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 supportBoost your customer service with Google Sheets and WhatsAppStarts on an incoming WhatsApp message · 12 stepsGoogle SheetsWhatsAppCustomer supportCrawls Korean SME government support programsStarts on an event in a connected app · 12 stepsGoogle SheetsCustomer supportGenerate FAQs with OpenAI and SupabaseStarts on another system calling it · 12 stepsSupabaseCustomer supportProactive SLA monitoring & ticket escalation with ZendeskStarts on a clock · 13 stepsGoogle SheetsSlackZendeskCustomer supportSync Beex WhatsApp ticket messages with HubSpotStarts on an event in a connected app · 13 stepsHubSpotCustomer supportTriage customer support emails with Groq AI and ClickUpStarts on an arriving email · 13 stepsClickUpGmailGoogle SheetsSlackCustomer supportUpdate HubSpot contacts with ZendeskStarts on a clock · 13 stepsHubSpotZendeskCustomer supportMulti-channel customer support automation suite with SlackStarts on another system calling it · 14 stepsEmailSlackCustomer supportTriage and escalate HubSpot tickets to Jira with Slack SLAStarts on a clock · 14 stepsHubSpotJiraSlackCustomer supportTriage and route support emails with Gemini and GmailStarts on an arriving email · 14 stepsGmailGoogle SheetsSlackCustomer supportTrack flight fares with Amadeus and SkyscannerStarts on a clock · 15 stepsPostgresCustomer supportAI-powered support ticket classifier with Google SheetsStarts on another system calling it · 16 stepsEmailGoogle SheetsSlackCustomer supportAutomate Instagram complaint handling with Claude and SLAStarts on another system calling it · 17 stepsGoogle SheetsSlackCustomer supportKakaoTalk notification for the government support programStarts on a clock · 17 stepsGoogle SheetsCustomer supportRoute grounded RAG support tickets with Claude and PineconeStarts on another system calling it · 17 stepsGoogle SheetsSlackZendeskCustomer supportSend Zendesk tickets to Pipedrive contacts and assign tasksStarts on a clock · 17 stepsPipedriveZendeskCustomer supportTriage and escalate tenant complaints from Gmail or formsStarts on another system calling it · 17 stepsAirtableGmailSlackCustomer supportCreate a two-way WhatsApp + Telegram integrationStarts on an incoming WhatsApp message · 18 stepsSupabaseTelegramWhatsAppCustomer supportRoute AI-powered customer support with Slack and PostgreSQLStarts on another system calling it · 18 stepsEmailGoogle SheetsPostgresCustomer supportSend Patient Appointment Reminders with Email and SMSStarts on another system calling it · 18 stepsAirtableEmailGoogle SheetsPostgresCustomer supportTriage and escalate support tickets with OpenAIStarts on another system calling it · 19 stepsGmailGoogle SheetsCustomer supportTriage and resolve support tickets with OpenAIStarts on another system calling it · 19 stepsSlackCustomer supportTriage support tickets into SLA queues with GmailStarts on another system calling it · 19 stepsGmailGoogle SheetsCustomer supportRoute omnichannel customer support with Ollama and PostgresStarts on another system calling it · 20 stepsPostgres

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.