Quick overview
Quick overview This workflow runs weekly to pull HR datasets from Google Sheets, calculate rule-based attrition risk signals, and enrich them with an OpenAI (GPT-4o-mini) risk assessment. It logs results back to Google Sheets, sends high-risk alerts via Telegram, emails an HTML digest via Gmail . How it works Runs every week on a schedule trigger. Reads employee master data, attendance, engagement surveys, performance reviews, and 1:1 notes from Google Sheets and merges them into one profile per employee. Calculates a rule-based flight-risk score and factors, and builds an anonymized payload for model analysis. Sends the anonymized employee signals to OpenAI (GPT-4o-mini), parses the returned JSON risk assessment, and falls back to rule-only scoring while notifying an admin in Telegram if parsing fails. Combines the rule-based and LLM scores into a composite risk score and assigns a risk level. Sends a Telegram alert and appends a flagged record to the Google Sheets Risk_Dashboard for high-risk employees, while logging standard-risk outcomes to the same sheet. Reads the day’s Risk_Dashboard entries, builds an HTML summary, and emails the weekly digest to the HR team via Gmail. If any workflow node errors, posts an execution alert to a Slack channel. Setup Add Google Sheets OAuth credentials, set your Google Sheet ID, and ensure the spreadsheet includes tabs named Employees_Master, Attendance, Engagement_Survey, Performance_Reviews, OneOnOne_Notes, and Risk_Dashboard. Add an OpenAI credential and confirm the model selection (gpt-4o-mini) matches what’s available in your account. Add Telegram Bot credentials and replace YOUR_TELEGRAM_CHAT_ID for both the high-risk alert and LLM-failure admin notification. Add Gmail OAuth credentials and set the recipient address for the HR digest email. Add Slack OAuth credentials and replace YOUR_SLACK_CHANNEL_ID for workflow error alerts. Review and adjust the high-risk threshold value (default 70) and the weekly cron schedule as needed. An n8n automation workflow template by Rahul Joshi.
Rahul Joshi
web
paid
No benchmark results have been added yet.