Quick Overview This workflow runs daily to test whether Fairy Frills appears in AI shopping recommendations by querying OpenAI with 10 brand-focused questions (with and without web search), extracting mention and competitor data, generating a GEO gap analysis, and emailing a consolidated HTML report via Gmail. How it works Runs every 24 hours on a schedule. Generates 10 predefined shopping queries for Fairy Frills and includes the brand URL and a competitor list with each query. Sends each query to OpenAI twice in parallel, once to gpt-4o-mini (no search) and once to gpt-4o-search-preview (web search enabled). Combines the two model responses per query and uses OpenAI to extract structured metrics such as whether Fairy Frills is mentioned, mention count and position, competitor mentions, sentiment, and a key snippet. Uses OpenAI again to perform a GEO (Generative Engine Optimization) gap analysis that explains why competitors ranked, why the target brand missed, and which content actions and exact phrases to add. Deduplicates and aggregates insights across all checks, builds an HTML summary, and sends the daily GEO report email via Gmail.
Tags
GmailOpenAISlackRelated workflows
See all AI Automation→
Triage Gmail and draft email replies with OpenAI, Slack, and Google Sheets
Quick overview This workflow polls your Gmail inbox every 15 minutes, uses OpenAI to classify unread emails as URGENT, STANDARD, or SPAM, drafts reply emails for non-spam messages, posts a review notification to Slack, and logs spam messages to Google Sheets. How it works Runs every 15 minutes on a schedule and fetches up to 20 unread messages from your Gmail Inbox. Marks each fetched Gmail message as read and extracts key fields (sender, subject, snippet, body text, thread ID) for processing. Sends the email content to OpenAI to return a strict JSON classification (category, action label, priority note, and suggested subject). Routes SPAM messages to Google Sheets to append a row in a “Spam Log” sheet and stops further processing for those emails. Sends URGENT and STANDARD messages to OpenAI to generate a concise, plain-text reply draft in your writing style. Saves the generated reply as a Gmail draft in the original thread and posts a Slack message with the triage details so you can review and send. Setup Connect a Gmail OAuth2 credential and ensure the workflow has access to read Inbox messages, mark them as read, and create drafts. Add an OpenAI credential and customize the two
Sort Gmail leads, meetings, and trash with OpenAI classification
Quick Overview This workflow monitors Gmail for new messages, applies rule-based pre-classification, and uses OpenAI to categorize ambiguous emails as lead, review, or trash, then applies Gmail labels and schedules automatic deletion for trash threads. How it works Triggers every 5 minutes when a new Gmail message is received. Fetches the full email content from Gmail and extracts key fields like sender, subject, body, and thread ID. Applies deterministic rules to classify emails as team, meeting, website form, trash (bulk/OTP), or unknown. Adds Gmail labels for team and meeting emails, and skips processing for website form submissions. Sends only unknown emails to OpenAI for classification into LEAD, REVIEW, or TRASH and parses the returned JSON safely. Labels lead and review emails in Gmail, and for trash emails calculates a deletion timestamp, labels them as pending deletion, waits until that time, and then moves the entire Gmail thread to trash. Setup Connect a Gmail OAuth2 credential and ensure the trigger and Gmail actions point to the correct mailbox. Add an OpenAI API credential and select a model in the OpenAI classification step. Replace the placeholder Gmail label IDs (T
Monitor overtime risk against Japanese labour caps with Gemini, Sheets, Slack & Gmail
Quick Overview This workflow runs weekly to read attendance overtime from Google Sheets, totals it per employee and month, uses Google Gemini to classify risk against Japanese labour-law limits, writes results back to Sheets, and escalates high-risk cases via Slack and a Gmail draft. How it works Runs every week on a schedule. Loads configured Japanese overtime limits and fetches raw attendance rows from a Google Sheets “Attendance” worksheet. Aggregates overtime hours per employee per month. Sends each employee-month total to Google Gemini, which returns a structured risk level (over/approaching/ok) plus a short summary and recommended manager actions. Stores or updates the assessment in a Google Sheets “Overtime Status” worksheet keyed by employee and month. Posts to Slack when overtime is over the cap (and drafts a manager notice in Gmail), posts an early-warning Slack message when approaching the cap, and flags unclear or failed assessments to Slack for manual review. Setup Add credentials for Google Sheets OAuth, Google Gemini (PaLM) API, Slack OAuth2, and Gmail OAuth2. Create a Google Sheets spreadsheet with an “Attendance” sheet containing Employee (or Name), Month (or Date)