HTTP Request Workflows
1.200 Ergebnisse — 3 herunterladbare Workflow-Dateien, 1.197 quellenverknüpfte n8n-Referenzen
Draft personalized cold emails from Google Sheets using Gemini and HubSpot
Quick overview This workflow batch-processes leads from Google Sheets, researches each person and company using Tavily plus Google Gemini, drafts a personalized cold email, then creates/updates the contact in HubSpot with a research note and a saved email draft before marking the lead as Done in the sheet. How it works Runs manually and sets a batch size that controls how many leads to process per run. Reads leads from Google Sheets, skips rows already marked as Done, and normalizes the selected batch into clean lead fields. Processes the batch one lead at a time and uses Tavily search (last 60 days) with Google Gemini to extract the most recent public activity, pain points, and a personalization hook. Cleans and parses the research JSON so it can be reused reliably downstream. Uses Google Gemini to draft a 90–120 word cold outreach email (subject and body) that incorporates the research and offers a free “Automated LinkedIn Post Creator” n8n workflow. Creates or reuses the HubSpot contact, logs a HubSpot note with the research and drafted email, and saves the email as a HubSpot engagement in DRAFT status. Updates the matching row in Google Sheets (by Email) to set Status to “Done
Create Zoho Books invoices from email attachments using OpenAI OCR
Quick overview This workflow monitors an IMAP inbox for emails with invoice attachments, uses OpenAI to OCR and extract structured invoice data, looks up customers and tax/currency settings in Zoho Books, and then creates a new Zoho Books invoice with the original attachment included. How it works Triggers when a new email arrives via IMAP. Filters for emails that contain attachments, then splits each attachment into its own item for processing. Normalizes each attachment’s binary data and routes it to OpenAI for OCR based on whether it is a PDF or an image. Fetches taxes, currencies, and active customer contacts from Zoho Books and prepares the data for matching and invoice creation. Sends the OCR text plus Zoho Books tax metadata to OpenAI to validate that the document is a sales invoice and to return invoice and customer details as JSON. Filters out non-invoice attachments, matches the extracted customer to an existing Zoho Books contact (with a configurable fallback), and posts a new invoice to Zoho Books using multipart upload to attach the original file. Setup Add IMAP credentials for the mailbox that receives invoice emails. Add Zoho Books OAuth2 credentials and ensure the c
WRecover Shopify abandoned carts and send weekly reports via Gmail and Sheets
Quick overview This template automates Shopify abandoned cart recovery with a 3-email Gmail sequence, tracks recoveries in Google Sheets via Shopify “order paid” webhooks, and sends a weekly HTML performance report every Monday using data aggregated from the same spreadsheet. How it works Receives a Shopify “checkout created” webhook, verifies the checkout includes an email address, and skips customers who already have an active recovery sequence logged in Google Sheets. Logs the abandoned checkout details to Google Sheets and waits one hour before checking Shopify Orders for a paid purchase by the same email. If no paid order exists, sends the first recovery email via Gmail and updates the Google Sheets row to mark Email 1 as sent. After another 23 hours, checks Shopify Orders again and, if still unpaid, sends the second recovery email via Gmail and updates Google Sheets. After another 48 hours, checks Shopify Orders again and, if still unpaid, creates a unique one-time Shopify discount (price rule + discount code) and sends the third email via Gmail, then stores the discount code and Email 3 status in Google Sheets. Receives a Shopify “order paid” webhook, looks up the customer i
Audit Meta pixel deduplication risks with Graph API and Claude
Quick overview This workflow audits Meta (Facebook) Pixels for potential duplicate conversion counting by comparing browser Pixel vs Conversions API (server) activity and highlighting events active campaigns optimize for, then uses Anthropic Claude to generate pixel-by-pixel verification next steps and prints a prioritized audit report. How it works Runs manually to start the audit. Calls the Meta Graph API to list ad account pixels and fetch ad sets to identify the optimization events used by ACTIVE campaigns. Selects which pixels to audit (prioritizing pixels tied to optimization events, optionally overridden by a dataset ID list) and limits the scope to reduce API calls. For each selected pixel, queries the Meta Graph API for browser-vs-server event source totals and per-event counts. Classifies each pixel’s tracking setup (browser-only, server-only, or dual-source) and prioritizes pixels where optimization events may need deduplication verification. Sends the flagged pixel stats to Anthropic Claude to produce a concise JSON summary and a concrete “verify dedup” action per pixel focused on the optimization events. Prints a formatted audit report showing source split, key convers
Review HeyReach campaign performance and tune Twain agents from Slack
Quick overview This workflow runs daily, pulls campaign stats and reply conversations from HeyReach, sends them to Twain for performance analysis, and posts a digest to Slack with optional one-click approval to apply Twain’s suggested agent updates. How it works Scheduled run Iterates through the configured pairs of Twain campaign IDs and HeyReach campaign IDs. Fetches the HeyReach campaign details, overall performance stats, and recent inbox conversations for each campaign. Packages key metrics and recent message threads and sends them to Twain’s /v2/Campaign/Analyze endpoint for analysis and optimization suggestions. Builds a Slack digest with health signals, reply themes, step diagnostics, and proposed agent changes (plus a link to the campaign in Twain when available). If there are actionable agent changes, posts the digest to Slack with Approve/Skip buttons and applies the approved changes via Twain’s /v2/Agent/Update, then confirms success or errors in Slack. If there are no changes, posts the digest only when the analysis is meaningful (for example, analyzed results or alerts), then moves on to the next campaign. Setup Add HeyReach API access using HTTP Header Auth credentia
Draft personalized LinkedIn outreach from buying signals with Twain and Slack
Quick overview This workflow captures buying-signal leads via a webhook (or optionally polls a HubSpot list), generates a personalized LinkedIn intro and follow-up sequence with Twain, and posts the ready-to-send draft to Slack, with an optional step to stage the lead in a HeyReach campaign. How it works Receives a lead signal via a POST webhook (or, if enabled, runs every 15 minutes to pull contacts from a HubSpot list). Sets the Twain LinkedIn campaign and optional HeyReach campaign IDs, then normalizes the incoming lead fields (name, email, company, LinkedIn URL, and signal context). Deduplicates leads using a stable unique identifier so previously processed contacts are skipped on future runs. If the lead has no LinkedIn profile URL but has an email, optionally looks up the LinkedIn URL using Findymail (or an alternative provider you enable) and merges it back into the lead. If a LinkedIn URL is available, calls the Twain Generate Sequence API to research the lead and generate an intro message plus follow-ups, or posts an error to Slack if generation fails. Formats the generated messages into a review-friendly summary and posts the draft to a Slack channel for manual sending, w
WSend hashed backend conversions to Meta Conversions API and Google Ads
Quick overview This workflow reads backend conversion events, normalizes and SHA-256-hashes required identifiers, and then sends each conversion to Meta Conversions API, Google Ads Enhanced Conversions, or both using HTTP requests with environment-based access tokens. How it works Runs manually to start the conversion upload. Sets the Meta Pixel ID, Meta/Google API versions, and Google Ads customer and conversion action IDs used to build requests. Loads backend conversion records (example rows) that include a destination flag (meta, google, or both) plus identifiers and conversion value data. Normalizes the identifier fields and hashes the required PII fields (email, phone, name, city/state/zip/country) with SHA-256. Regroups hashed identifiers with the original non-hashed fields (such as external_id, fbc/fbp, IP address, and user agent) into a per-conversion payload structure. Routes each conversion to Meta and/or Google based on the destination flag. Sends conversions to the Meta Conversions API and uploads conversions to the Google Ads API using authenticated HTTP requests. Setup Replace the example conversion source with your own data source (for example Supabase, Postgres, or
WGenerate and email invoice PDFs from Google Sheets with PDFMunk and Gmail
Quick overview This workflow watches a Google Sheets order sheet for new invoice rows, generates a unique invoice number, appends the normalized record to another sheet, converts an HTML invoice into a PDF via PDFMunk, and emails the PDF to the client using Gmail. How it works Triggers when a new row is added to a specified Google Sheets worksheet. Maps the incoming columns (client details, item, quantity, price, due date, and status) into a standardized structure and generates an invoice number. Appends the invoice data, including the generated invoice number, into a second worksheet in Google Sheets. Builds an HTML invoice template and calculates totals from quantity and unit price. Sends the HTML to the PDFMunk API to generate a PDF link, then downloads the PDF file. Sends the invoice to the client via Gmail with the PDF attached. Setup Connect your Google Sheets OAuth credentials and select the correct spreadsheet and source/target worksheets for the trigger and append actions. Create a PDFMunk API key (or equivalent header auth) and add it as HTTP Header Auth credentials for the PDF generation request. Connect your Gmail OAuth2 credentials and confirm the email subject/body an
Switch Gainium DCA bot risk mode with the fear and greed index and Telegram
Quick overview This workflow runs daily, fetches the Crypto Fear & Greed Index from alternative.me, and uses it to start or stop a Gainium Crypto Trading DCA bot as a simple risk-on/risk-off switch, sending the current regime and any errors to Telegram. How it works Runs every day at 08:00 on a schedule. Loads your bot settings, Fear/Greed thresholds, and Telegram chat ID from a single configuration step. Fetches the latest Crypto Fear & Greed Index value from the public alternative.me API. Classifies the 0–100 index value into risk-off, risk-on, or neutral based on your thresholds. Stops the Gainium bot when the value is at or below the fear threshold, starts the Gainium bot when it is at or above the greed threshold, and makes no change in the neutral band. Sends a Telegram message describing the index value, regime, and action taken, and posts Telegram alerts if the index fetch, bot action, or any workflow step fails. Setup Install the n8n-nodes-gainium community node and add a Gainium API credential with permission to start/stop the target bot. Add Telegram credentials (bot token) and set your Telegram chat ID in the Config step, and also update the chat ID in the three alert s
CWReport workflow errors to Asana tasks with Google Chat and Grok 4.5 analysis
Quick overview When a monitored workflow fails, this reads its Description field to find the owning client and assignee, looks them up in Asana, analyses the error with Grok 4.5, and creates an assigned task with a severity-based due date. Repeat failures comment on the existing task. How it works Any workflow that names this one as its error workflow triggers it on failure. There is no production trigger by design. The error payload only carries a workflow ID, so an HTTP Request calls the n8n API to read that workflow's own Description field, which holds a small JSON object naming the client and the assignee. Asana projects and users are fetched live and matched by name, so no GID is ever hardcoded. A failed match raises a warning that travels downstream instead of failing silently. Asana is searched for an open task covering the same workflow and node. If one exists, a comment carrying the new execution ID is added rather than a duplicate task. For a new error, Grok 4.5 via OpenRouter returns a root cause, a solution, concrete steps, a severity, and a category, held to a fixed shape by a structured output parser. Severity sets the due date: Critical today, High tomorrow, Medium i
Create Instagram carousels and TikTok slideshows with OpenAI and PostFast
Quick overview This workflow runs on a Mon/Wed/Fri schedule to generate an Instagram carousel or TikTok slideshow using OpenAI (GPT-4o-mini and gpt-image-1), sends the slides to Telegram for approval, and only then uploads the images and schedules the post via PostFast. How it works Runs every Monday, Wednesday, and Friday at 8am and loads your brand, topics, slide count, platform filter, and Telegram chat ID. Retrieves your connected social accounts from PostFast and keeps only accounts that are connected and match the selected platforms. Uses OpenAI (gpt-4o-mini) to write a carousel as strict JSON containing a caption and slide-by-slide headings, body text, and visual descriptions. Builds per-slide image prompts and uses OpenAI (gpt-image-1) to generate a 1024×1536 portrait image for each slide. Sends the generated slide images to Telegram and waits for you to approve or decline posting. If approved, requests per-account upload URLs from PostFast, uploads each slide image to the provided storage URLs, and schedules one PostFast social post per account with the slides in order and the generated caption. Setup Install and enable the PostFast community node (n8n-nodes-postfast) and
BW
Send and track LinkedIn outreach with Airtable, Unipile, and OpenRouter
Quick overview This workflow automates LinkedIn outreach by using Airtable as a CRM, Unipile to fetch profiles and send connection requests/messages, and OpenRouter to generate personalized connection notes and follow-ups, while tracking accepts and replies via Unipile webhooks. How it works Runs every weekday at 09:00 to pull up to 15 Airtable leads with Connection Status set to New. For each lead, derives the LinkedIn public identifier, fetches the LinkedIn profile from Unipile, and uses OpenRouter to generate a personalized connection note capped at 300 characters. Sends the LinkedIn connection request via Unipile, updates the Airtable record with request details (note, timestamps, invitation ID), and waits 30–90 seconds between sends. Receives Unipile new_relation webhook events, matches the lead by Provider ID, and marks the Airtable record as Accepted with an Accepted At timestamp. Receives Unipile message_received webhook events, filters to inbound replies, finds the matching Airtable lead, and marks it Replied while stopping the campaign. Runs daily at 10:00 to find accepted, no-reply leads due for follow-up, uses OpenRouter to write follow-up #1 or #2, sends the DM via Uni
WMonitor crypto news risk with CoinDesk RSS, OpenAI, Gmail, and Google Sheets
Quick overview This workflow polls the CoinDesk RSS feed every 10 minutes, filters for crypto-related stories, checks Google Sheets to avoid duplicates, uses OpenAI to score and summarize risk, logs results to Google Sheets, and sends Gmail alerts when the risk priority is HIGH or MEDIUM. How it works Polls the CoinDesk RSS feed every 10 minutes and retrieves the latest articles. Extracts each article’s title, description, link, and publish date, generates an article ID, and filters to only crypto-relevant items using a keyword match. Checks a Google Sheets “Seen Articles” tab to skip any article IDs that have already been processed. Sends the article text to the OpenAI Chat Completions API to return a JSON risk assessment including summary, coins, risk level, score, and recommended action. Parses the OpenAI response, normalizes the risk level into a HIGH/MEDIUM/LOW priority, and appends the article ID to the “Seen Articles” tab and the full analysis to a “Risk Log” tab in Google Sheets. Sends a formatted Gmail alert email for articles marked HIGH or MEDIUM priority. Setup Add an OpenAI API credential (OpenAI API) for the HTTP request to the Chat Completions endpoint. Create a Goog
Draft weekly blog newsletter digests from RSS with OpenAI-compatible APIs
Quick overview This workflow runs every Monday at 08:00, reads your blog’s RSS feed, filters posts from the last 7 days, and uses an OpenAI-compatible Chat Completions API to generate a markdown newsletter digest you can copy into your email tool. How it works Runs every Monday at 08:00 on a schedule. Loads configuration values (RSS feed URL, OpenAI-compatible base URL, model name, and desired tone). Reads the RSS feed and keeps only items published in the last 7 days, collecting each post’s title, link, and a short snippet. Stops with a “nothing to send” outcome when no posts are found for the week. Sends the weekly post list to an OpenAI-compatible Chat Completions endpoint to write a clean markdown digest (intro, one bullet per post, and a sign-off). Extracts the generated markdown content into a single field so you can copy the draft from the final output. Setup Update the RSS feed URL (and optionally the model, tone, and API base URL) in the configuration step. Create an HTTP Header Auth credential with an Authorization: Bearer header and attach it to the HTTP request that calls the Chat Completions API. If you use a non-OpenAI provider, set the API base URL to your OpenAI-com
WScreen, score and route job applicants with Gemini, Gmail, Sheets and Slack
Quick Overview This workflow runs daily to pull job applicants from Google Sheets, score each candidate against role requirements using the Google Gemini API, log results back to Google Sheets, and notify a Slack channel when an applicant meets or exceeds a minimum score. How it works Runs every day at 08:00 on a schedule. Reads applicant records from an “Applicants” tab in Google Sheets. Combines the job title, requirements, and each applicant’s resume text into a screening prompt. Sends the prompt to the Google Gemini API and requests a JSON response with score, verdict, strengths, gaps, and summary. Parses the returned JSON and normalizes the screening fields (score, verdict, strengths, gaps, and summary). Appends the screening result for every applicant to a “Screening” tab in Google Sheets. Posts a formatted message to a Slack channel when the applicant’s score is greater than or equal to the configured minimum score. Setup Connect credentials for Google Sheets OAuth, Google Gemini (PaLM) API, and Slack OAuth. Select your Google Sheets spreadsheet and ensure it has an “Applicants” sheet with fields like Name, Email, and Resume/ResumeText, plus a “Screening” sheet to store resu
WRepurpose blog posts into social content with Gemini, Google Sheets, and Slack
Quick Overview This workflow runs daily, reads your blog RSS feed, uses Google Gemini to repurpose the latest posts into Twitter/X and LinkedIn drafts in your brand voice, then appends the drafts to Google Sheets and posts them to a Slack channel for review. How it works Runs every day on a schedule and reads items from your blog’s RSS feed. Keeps only the three most recent posts to process. Builds a prompt that includes your brand voice, hashtags, and each post’s title, URL, and excerpt. Sends the prompt to the Google Gemini API to generate Twitter/X and LinkedIn copy formatted as JSON. Parses the Gemini response into separate twitter and linkedin draft fields. Appends the drafts to a Google Sheets worksheet and posts the formatted drafts to a Slack channel for review. Setup Add credentials for the Google Gemini (PaLM) API, Google Sheets OAuth2, and Slack OAuth2. Paste your blog RSS feed URL in the RSS reader step. Update the brand voice text and default hashtags to match your tone. Select the target Google Sheets spreadsheet and worksheet (for example, a “Social Drafts” tab) where drafts are appended. Choose the Slack channel where draft messages are posted.
WTriage and route support emails with Gemini, Gmail, Sheets and Slack
Quick Overview This workflow monitors unread Gmail support emails, uses Google Gemini to classify and summarize each message and draft a reply, logs the ticket details to Google Sheets, creates a Gmail draft response, and sends a Slack alert when the ticket is marked high priority. How it works Triggers every minute when a new unread email arrives in Gmail. Adds brand context and support guidelines, then builds a prompt that asks Google Gemini to return a JSON classification, priority, summary, and suggested reply. Sends the prompt to the Google Gemini API and parses the returned JSON into structured ticket fields. Appends the ticket details (sender, subject, category, priority, summary, and suggested reply) to a Google Sheets tab. Creates a Gmail draft reply in the original thread using the suggested response text. Sends a Slack message to a chosen channel when the ticket priority is high. Setup Connect credentials for Gmail, Google Gemini (PaLM) API, Google Sheets, and Slack. Update the brand name and support guidelines values used to guide Gemini’s response. Select the target Google Sheets spreadsheet and the “Tickets” sheet (and ensure your header columns match the fields you w
WRun LinkedIn outreach with Google Gemini, Apify, Google Sheets, and PhantomBuster
Quick overview This workflow collects a plain-English LinkedIn audience description via an n8n form, uses Google Gemini to generate a search URL, pulls matching leads from Apify, writes five personalized icebreakers to Google Sheets, and drip-launches a PhantomBuster agent every 15 minutes. How it works Receives a form submission with a plain-English description of your target LinkedIn audience. Uses Google Gemini to turn the audience description into a JSON response containing an Apollo-style search URL, then parses and extracts the searchUrl value. Calls the Apify API to run an actor and return up to 100 lead records matching the configured filters. Limits processing to the first five leads to control outreach volume. Uses Google Gemini to generate a short, unique connection-message icebreaker for each lead based on their profile fields. Appends or updates each lead in Google Sheets with contact details, LinkedIn URLs, and the generated icebreaker. Waits 15 minutes per lead and then triggers a PhantomBuster agent via HTTP request to start the outreach action. Setup Create and add credentials for Google Gemini (PaLM API) and update the model selection if needed. Add an Apify API t
WCreate daily vaping news avatar videos with Perplexity, Browserless, HeyGen, Telegram and Google Drive
Quick Overview This workflow runs daily at 9 AM, uses Perplexity to compile vaping industry news, optionally captures article screenshots via Browserless, and generates a HeyGen avatar video from a template. It then polls for completion, sends a Telegram notification, and archives the final video to Google Drive. How it works Runs daily at 9 AM and sets the output mode (portrait/landscape) and background type (screenshot or inline_title). If set to inline_title, it asks Perplexity for 4 ready-to-use stories (title, script, subtitle) and maps them into HeyGen template variables. If set to screenshot, it asks Perplexity for up to 10 stories, validates article accessibility with Browserless scraping until it collects 4 reachable URLs, and prepares the final story list. For the screenshot path, it screenshots each article with Browserless, uploads each image to HeyGen, and combines each story with its uploaded image URL. It sends the assembled template variables to HeyGen to generate a template-based video (in test mode) with the configured dimensions. It waits briefly, polls HeyGen until the video status is completed, and formats the final video metadata. It posts an optional Telegram
Generate Seedance videos with the Vancine Doubao API using polling
Quick overview Generate Seedance videos through the Vancine API, automatically poll asynchronous tasks, return the final video URL, and handle failed or timed-out generations with bounded retries. How it works Starts manually to define the Seedance model, prompt, video size, base URL, and polling limits. Sends a POST request to the Vancine /v1/video/generations endpoint to create a video generation task. Extracts and stores the returned task ID and initializes polling state (interval and maximum attempts). Waits for the configured interval, then sends a GET request to /v1/video/generations/{task_id} to check task status. Repeats polling until the task status is completed or until the maximum poll count is reached. Outputs the generated video result_url when completed, or stops with an error if the task fails or times out. Setup Create an HTTP Header Auth credential with Name set to Authorization and Value set to Bearer YOUR_VANCINE_API_KEY. Assign the same credential to both HTTP Request nodes: submitTask and pollTask. Confirm the Vancine API base URL in the workflow (default https://vancine.com) matches your environment. Update the prompt, model, size, and polling settings (interv
WClone brand voices and generate voiceovers with Smallest AI and Google Drive
Quick Overview This workflow receives a webhook request with an audio sample URL, voice name, and script, clones a voice and generates a matching voiceover using Smallest AI, uploads the MP3 to Google Drive, logs the voice ID in Google Sheets, and returns a public link in the webhook response. How it works Receives a POST webhook request containing an audio_url, voice_name, and script text. Downloads the provided voice sample file from the audio_url. Sends the sample to Smallest AI Voice Cloning to create a new voice profile and extracts the returned voiceId. Truncates the script text to a safe length and synthesizes speech with Smallest AI using the cloned voice ID. Uploads the generated MP3 voiceover to Google Drive and updates its sharing settings to be publicly readable. Appends the cloned voice ID and voice name to a Google Sheets “voice library” spreadsheet and returns a JSON response with the voice ID, Drive link, and timestamp. Setup Create a Smallest AI API key, store it securely in n8n, and replace the hardcoded Authorization: Bearer ... header used for voice cloning. Add a Smallest AI credential in n8n for the speech synthesis step and ensure it has access to the same Sm
WHandle NPS survey responses with OpenAI, Gmail, and Google Sheets
Quick Overview This workflow runs every 6 hours to read new NPS survey responses from Google Sheets, generates a personalized reply with OpenAI, and sends the email via Gmail. It then routes promoters, passives, and detractors for follow-up actions and marks each response as processed. How it works Runs on a schedule every 6 hours. Reads NPS responses from a Google Sheets tab and keeps only rows where Status equals "new". Validates required fields, parses the 0–10 NPS score, and classifies each response as Promoter, Passive, or Detractor. Sends the response context to OpenAI (Chat Completions) to generate a concise, personalized email body and builds a segment-specific subject line. Sends the personalized reply to the respondent using Gmail. For promoters, appends the comment as a quote to a separate Google Sheets testimonials tab and updates the original row’s Status to "Processed". For passives, updates the original Google Sheets row’s Status to "Processed", and for detractors, emails an alert to a support inbox via Gmail and then updates Status to "Processed". Setup Add credentials for Google Sheets, Gmail, and OpenAI in n8n. Replace YOUR_NPS_SHEET_ID with your Google Sheets doc
WHandle NPS survey replies and routing with OpenAI, Gmail, and Google Sheets
Quick Overview This workflow runs every 6 hours to read new NPS responses from Google Sheets, uses OpenAI to draft a personalized reply, sends it via Gmail, routes respondents by NPS segment, logs promoter quotes back to Google Sheets, alerts support on detractors, and marks each row as processed. How it works Runs on a schedule every 6 hours and reads NPS response rows from a Google Sheets document. Filters the sheet to keep only rows where Status equals “new” to avoid reprocessing. Validates required fields, parses the 0–10 NPS score, and classifies each response as Promoter, Passive, or Detractor. Calls the OpenAI Chat Completions API to generate a warm, personalized email body based on the score segment and the customer’s comment. Sends the generated reply to the customer via Gmail and then routes the workflow by segment. For promoters, appends the customer comment as a quote to a “promoter-quotes” tab in Google Sheets and marks the original row as Processed; for passives, it marks the row as Processed. For detractors, sends an alert email to your support team via Gmail and then updates the original Google Sheets row status to Processed. Setup Create credentials for Google Shee
Tailor ATS-ready resumes and cover letters with Gemini, Google Drive, Notion, and Gmail
Quick overview Transform any resume into a professional, ATS-compliant document with AI. Supports Global ATS, German, and Japanese resume formats, generates personalized cover letters, and automates PDF creation and delivery for every job application. How it works Receives an n8n form submission with the company name, job description, selected ATS type, and an optional request to generate a cover letter. Lists resume PDF files from a specified Google Drive folder, downloads each file, extracts the PDF text, and cleans it into a single plain-text resume input. Uses Google Gemini to rewrite the resume into pure-HTML output tailored to the job description, choosing Global ATS, German Lebenslauf, or Japanese Rirekisho formatting based on the selected ATS type. Converts the generated HTML resume into a PDF using the PDF.co HTML-to-PDF API and retrieves the resulting PDF from the returned URL. Uploads the generated resume PDF to a Google Drive output folder, then reads the existing Notion database entries to compute the next serial number and creates a new Notion database page linking to the uploaded file. If cover letter generation is requested, uses Google Gemini to write a localized c