Start from a Template
Discover and import ready-to-use automation templates, then connect them to AI agents and run in minutes.
All Templates
266+ pre-built automation templates to help you get started quickly
Categories
Showing 12 of 266 templates
Website Pitch Builder
Finds a shop that has no website and builds it one. Google Maps is searched through the scrape.do API, the listings are filtered down to businesses with a phone, enough reviews to prove they have customers, and no real site of their own - a Facebook page or a Wix subdomain counts as no site - and the best one is scored out. Its opening hours, ten best reviews and four public domain photographs are gathered, and a DeepSeek Agent writes a single self-contained page from that brief and nothing else. A real browser then photographs the page, and the screenshot and a CSV row are mailed to you. Google Maps has no email column, so the packet comes to you with the shop's phone number in it, and a person makes the call.
API Calls with Http Request
Three HTTP calls, one node. A plain read of a public exchange rate service, the same call behind a password, and a call that carries a file. They differ only in their properties, which is the point: authentication is a property and not a different node, and neither is a multipart body. Basic Authentication takes a vault item and nothing else, so no password is written into the flow, and an at-sign in front of a path is what makes the node open that file and send it as a form part, exactly the way curl does it.
Clinic Support Assistant
A customer support assistant for a website, served to the page as one MCP tool. A visitor and a signed-in patient are answered by two different Hermes Agents, and the difference is not a prompt or a flag, it is two wires: the visitor's agent is wired to the practice documents and to nothing else, so nothing on that side of the canvas can reach a patient record whatever the model is asked. The signed-in tools take no arguments at all. They read the record number the website established from a session cookie, so the model cannot name a patient, and every turn is written to a dialog log the practice can read in the morning.
Webhook Screenshot Service
A flow that waits to be called. Http In gives it a public URL that Robomotion hosts for you, with no port to open and no tunnel to run, and Http Out answers on the same held-open request. Between the two, the robot does what a web service cannot do for itself: it opens a real browser, loads the page it was asked about, waits three seconds for it to settle, and photographs it. The reply is the PNG, attached to the response, so curl -o shot.png is a complete client and nothing about the caller needs to know what Robomotion is.
Conversational Order Assistant
A conversational chat assistant that takes a return in whatever order the customer explains it. An LLM Agent asks for whatever is missing, and an ordinary automation wired to its tools port looks the order up mid conversation and hands the answer back.
Guided Returns Desk
A guided chat assistant that opens a product return, one question at a time. Uses Chat Assistant widget nodes for the questions, checks the order number while the customer is still in the conversation, and loops back to the question when it does not recognise one instead of throwing an exception.
Internship Application Intake
Collect work from people who are not in your workspace. A published Robomotion form is a public web page with its own link: whoever answers it needs no account and installs nothing, and every submission becomes one item on a workspace queue. Submissions are encrypted in the visitor's own browser with the public half of an RSA key pair from your vault, so the platform stores the history of every application and can never read one. Three nodes take the next application off the queue, decrypt it with the private half, and show every field the applicant filled in.
Knowledge Base Endpoint
Ask your own documents a question over HTTP. A Robomotion Knowledge Base is indexed by a workspace agent on your machine and searched locally by the robot; one Query Knowledge Base node returns the passages that answer a question, each with the document and heading it came from. Http In and Http Out turn the flow into a service anything can call, and a Min Score fence means it answers "I could not find that" instead of inventing something. Ships four sample documents and a thirty-line Python client.
Refund Queue
A work queue with both halves built for real: an intake that puts refund requests on a workspace queue one at a time, and a worker loop that takes them off, decides each one, and records Successful or Failed against it. Items are encrypted with an AES key from your vault before they leave the robot, so the Admin Console keeps the history of every item without ever being able to read one. Cut a single wire and the two halves become an intake you can schedule and a worker you can run on any number of robots.
Tax Portal MCP Server
Serves an ordinary RPA automation to an AI assistant as MCP tools, so a model can ask a question of a system it could never sign into. One Listen HTTP node makes the flow a stateless MCP server; three Tool In nodes declare the contracts a model reads, with no arguments, one required argument and one optional. Behind them a sign in subflow answers a government portal's tax number, password and one-time code from the vault, and two more subflows read VAT returns, penalties and electronic invoices off the page. The caller is given a bearer token and nothing else, and Tool Out's Is Error flag lets the flow refuse a company it holds no mandate for instead of returning an empty answer the model will fill in for itself.
Payment Run with Hold Report
Runs the weekly vendor payment run in a SAP-style ERP and then accounts for every bill it refused to pay. Signs in with credentials read from the Robomotion Vault, proposes the bills due within seven days, confirms the run so a journal entry is posted per document, and verifies the posted summary against the proposal before going on. Then it opens the bills list, filters to the blocked bills, and reports each one with the reason it is on hold - a pending goods receipt, a quantity or price mismatch against the purchase order, or a missing PO reference. Writes a two-section CSV covering what was paid and what was held back, with the value held back totalled.
RAG with DeepSeek
Retrieval-augmented generation over your own documents, with the retrieval handed to the agent instead of done for it. Documents are read, chunked, embedded and stored in LanceDB - an embedded vector database that is just a directory on disk. A DeepSeek Agent then answers questions through a search_knowledge tool built from ordinary flow nodes, writing its own queries and searching as many times as a question needs, with the source document named against every fact.