIPower a webshop support chatbot with OpenAI and TavilyStarts on someone opening a chat with it · 5 stepsCustomer supportAIQuery and answer questions from Excel spreadsheets with OpenAIStarts on someone opening a chat with it · 5 stepsCustomer supportAIAutomate WHMCS support ticket creation with GeminiStarts on someone opening a chat with it · 6 stepsCustomer supportAIGenerate customer support replies with Cloudflare Workers AIStarts on another system calling it · 6 steps

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.