OpenAI Workflows
630 Ergebnisse — ausschließlich quellenverknüpfte n8n-Referenzen
Generate rich character bibles for writers with GPT-4.1 and Google Sheets
Quick overview This workflow accepts character details via webhook or manual trigger, uses OpenAI to generate psychology, backstory, and emotional arc drafts in parallel, then synthesizes them into a structured “Character Bible” JSON response and optionally appends a log row to Google Sheets. How it works Receives a POST request on an n8n webhook (or runs manually) with character parameters like name, age, archetype, world setting, story role, traits, and constraints. Normalizes the incoming fields, validates the archetype, and derives genre tags from the world setting using Python logic. Sends the enriched character inputs to OpenAI three times in parallel to generate a psychology profile, a backstory, and an emotional arc document. Combines the three AI documents into a single context object and passes it to OpenAI again to synthesize a unified Character Bible with defined sections. Parses the Character Bible into structured JSON fields (identity snapshot, personality core, backstory highlights, emotional arc, voice, and story hooks) and adds metadata like request ID and timestamp. Returns the completed character profile as a JSON webhook response and optionally appends a summary
Manage KlickTipp contact tags with GPT-5-mini via chat input
Quick overview This workflow uses an n8n chat trigger, OpenAI (gpt-5-mini), and KlickTipp community nodes to interpret chat instructions and create, apply, or remove tags for an existing KlickTipp contact, returning a structured JSON result. How it works Receives a chat message containing a contact email address and explicit tag add/remove instructions. Uses OpenAI (gpt-5-mini) to extract the email plus the requested tags to apply and/or remove, enforcing strict rules to avoid inventing tags. Looks up the contact in KlickTipp by email and reads the contact’s currently assigned tag IDs. Retrieves the full tag list from KlickTipp and creates any missing tags that were explicitly requested for applying. Applies the resolved tag IDs to the contact in KlickTipp when an explicit apply action is present and the contact does not already have them. Removes specific tag IDs (or all currently assigned tag IDs when requested) from the contact in KlickTipp when an explicit remove action is present. Returns a structured JSON response summarizing what was requested, which tags were created, and which tag IDs were applied or removed. Setup Add KlickTipp credentials for the community KlickTipp node
Enrich KlickTipp contact fields using OpenAI GPT-5.5 and context
Quick Overview This workflow receives an email and a context block, uses OpenAI to extract and validate enrichment details against the existing KlickTipp subscriber record, and then updates approved mapped data fields in KlickTipp. How it works Receives an incoming request from another workflow containing a contact email address and a free-text context block. Fetches the existing subscriber record from KlickTipp using the provided email. Uses OpenAI to extract enrichment attributes from the context, compare them to the current KlickTipp values, and decide final values using a confidence threshold for overwriting non-empty fields. Updates the KlickTipp subscriber with the final approved values for the mapped fields (for example name, company, address, phone numbers, website, birthday, and social profile URLs). Setup Add KlickTipp credentials and ensure the target subscriber fields (including any custom fields for LinkedIn, Instagram, Facebook, and job title) exist in your KlickTipp account. Add an OpenAI API key credential and select the model you want to use in the OpenAI chat model configuration. Ensure the incoming payload sent to this workflow includes at least email and context
Generate personalized email salutations for KlickTipp contacts with OpenAI
Quick Overview This workflow triggers when a contact is tagged in KlickTipp, uses OpenAI to generate an HTML-ready email salutation with a quality score, and updates the KlickTipp subscriber record with the salutation only when it meets a defined confidence threshold. How it works Triggers when a contact is tagged in KlickTipp and receives the contact’s profile fields (name, email, company, and address data). Sends the contact details to OpenAI to generate a JSON response containing an HTML-ready salutation plus language, style, and a salutation quality score. Parses and validates the OpenAI response against a structured JSON schema. Checks whether the generated salutation quality score is greater than 80. Updates the contact in KlickTipp by writing the generated salutation into a configured custom field when the score passes the threshold. Setup Add KlickTipp credentials and ensure the KlickTipp trigger for “contact tagged” is enabled for your account. Add an OpenAI API key for the chat model used to generate the salutation. In KlickTipp, create/identify the tag that should trigger this automation and configure it to call the n8n webhook URL from the trigger. Create a KlickTipp cu
Send prioritized forex risk alerts from ForexLive RSS with OpenAI and Slack
Quick Overview This workflow polls the ForexLive RSS feed every five minutes, filters for forex-relevant headlines, uses OpenAI to generate structured risk analysis, deduplicates items in an n8n Data Table, and sends high-priority alerts to a Slack channel. How it works Polls the ForexLive RSS feed on a */5 * * * * schedule and ingests newly published items. Normalizes each RSS item into consistent fields (title, description, link, and date) and checks the text for predefined forex and macroeconomic keywords. For relevant items, sends the title and description to OpenAI (GPT-4.1-mini) to return a strict JSON risk assessment including summary, impacted currency pairs, risk level, confidence score, and recommended action. Parses the OpenAI JSON response, merges it back with the original news data, and computes a final risk score, priority level, and a normalized deduplication key. Checks an n8n Data Table for the dedupe key and only continues when the item has not been seen before. Stores the processed item in the n8n Data Table and posts a formatted Slack message when the computed priority is HIGH. Setup Add OpenAI credentials and ensure the OpenAI node is set to a model you have ac
BAnswer HR policy and benefits questions with BambooHR, OpenAI and Supabase
Quick Overview This workflow ingests company policy PDFs from BambooHR into a Supabase vector database and provides an employee chat interface that answers policy and benefits questions using OpenAI, with an additional employee/department lookup powered by BambooHR employee data. How it works Starts a manual run to fetch files from BambooHR and keep only PDFs in the “Company Files” category. Downloads each selected PDF, splits it into chunks, generates OpenAI embeddings, and inserts the content into a Supabase vector table for retrieval. Exposes a chat trigger where employees submit questions to an HR assistant. Uses OpenAI with conversation memory and retrieves relevant policy content from the Supabase vector store to ground responses. When a question requires a contact person, looks up employee details in BambooHR by exact name or finds the most senior person in a requested department using an OpenAI-assisted department extraction and ranking step. Returns the final answer to the chat, including policy-based guidance and any retrieved employee contact details. Setup Add BambooHR credentials and ensure your policies/benefits PDFs are available in the BambooHR file category named “
Score and advance job applicants with Airtable, Google Workspace and GPT-4o
Quick Overview This workflow collects job applications via an n8n form, stores CVs in Google Drive, logs applicants in Airtable, and uses OpenAI to score CV-to-role fit. Shortlisted candidates receive an AI-generated questionnaire, a personalized Gmail outreach, an auto-booked Google Calendar phone screen, and saved screening questions. How it works Receives a job application through an n8n form submission, including applicant details and a PDF CV upload. Uploads the CV to Google Drive, builds a normalized applicant record (name, email, phone, experience, CV link), and creates an applicant entry in Airtable. Downloads the stored CV from Google Drive, extracts text from the PDF, and uses an OpenAI-powered agent to score the CV against the job description pulled from Airtable. Updates the applicant’s Airtable record as either “Interviewing” (score ≥ 0.7) or “No hire” (score < 0.7), including the numeric score and short reasoning. For shortlisted candidates, generates five interview questions with OpenAI, presents them in a follow-up n8n form, and saves the candidate’s responses back to Airtable. Uses OpenAI plus Airtable job/candidate context to draft a personalized outreach email, s
WAnswer HR and IT policy questions on Telegram with OpenAI and Postgres PGVector
Quick overview This workflow builds a searchable HR policy knowledge base from a PDF and runs a Telegram helpdesk bot that answers employee questions from that content, handling both text messages and voice notes via OpenAI transcription and retrieval from a Postgres PGVector vector store. How it works Manually runs once to download an HR policy PDF over HTTP and extract its text. Splits the extracted policy text into chunks, generates OpenAI embeddings, and inserts the vectors into a Postgres PGVector store. Triggers on new Telegram messages sent to your bot. Routes incoming Telegram updates by type, sending text directly to the assistant, transcribing voice messages with OpenAI, or replying that other formats are unsupported. Uses an OpenAI chat model with Postgres-backed chat memory and a PGVector retrieval tool to answer questions grounded in the stored policy content. Sends the final answer back to the user in Telegram. Setup Add an OpenAI API key for embeddings, chat completions, and audio transcription. Set up a Postgres database with the PGVector extension enabled and add the Postgres credentials for both the vector store and chat memory. Create a Telegram bot with BotFathe
Create social posts from RSS feeds with OpenAI, Unsplash, and Buffer
Quick overview This workflow polls an RSS feed for new articles, uses OpenAI to generate platform-specific copy for X, LinkedIn, and Instagram, pulls a related random image from the Unsplash API, and creates queued posts in Buffer for each social channel. How it works Runs every hour and reads the latest items from the configured RSS feed. Sends each article title and snippet to OpenAI to generate three ready-to-post messages for X, LinkedIn, and Instagram. Requests a random related image from the Unsplash API using the article title as the search query. Creates an image post in Buffer for X using the generated Twitter text and the Unsplash image URL. Creates an image post in Buffer for LinkedIn using the generated LinkedIn text and the Unsplash image URL. Creates an image post in Buffer for Instagram using the generated Instagram caption and the Unsplash image URL. Setup Add an OpenAI API credential in n8n (or replace the included OpenAI credential) for the OpenAI node. Create a Buffer account, connect your X/Twitter, LinkedIn, and Instagram profiles, and add your Buffer API credential in n8n. Create an Unsplash developer app and replace the client_id value in the HTTP Request URL
Create blog drafts, images, and LinkedIn posts with Tavily, Gemini, and OpenAI
Quick overview This workflow receives a blog request via webhook, researches the topic with Tavily, generates a long-form HTML article using Google Gemini, creates two images via the kie.ai API, stores assets in Google Drive, updates a Google Sheets tracker, and notifies a Slack user with links. How it works Receives a POST webhook request containing a Google Sheets row payload with an “AI Blog Title” and related metadata. Searches the web for supporting sources using Tavily and passes the research plus the title to Google Gemini to generate the full article as HTML. Converts the generated content to HTML, creates a temporary HTML file in Google Drive, downloads it to set the correct text/html MIME type, re-uploads it as the final Drive file, and deletes the temporary file. Sends the finished article to OpenAI to generate a short LinkedIn post, then updates the matching row in Google Sheets with a Done flag, the article folder/link value, and the LinkedIn post text. Creates a cover image and an in-article infographic by submitting two text-to-image jobs to the kie.ai API, polling until each job succeeds, downloading each resulting image, and uploading both images to Google Drive. W
Generate digital product launch content with OpenAI GPT-4o-mini and Google Sheets
Quick overview This workflow generates a multi-channel digital product launch content pack from product details, using OpenAI to create a blog intro, LinkedIn post, X post, Instagram caption, and launch email, and can optionally append the results to Google Sheets. How it works Runs manually when you execute the workflow. Loads sample product details such as name, tagline, price, URL, target audience, and brand tone. Sends the product details to OpenAI (GPT-4o-mini) with instructions to return a JSON content pack for blog, LinkedIn, X, Instagram, and email. Normalizes and validates the returned JSON, ensuring all five content fields are present and formatted as plain text. Optionally appends the generated content fields as a new row in Google Sheets (when the Google Sheets step is enabled). Setup Add an OpenAI API credential and select it in the OpenAI Chat Model configuration. Replace the sample product fields (especially productURL and brandTone) with your own product data or connect a real data source. (Optional) Enable the Google Sheets step, add Google Sheets OAuth2 credentials, and set the target spreadsheet ID and sheet name. Requirements n8n instance (cloud or self-hosted)
Monitor AI search visibility with Talordata SERP, OpenAI, and Google Sheets
Quick overview This workflow runs on demand to crawl Google SERP pages via Talordata, aggregates organic results and related searches, uses OpenAI to produce a structured AI Search Visibility report with GEO recommendations and a score, and appends or updates the results in Google Sheets. How it works Starts when you manually execute the workflow and sets the target query, search engine (Google), and initial page. Calls the Talordata MCP Search API to fetch the first SERP page, then extracts pagination metadata and builds a list of pages to crawl. Loops through each SERP page and requests additional results from Talordata using the corresponding page/start value. Normalizes each page into structured datasets for organic results and related searches, and aggregates all page data into a single consolidated SERP payload. Sends the consolidated SERP dataset to OpenAI to generate a structured AI Search Visibility report (metrics, domain categorization, opportunities, recommendations, executive summary, and score). Parses the model output into JSON and appends or updates a matching row in Google Sheets keyed by the SERP link. Setup Add a Talordata Bearer Auth credential and confirm acces
Create Google Tasks from Tactiq meeting transcripts using OpenAI and Telegram
Quick overview This workflow monitors a Google Drive folder for new Tactiq transcript files, uses OpenAI to extract explicit action items, creates matching Google Tasks, sends a Telegram notification, and logs each processed transcript in an n8n Data Table to prevent duplicate processing. How it works Triggers when a new file is created in a specified Google Drive folder (or on an optional 12-hour schedule). Loads previously processed transcript filenames from an n8n Data Table and lists files in the target Google Drive folder. Filters out files that have already been processed, then downloads each new transcript and converts it to plain text. Sends the transcript text to OpenAI to return strict JSON containing only explicit action items with an owner, optional due date, and an evidence quote. Creates a Google Task for each extracted action item, including source transcript details in the task notes, and sends a Telegram error message if task creation fails. Records the transcript as processed in the n8n Data Table (including zero-task transcripts) and sends a Telegram success message. Setup Add credentials for Google Drive, Google Tasks, OpenAI, and Telegram. Create or choose an n
Run a multi-agent research and publishing pipeline with GPT-4o, Tavily and Notion
Quick overview Three specialized AI agents: Researcher, Writer, and Reviewer, collaborate autonomously to research a topic, draft content, and quality-check it through a self-correcting review loop with a circuit breaker. Approved content is published directly to Notion with full audit metadata. How it works A form submission captures the research topic, content format (blog post, exec summary, or LinkedIn post), target audience, and maximum revision cycles allowed before the circuit breaker fires. The Researcher Agent uses GPT-4o and Tavily Search to gather authoritative sources, extract key facts and contradictions, and produce a validated research brief. Search depth and result count are automatically scaled to the requested format. The Writer Agent receives the research brief and produces a structured draft in the correct format. On revision cycles it also receives the Reviewer's specific rejection notes and must address them directly. A Circuit Breaker sits between the Writer and Reviewer. If the number of Reviewer rejections reaches the user-defined maximum, the draft is force-approved and the pipeline proceeds to publishing without another LLM call. The Reviewer Agent evalua
Route rental payment and receipt messages with Telegram and OpenAI GPT-4.1
Quick overview This demo workflow listens for Telegram rental messages, routes receipt-related commands, uses OpenAI to classify payments, costs, and booking summaries, then replies with parsed details and a sample receipt flow. How it works Triggers when a new Telegram message is received. Routes the message into one of four paths: full /receipt command, receipt request, receipt date reply, or general rental tracking. If a full /receipt command is provided, it parses client, property, stay dates, amount, and transaction details and replies in Telegram with the extracted fields. If the user sends a receipt request, it looks up the last saved payment for that Telegram chat and either prompts the user for stay dates or returns an error if no payment is stored. If the user replies with stay dates during a pending receipt flow, it combines those dates with the stored payment to build receipt details and replies with either a “ready to generate” summary or an error message. For all other messages, it sends the text to OpenAI to classify it as payment, cost, or booking summary, normalizes the JSON result, and replies in Telegram with the parsed output. When a payment is detected, it extr
BCWScrape Hacker News hiring threads with OpenAI GPT-4o-mini and Airtable
Quick overview This workflow manually runs a scraper that finds the latest Hacker News “Ask HN: Who is hiring?” thread via the Algolia HN Search API, pulls each job comment from the Hacker News Firebase API, uses OpenAI to structure postings into fields, and saves the results to Airtable. How it works Starts when you manually execute the workflow. Queries the Algolia Hacker News Search API for recent “Ask HN: Who is hiring?” stories and keeps only the relevant thread metadata. Filters the results to the most recent thread (created within the last 30 days) and fetches the full thread from the Hacker News Firebase API. Iterates through the thread’s comment IDs, fetching each individual job comment from the Hacker News Firebase API. Extracts and cleans the job text to remove HTML/entities and normalize links and whitespace. Sends the cleaned text to OpenAI (GPT-4o-mini) to extract a structured JSON record (company, title, location, type, salary, description, and URLs). Creates a new record in Airtable for each structured job posting. Setup Add an Airtable credential and set the target base and table in the Airtable create step. Add an OpenAI credential for the GPT-4o-mini chat model.
Enrich company records with social media URLs using Supabase and GPT-4o
Quick overview This workflow pulls companies from Supabase, uses an OpenAI (GPT-4o) agent to crawl each company website and collect social media profile URLs via HTTP requests and HTML parsing, and then writes the enriched company record (name, website, and social links) back to Supabase. How it works Runs manually and loads all company records from a Supabase companies_input table. Keeps only each company’s name and website fields and sends the website to an OpenAI (GPT-4o) agent. The agent fetches page text (HTML converted to Markdown) and extracts links from pages (anchor hrefs), following additional URLs as needed to find social profiles. The agent returns a structured JSON object of social media platforms and their profile URLs. The workflow combines the extracted social links with the original company name and website. Inserts the enriched record into the Supabase companies_output table. Setup Add a Supabase credential and set the correct workspace/project so the workflow can read from companies_input and write to companies_output. Add an OpenAI API key in the OpenAI Chat Model node (configured for GPT-4o). Ensure your input table contains name and website fields (or update t
Send portfolio risk reports from Google Sheets with OpenAI and Gmail
Quick overview This workflow collects a portfolio request via an n8n Form, loads holdings from Google Sheets, calculates portfolio risk and concentration metrics, generates an HTML risk narrative with OpenAI, then emails the full report via Gmail and appends an audit record back to Google Sheets. How it works Receives a portfolio analysis request from an n8n Form containing the investor details, base currency, and a Google Sheet ID. Reads all holdings from the provided Google Sheets document (Portfolio tab) and bundles the rows into a single portfolio dataset. Calculates market value, allocations, sector and asset-class breakdowns, P&L, concentration flags, and a 0–100 risk score. Sends the computed portfolio summary, breakdowns, risk flags, and holdings to OpenAI to generate a structured risk report in HTML. Builds a branded HTML email that includes the AI narrative plus sector and top-holdings tables and a concentration alert banner. Sends the HTML risk report to the investor via Gmail and appends a summary row to a Google Sheets “Analysis Log” audit sheet. Setup Create a Google Sheet with a tab named “Portfolio” and headers: ticker, company, sector, asset_class, quantity, avg_bu
Qualify inbound leads with OpenAI, Slack, and Google Sheets
Quick overview This workflow receives inbound leads via a webhook, normalizes common form fields, and uses OpenAI to score and tier each lead as HOT, WARM, or NURTURE. It logs the result to Google Sheets, sends a tier-specific email auto-reply, and alerts a Slack channel for HOT leads. How it works Receives an inbound lead submission via a POST webhook. Normalizes incoming fields (name, email, company, website, message, budget, timeline, and source) into a consistent structure. Sends the normalized lead details to OpenAI to generate JSON scores (fit, budget, urgency, overall), a tier, reasoning, next action, and red flags. Merges the AI qualification results back into the lead record and routes the lead based on the tier. For HOT leads, posts an alert to Slack, appends the lead to the “Hot Leads” tab in Google Sheets, and sends a HOT auto-reply email. For WARM and NURTURE leads, appends the lead to the matching Google Sheets tab and sends the corresponding tier-specific auto-reply email. Returns a JSON response to the webhook caller confirming success and the assigned tier. Setup Add an OpenAI credential and customize the system prompt ICP/scoring rules in the OpenAI step. Add Goog
WTurn Telegram into a French fitness coach with Claude, OpenAI and Google Sheets
Quick overview This workflow turns a Telegram chat into a French-speaking fitness and nutrition coach that can handle text or voice messages, use Anthropic for responses, log and read training/nutrition data in Google Sheets, and schedule workouts in Google Calendar. How it works Triggers when a new Telegram message is received. Detects whether the incoming message is a voice note and, if so, downloads it from Telegram and transcribes it with OpenAI. Normalizes the user message, chat ID, and current date fields for downstream processing. Uses an Anthropic chat model with short-term session memory to generate a coaching response and decide when to call tools. Reads from and writes to Google Sheets to fetch or update the user profile, log workouts and meals, retrieve daily nutrition totals, and create or update weekly training and nutrition plans. Optionally creates a workout event in Google Calendar when the user asks to schedule a session. Sends the generated response back to the user in Telegram. Setup Create and connect credentials for Telegram, Anthropic, OpenAI (for audio transcription), Google Sheets OAuth2, and Google Calendar OAuth2. Replace YOUR_SHEET_ID_HERE and select the
Create vertical AI videos from web articles with OpenAI, Seedance and Blotato
Quick overview This workflow accepts an article URL from Telegram, extracts the page text, uses OpenAI to generate a Seedance 2.0 video prompt plus platform-specific captions, creates a vertical video via the AtlasCloud Seedance API, then publishes it to TikTok, Instagram, and YouTube through Blotato and confirms back on Telegram. How it works Receives a message in Telegram containing a web article URL. Fetches the web page HTML, strips it to plain text, and truncates the extracted content for prompting. Uses OpenAI to turn the URL and extracted text into a Seedance 2.0 text-to-video prompt plus TikTok and Instagram captions and a YouTube title and description. Submits the generated prompt to the AtlasCloud Seedance 2.0 generateVideo API with the configured duration, resolution, and FPS. Polls the AtlasCloud prediction endpoint on a wait interval until the video status returns completed/succeeded. Publishes the resulting video URL to TikTok, Instagram, and YouTube via Blotato using the generated captions and YouTube metadata. Sends a Telegram confirmation message that includes the video title and the final video URL. Setup Create a Telegram bot with @BotFather, add Telegram credent
Triage telehealth appointments with GPT-4o-mini, Telegram, Google Calendar
Quick overview This workflow collects telehealth appointment details via an n8n Form, uses OpenAI (GPT-4o-mini) to score no-show risk, then sends Telegram reminders and confirmations and updates Google Calendar based on the patient’s response, with Slack alerts on workflow errors. How it works Receives a new appointment submission from an n8n Form with patient, appointment, and Telegram chat details. Sends the appointment data to OpenAI (GPT-4o-mini) to generate a 0–100 no-show risk score and explanation. Routes the flow based on the risk score, sending a single friendly Telegram reminder for low-risk patients. For high-risk patients, sends escalating Telegram reminders and a final message that waits for a confirmation or cancellation reply. If the patient cancels, creates a new “rescheduled” time slot in Google Calendar and sends the patient a Telegram reschedule acknowledgement. If the patient confirms, updates the existing Google Calendar event to note the confirmation and sends a Telegram confirmation message. If any step fails, posts an error notification to a Slack channel. Setup Add credentials for OpenAI (Chat), Telegram Bot, Google Calendar OAuth2, and Slack OAuth2 used fo
Score mortgage loan risk from Google Drive PDFs with OpenAI and Gmail
Quick overview This workflow monitors a Google Drive folder for new loan application PDFs, extracts text, and uses OpenAI (GPT-4o-mini) to structure applicant data, score risk, generate a lending summary, and produce an underwriting recommendation, then emails the final report via Gmail and posts Slack alerts on failures. How it works Triggers when a new PDF is created in a specified Google Drive folder. Downloads the PDF from Google Drive and extracts its text content. Uses OpenAI (GPT-4o-mini) to extract key applicant and loan fields into a validated JSON structure. Uses OpenAI (GPT-4o-mini) to calculate a risk score, risk level, approval confidence, and key findings in JSON. Uses OpenAI (GPT-4o-mini) to write a plain-text lending summary and then generate a final underwriting decision (approve/conditional approval/further review/decline) with reasoning and conditions. Assembles a single report from the extracted data, risk analysis, summary, and decision, and sends it to the loan officer via Gmail. If extraction or risk scoring fails, sends a Slack alert and retries by re-downloading the application PDF. Setup Connect Google Drive OAuth2 credentials and replace YOUR_GOOGLE_DRIVE
Recover overdue invoices with GPT-4o-mini, Gmail, Google Sheets and Slack
Quick overview This workflow runs every 24 hours to read overdue invoices from Google Sheets, uses OpenAI (GPT-4o-mini) to draft personalized recovery emails and determine escalation, sends emails via Gmail, logs outcomes back to Google Sheets, and posts status and error alerts to Slack. How it works Runs every 24 hours on a schedule trigger. Reads invoice rows from a Google Sheets “invoices” tab and checks whether there are any valid invoice entries to process. If no invoices are found, posts a “no overdue invoices” message to a Slack channel. For each invoice found, uses OpenAI (GPT-4o-mini) to assign an escalation level, draft a personalized HTML email (including payment plans when applicable), and recommend an escalation action. Parses the AI output into structured fields and sends the recovery email to the client via Gmail. If the AI recommends escalation, sends an internal escalation alert email to the legal team via Gmail. Updates the invoice row in Google Sheets with the new escalation level and AI summary, then appends a full audit log row to a “Recovery sheet” tab. If AI processing fails, posts an error alert to Slack and continues with the next invoice. Setup Add Google