Quick Overview This workflow takes a real estate listing, uses OpenAI to generate ad copy and a video generation prompt, then sends it to the Videotok API to create a 9:16 vertical listing video ad with a caption and compliance notes. How it works Starts manually to test the workflow with a sample property listing. Builds a listing record containing the address, listing details, and image URLs (replace this with your real listing source). Sends the listing data to OpenAI to generate structured JSON for a video ad, including a script, generation prompt, caption, and compliance notes. Parses the OpenAI output and maps it into a Videotok generation payload with brand kit, reference images, quality, duration, and an idempotency key. Calls the Videotok Generations API to create the vertical video ad using the generated prompt and listing images. Setup Add environment variables for OPENAI_API_KEY, VIDEOTOK_API_KEY, and VIDEOTOK_BRAND_KIT_ID. Replace the sample listing step with your own source (CRM, Airtable, Google Sheets, MLS export, or scraper) and ensure it outputs address, listing_details, and listing_image_urls.
Tags
Related workflows
See all General Automation→Generate Pinterest pin copy CSV from blog RSS with OpenAI-compatible chat
Quick overview Turn your latest blog posts into Pinterest-ready pin titles, descriptions and keywords, exported as a CSV formatted for Pinterest's native bulk upload. An AI writes one conversion-focused pin per post from your RSS feed — curiosity-preserving titles under 90 characters, natural keywords, no clickbait. How it works Starts when you manually execute the workflow. Loads configuration values such as the RSS feed URL, number of posts to process, target Pinterest board name, and the AI API base URL and model. Reads the blog’s RSS feed and collects the newest N posts with their titles, links, and short snippets. Sends the post list to an OpenAI-compatible Chat Completions endpoint to generate one Pinterest pin title, description, and keyword set per post as structured JSON. Transforms the AI response into Pinterest bulk upload columns (including Title, Description, Keywords, Link, and Pinterest board) and inserts a placeholder Media URL for you to replace. Converts the rows into a CSV file and provides it for download. Setup Add an HTTP Header Auth credential for your OpenAI-compatible API (for example, Authorization: Bearer ) and select it on the AI request step. Update the
Track data deletion requests from Gmail with Jira, BigQuery, and Slack
Quick Overview This workflow monitors a Gmail inbox for potential privacy/data deletion requests, classifies each email, creates the appropriate Jira issue, logs a minimal audit record to BigQuery, and alerts the team in Slack, with an optional Gmail confirmation draft for human review. How it works Triggers when a new email matching deletion-related keywords arrives in Gmail (or runs manually for testing). Loads shared configuration values like Jira project details, BigQuery destination, SLA window, Slack channel, and confidence threshold. Cleans the email text, extracts the requester address, classifies the request type (deletion/access/correction), and calculates an SLA due date with a confidence score. Creates a Jira task for the privacy team when the classification is confident, or creates a separate Jira task labeled for manual review when it is not. Inserts an audit row into Google BigQuery with metadata such as request type, confidence, received time, due date, and whether a Jira issue was created. Posts a Slack message to the configured channel about the routed request or the need for manual review. Creates a draft confirmation email in Gmail for the requester after a rout
Draft security questionnaire answers with Notion, Google Docs, and Slack
Quick overview This workflow runs on demand to match security questionnaire questions against an approved-answer library in Notion, then creates a Google Docs draft and notifies reviewers in Slack, optionally updating a Notion tracker page. How it works Starts manually to run a test questionnaire and load configuration values like the Notion database ID, Google Drive folder ID, and confidence threshold. Loads a list of questionnaire questions and queries the Notion database for answers whose Status equals the configured approved value. Compares each questionnaire question to the approved Notion questions, selects the closest match, and marks low-confidence matches as “Needs review” instead of auto-answering. Branches based on whether any answers need review and posts a corresponding Slack notification to the configured review channel. Builds a formatted draft body containing each question, match confidence, owner, and either the approved answer or a “Needs review” placeholder. Creates a new Google Docs document for the draft and optionally updates a Notion questionnaire tracker page with “Draft ready for review” and the needs-review count. Setup Add Notion credentials and set the a