AI Automation
923 sonuç — tümü kaynağa bağlı n8n referansı
Detect early payment invoice opportunities with Groq and Google Sheets
Quick Overview This workflow runs daily to fetch invoice data from an HTTP endpoint, calculate early-payment savings and annualized ROI, and use Groq (Llama 3.3) to prioritize eligible discounts. It logs eligible and expired invoices to Google Sheets and emails a digest of HIGH-priority recommendations via Gmail. How it works Runs every day at 9:00 to start an invoice scan. Fetches invoice records from an external HTTP API endpoint. Calculates potential savings, days saved by paying early, annualized ROI, and whether each invoice is still eligible before the discount deadline. Routes eligible invoices to Groq (Llama 3.3) to return a JSON decision with a YES/NO recommendation, HIGH/MEDIUM/LOW priority, and a short reason, then normalizes the AI response. Appends eligible invoice evaluations (including ROI, savings, priority, recommendation, and reason) to a Google Sheets log. Filters for invoices marked YES and HIGH priority, aggregates them into a daily batch, and emails a plain-text digest to the finance team via Gmail. Marks ineligible invoices as expired with a skip reason and appends them to a separate Google Sheets audit log. Setup Add a Groq API credential and ensure the sele
Triage supplier capacity risk with Groq, Gmail, Slack, and Google Sheets
Quick overview This workflow runs daily to pull supplier performance data from an HTTP endpoint, calculate fulfillment and delay risk metrics, use Groq (Llama 3.3) to classify supplier risk and generate mitigation actions, then notify via Gmail and Slack and log outcomes to Google Sheets. How it works Runs every day at the scheduled time. Fetches supplier performance data from an HTTP API and stops if the supplier has no orders. Normalizes the supplier fields and calculates fulfillment rate, delay, rule-based flags, and a risk score. Sends the metrics to Groq (Llama 3.3) to classify risk (Low/Medium/High) with a reason and confidence, then merges the AI result with the computed metrics (falling back to the rule-based classification if parsing fails). If the AI risk is Medium, Groq generates three mitigation actions and the workflow fetches backup supplier options from an HTTP API, then combines both into a single alert payload. Sends the mitigation actions by Gmail email and Slack message, then appends a “high risk” audit row to Google Sheets. If the AI risk is not Medium, appends a “no alert sent” audit row to Google Sheets with the assessed risk details. Setup Add Groq API creden
Handle WhatsApp sales inquiries with OpenAI, Pinecone, Google Calendar, and Slack
Quick overview This workflow handles inbound WhatsApp Business messages with an OpenAI-powered sales agent that uses Pinecone RAG for product answers and Google Calendar tools for scheduling, then either replies on WhatsApp or hands the conversation to Slack, with Slack-based error alerts. How it works Triggers on every inbound WhatsApp Business message and checks whether the payload contains a text body. Drops non-text messages (such as images or voice notes) and continues only with text conversations. Uses an OpenAI chat model with per-customer session memory to generate a concise sales reply and decide whether a human handoff is needed. Lets the agent query a Pinecone-backed product catalog via OpenAI embeddings to answer pricing, specs, and availability questions. Lets the agent check availability and book appointments in Google Calendar when the customer requests scheduling. Parses the agent’s HANDOFF flag and either posts the customer message plus draft reply to a Slack channel or sends the reply back to the customer on WhatsApp. Sends a Slack alert to an ops channel if any step in the workflow fails. Setup Connect WhatsApp Business Cloud credentials and set the WhatsApp Phon
Verify loan documents and score eligibility with Claude and Google Sheets
Quick overview This workflow receives loan applications via webhook, uses Anthropic Claude to verify document text and generate an underwriting recommendation, calculates an explainable risk score in code, logs each application to Google Sheets, and sends decision emails through SendGrid before returning a JSON response. How it works Receives a loan application via a POST webhook, including applicant details and extracted text from ID, income proof, and bank statement documents. Uses Anthropic Claude to extract key fields from the documents and cross-checks them against the applicant’s declared name, employer, and income to produce a verification score and inconsistency list. Stops early and returns a “Documents Insufficient” webhook response when the verification score is below the threshold. Calculates verified income, estimated monthly installment, debt-to-income and loan-to-income ratios, and a weighted 0–100 risk score and tier from credit score, ratios, employment tenure, bank health, and document consistency. Waits briefly, then uses Anthropic Claude to generate an eligibility recommendation (Approve, Conditional Approval, Manual Review, or Decline) with reasoning, condition
Create a Gmail morning audio briefing with Google Gemini and Google Drive
Quick Overview This workflow runs every weekday at 7 AM to fetch up to 10 unread Gmail messages from the last day, summarize them into a narrated script with Google Gemini, convert the script to an MP3 using Smallest.ai, upload it to Google Drive, and email you a public listening link. How it works Runs on a schedule every weekday at 7:00 AM. Pulls up to 10 unread Gmail emails from the last 24 hours. Cleans and categorizes the emails into URGENT, NEWSLETTERS, and OTHER sections while skipping common job-alert style messages. Uses a LangChain AI Agent powered by Google Gemini to turn the digest into a plain-text morning briefing script. Truncates the script to a safe character limit and converts it to speech as an MP3 with Smallest.ai. Uploads the MP3 to Google Drive, makes the file publicly readable, and sends a Gmail message with the listening link and the script text. Setup Connect your Gmail credentials for both reading unread emails and sending the briefing email, and update the recipient address in the outgoing email step. Add Google Gemini credentials in the Google Gemini Chat Model used by the AI Agent. Add your Smallest.ai API credentials for text-to-speech generation. Conn
Create narrated blog audio from RSS with Google Gemini, Smallest.ai and WordPress
Quick Overview This workflow polls a blog RSS feed, rewrites new posts into a spoken-word script using Google Gemini, generates an MP3 with Smallest.ai, uploads it to Google Drive, and updates the matching WordPress post to embed a public audio player. How it works Polls an RSS feed every minute to detect newly published or updated blog items. Extracts the post body and strips HTML, scripts, styles, and common entities to produce clean plain text. Uses Google Gemini to rewrite the text into a single, conversational narration script with an intro/outro and length limits. Sends the rewritten script to Smallest.ai to synthesize an English MP3 audio file. Uploads the MP3 to Google Drive and updates sharing so anyone with the link can play it. Updates the corresponding WordPress post to embed an HTML5 audio player pointing to the Google Drive link and includes the article text below it. Setup Set the RSS feed URL in the RSS Feed Trigger node and confirm the feed provides the fields used for the post content and GUID. Add credentials for Google Gemini (Google AI / Gemini) and select that connection in the chat model used by the rewrite step. Add your Smallest.ai API credentials and verif
Qualify leads and send personalized audio follow-ups with Gemini and Smallest.ai
Quick Overview This workflow receives lead submissions via a webhook, uses Google Gemini to qualify the lead and write a personalized spoken follow-up script, and for qualified leads generates an MP3 with Smallest.ai, shares it from Google Drive, emails it via Gmail, logs outcomes to Google Sheets, and alerts sales in Slack. How it works Receives a POST webhook request containing a lead’s name, email, and message. Sends the lead details to a Google Gemini–powered AI agent to determine whether the lead is qualified and, if so, generate a short personalized audio script. Parses the agent’s JSON response and routes the workflow based on the qualified flag. If the lead is qualified, Smallest.ai synthesizes the script into an MP3 and uploads it to Google Drive. Shares the Google Drive audio file publicly and sends the lead a Gmail message with a link to listen. Appends the qualified lead record (including the audio link and timestamp) to Google Sheets and posts a notification to a Slack channel. If the lead is unqualified, appends the lead details and timestamp to Google Sheets without generating audio or sending email. Setup Enable the webhook and copy the generated /lead-capture URL i
Transcribe and summarize Twilio calls with Smallest.ai, Gemini, Slack, and GoHighLevel
Quick Overview This workflow listens for completed Twilio call recordings, downloads and transcribes the audio with Smallest.ai, summarizes the transcript with Google Gemini, then notifies a Slack user and creates a new opportunity in GoHighLevel. How it works Triggers when Twilio Voice Insights reports a call summary as complete. Downloads the call recording audio from Twilio using the provided recording URL. Sends the audio file to Smallest.ai to generate a speech-to-text transcription. Uses a Google Gemini-powered AI agent to produce a short call summary, caller sentiment, and a suggested next step from the transcript and call metadata. Sends the generated summary to a specified Slack user. Creates a new opportunity in GoHighLevel that includes the caller number and AI summary. Setup Connect your Twilio credentials and ensure Twilio Voice Insights call summary events are enabled for your account. Add your Smallest.ai API credentials for the transcription step. Configure Google Gemini credentials in the LangChain Google Gemini chat model used by the AI agent. Connect your Slack credentials and set the target user (or change to a channel) for notifications. Connect your GoHighLeve
WSend Calendly meeting prep briefs with Gmail, Notion, OpenAI and Sheets
Quick Overview This workflow monitors Gmail for Calendly “New Event” emails, extracts meeting details with OpenAI, enriches the invitee with Notion CRM data, Google Sheets STR records, and SerpApi building research, then generates and schedules a meeting-prep brief email to send 30 minutes before the meeting. How it works Triggers every minute when a new Gmail message arrives and continues only if it is a Calendly notification for a new event. Uses OpenAI to extract the invitee email and meeting date/time from the email and calculates a send time 30 minutes before the meeting. Looks up the lead in a Notion database by invitee email and pulls building research via SerpApi, then uses OpenAI to extract building details from the AI Overview results. Loads STR registration data from Google Sheets and matches it to the building address to flag whether the property appears in STR records. Searches recent Gmail history in two accounts for messages involving the lead’s email address and checks whether any history exists. If email history exists, uses OpenAI to summarize the relationship and generate a concise meeting brief, then formats it as an HTML email. If no email history exists, uses
WTurn LinkedIn post reactions into AI content ideas with OpenAI and Google Sheets
Quick overview This workflow runs daily to fetch your recent LinkedIn post reactions via a RapidAPI LinkedIn endpoint, uses OpenAI to turn each reacted post into a structured original content idea, and appends or updates the results in a Google Sheets idea vault without duplicates. How it works Runs every day at 08:00 using a schedule trigger. Loads configurable settings like your LinkedIn username, reaction type filter, recency window, max posts to analyze, OpenAI model, and output language. Calls the linkedin-api8 RapidAPI endpoint to retrieve posts you recently reacted to and splits the response into individual reaction items. Filters reactions to keep only the selected reaction type (or all when blank) and posts newer than the configured number of days. Limits the number of reactions sent for analysis to control cost. Sends each source post (author, reaction, text, and URL) to OpenAI to generate a structured content idea (category, angle, hook, takeaway, format, and hashtags). Saves each idea to Google Sheets using an upsert that matches on Post URL to avoid duplicate rows. Setup Create a RapidAPI subscription for linkedin-api8 and add an HTTP Header Auth credential that sends
Analyze YouTube comments with OpenAI, Google Sheets, and Gmail
Quick overview This workflow monitors a Google Sheets list of YouTube video IDs, fetches video details and top comments from the YouTube Data API, analyzes the comments with OpenAI into structured sentiment and themes, emails an HTML report via Gmail, and writes the results back to Google Sheets. How it works Triggers every minute when a row in Google Sheets is added or updated. Reads the video ID and status from the row and continues only if the status is set to “Pending”. Calls the YouTube Data API to fetch the video’s metadata and the top comment threads for that video. Flattens the comment threads, calculates basic stats (comment count and average likes), and compiles a limited comment text block for analysis. If comments exist, sends the compiled comments and video title to OpenAI to generate a structured analysis (sentiment score, sentiment breakdown, themes, questions, feedback, insights, and summary). Builds an HTML email report from the structured results, sends it to the configured recipient with Gmail, and updates the Google Sheet row with the analysis fields; if no comments exist, marks the row as “No comments”. Setup Create or duplicate a Google Sheet with at least “Vi
Audit landing page CRO and log results with OpenAI and Data Tables
Quick overview This workflow collects a landing page URL, scrapes its HTML, and uses OpenAI to generate a structured conversion-rate-optimization (CRO) audit with scores and prioritized tips, then renders a styled report in the browser and logs each audit to an n8n Data Table. How it works Presents an n8n Form where the user submits a landing page URL. Fetches the landing page HTML via an HTTP request with retries, and routes to an error page if the URL can’t be retrieved. Sends the scraped HTML and URL to OpenAI to produce a CRO audit including an overall score, category scores, a written roast, and a ranked list of optimization tips. Uses a structured output parser with an OpenAI “fixer” model to validate and auto-correct the AI response into the required JSON schema. Builds a styled HTML report from the structured audit results. Logs the audit metadata (URL, score, verdict, summary, language, timestamp) to an n8n Data Table and displays the report back in the user’s browser. Setup Add an OpenAI API credential and select it for both the main OpenAI model and the output-fixer model. Create or select an n8n Data Table (for example, “CRO Audit Log”) and map the columns used for url,
Enrich company records with social media links using GPT-4o and Supabase
Quick overview This workflow is manually triggered to pull company names and websites from Supabase, crawl each site with an OpenAI-powered agent to extract social media profile URLs, and write the enriched results to a separate Supabase table. How it works Runs when you manually execute the workflow. Reads all rows from the Supabase companies_input table and keeps the name and website fields for processing. Uses an OpenAI (GPT-4o) agent to crawl the company website, following discovered links and extracting social media profile URLs. Forces the agent output into a structured JSON schema and maps the extracted links into a social_media array. Merges the original company name and website with the extracted social media data. Inserts the enriched record into the Supabase companies_output table. Setup Add a Supabase credential and set the correct project details for both reading from companies_input and writing to companies_output. Add an OpenAI API credential for the GPT-4o chat model used by the crawling agent. Ensure your input table has name and website fields or update the field selection and mapping to match your schema. Confirm the output table accepts the mapped fields (for ex
CAnswer WooCommerce order and DHL tracking questions with GPT-4 chat
Quick overview This workflow serves a demo web page with an n8n chat widget and runs an OpenAI-powered support agent that looks up WooCommerce orders and DHL tracking details by calling the same workflow as a tool. How it works Serves a demo HTML page via a webhook that embeds the n8n Chat widget configured to start a chat session. Triggers a new conversation when the chat widget connects and provides a customer email (mocked in this template) as session metadata. Uses an OpenAI (GPT-4) chat model with short-term memory to answer order-related questions and decide when to fetch live order data. Calls the same workflow as a tool with the customer email (and optional comma-separated order IDs) to retrieve matching WooCommerce orders. Looks up the WooCommerce customer by email, fetches their orders, and extracts shipment tracking metadata from each order. For orders with DHL tracking numbers, queries the DHL API for current shipment status, then merges tracking results back into the order data. Returns a JSON response containing the customer’s orders and any available DHL tracking details to the agent for use in the chat reply. Setup Add a WooCommerce API credential and update the sto
C
Summarize Zoom meetings and create follow-ups with OpenAI, ClickUp, and Outlook
Quick overview This workflow pulls the transcript and participant list from a recent Zoom meeting, uses OpenAI to generate formal meeting minutes, emails the summary via SMTP, and runs an AI agent that creates ClickUp tasks and (when details exist) schedules a follow-up meeting in Microsoft Outlook Calendar. How it works Starts when you manually run the workflow. Fetches your scheduled Zoom meetings and keeps only those that started within the last 24 hours. Requests the meeting recording files from Zoom, stops with an error if no transcript is available, then extracts the transcript download URL. Downloads the Zoom transcript file, extracts its text, and reformats it into clean, readable dialogue. Pulls the Zoom meeting participant list (including emails) and sends the transcript and participants to OpenAI to generate structured meeting minutes. Formats the minutes into an HTML email and sends the summary via SMTP to a participant email address. Uses an OpenAI-powered agent to extract action items and follow-up details from the same transcript, then creates tasks in ClickUp and creates a follow-up event in Microsoft Outlook Calendar when scheduling information is present. Setup Ad
Qualify voicemail leads with Twilio, Google Gemini, Gmail and Google Sheets
Quick overview When a buyer or seller leaves a voicemail, this workflow transcribes it automatically, qualifies their intent using Gemini AI, sends an instant SMS acknowledgment, and alerts the agent for Hot leads — turning every missed call into a qualified lead within seconds. How it works Receives a POST webhook from Twilio when a voicemail recording and transcription are completed. Validates the voicemail by checking that the recording is completed, the transcription is completed, and the call duration is longer than 5 seconds. Extracts the transcript, caller phone number, call SID, duration, and recording URL, then sends the transcript to Google Gemini to return structured lead details, a Hot/Warm/Cold score, and draft SMS/email replies. Parses and sanitizes the Gemini JSON output, applies fallbacks if parsing fails, optionally appends a Google Calendar booking link for Hot leads, and builds an agent-ready HTML summary including the transcript and recording link. Sends an acknowledgment SMS to the caller via Twilio, and sends an acknowledgment email via Gmail only when a caller email address is available. Appends the lead details, transcript, and messaging status to a Google S
WSend weekly blended ad performance reports with Meta Ads, Google Ads, GA4 and OpenAI
Quick overview This workflow runs every Monday at 8am, pulls last-7-days performance data from the Meta Ads API, Google Ads API, and Google Analytics 4, calculates blended KPIs, uses OpenAI to generate a client-friendly insight summary, and delivers an HTML report by Gmail while posting status update to Slack. How it works Runs every Monday at 8am on a schedule trigger. Fetches the last 7 days of spend and engagement metrics from the Meta Ads Insights endpoint. Fetches the last 7 days of campaign cost, clicks, and conversions from the Google Ads API using a streamed search query. Fetches the last 7 days of conversions and revenue by default channel group from the Google Analytics 4 Data API. Combines the three datasets and calculates blended totals for spend, conversions, revenue, and ROAS. Sends the blended metrics to OpenAI to generate a 3–4 sentence plain-language weekly performance summary. Builds a simple HTML report and sends it to the client via Gmail while posting a short “report sent” summary to a Slack channel. If the workflow execution fails, posts the error message to an ops Slack channel. Setup Add credentials and replace the placeholders for your Meta Ads token and ad
Recommend supplier consolidation with Google Sheets, Groq, Slack and Gmail
Quick overview This workflow runs weekly to read supplier spend data from Google Sheets, detect overlapping suppliers across departments, estimate potential consolidation savings, and use Groq-hosted LLM analysis to assess risk and produce recommendations that are sent to Slack and emailed via Gmail. How it works Runs every week on a scheduled trigger. Reads supplier records from a Google Sheets spreadsheet and keeps key fields like supplier name, department, spend, risk rating, and stakeholder email. Groups and normalizes supplier names to find suppliers used by multiple departments and calculates estimated savings and an opportunity level. Sends each consolidation opportunity to a Groq chat model to evaluate risk versus savings and return a JSON decision and recommendation. Parses the AI JSON output, merges it with the calculated savings data, and formats a final recommendation record. Posts the recommendation to a Slack channel and emails a formatted report to the supplier stakeholder email address. Setup Connect your Google Sheets OAuth account and update the spreadsheet ID and sheet/tab to match your supplier records. Add a Groq API credential for the chat model used to evalua
Score and triage inbound leads with Groq, Slack, Google Sheets, and Google Tasks
Quick Overview This workflow captures leads via an n8n form, stores them in an n8n Data Table, uses a Groq Llama 3.3 chat model to score and categorize each lead and draft a reply, optionally alerts in Slack and creates a Google Task, and writes the results back to the Data Table. How it works Receives a new lead submission through an n8n Form trigger (name, email, company, source, and message). Saves the submitted lead into an n8n Data Table and keeps only the fields needed for scoring. Sends the lead details to a Groq Chat Model via an AI Agent to generate a JSON response with a score (1–100), tier (Hot/Warm/Cold), and a suggested reply. Uses the AI Agent’s tool actions to post an alert to Slack and create a task in Google Tasks only when the lead’s score is above the defined threshold. Parses the AI Agent output as JSON and updates the original Data Table row with the generated score, tier, and reply. Setup Configure the n8n Form trigger and embed or share its URL where you collect leads. Create or select an n8n Data Table for leads and ensure it includes columns for score, tier, reply, and an id used to match rows during updates. Add a Groq API credential and select the Groq ch
Extract and validate invoice data from Google Drive using OCR.Space, Gemini, and Google Sheets
Quick overview This workflow monitors a Google Drive folder for newly uploaded invoice files, extracts text with OCR.Space, uses Google Gemini to convert the OCR text into structured invoice fields, validates required values, then stores results in Google Sheets and sends Gmail notifications for success or manual review. How it works Triggers when a new file is created in a specified Google Drive folder. Downloads the uploaded invoice file from Google Drive and checks that the MIME type is PDF, JPG, JPEG, or PNG. Sends the file to the OCR.Space API to extract the invoice text and stops if OCR reports a processing error. Uses Google Gemini to convert the OCR text into structured JSON containing supplier, invoice metadata, amounts, currency, and line items. Validates and normalizes the extracted fields, flags missing required values, and marks the record for manual review when needed. If manual review is required, sends a Gmail alert listing missing fields; otherwise, appends key invoice fields to Google Sheets and sends a Gmail confirmation email. Setup Connect Google Drive OAuth2 credentials and set the folder ID to watch for invoice uploads. Provide an OCR.Space API key and ensure
Route supplier risk alerts from Gmail to Slack with Gemini and Google Sheets
Quick overview This workflow monitors incoming Gmail messages from suppliers, uses Google Gemini to analyze sentiment and relationship risk, generates an engagement strategy for risky emails, sends an alert to Slack, and logs the analysis and recommended response to Google Sheets. How it works Triggers every minute by checking Gmail for new incoming emails. Filters out irrelevant messages (for example newsletters, unsubscribe emails, no-reply senders, and auto-replies) and keeps only valid supplier emails. Extracts the sender, subject, and email snippet into a single text block and waits briefly to buffer processing. Sends the email text to Google Gemini to return a structured JSON analysis with sentiment score/label, intent, urgency, key concern, and deterioration risk, then normalizes these fields and derives a trend. Flags the interaction as high risk based on the deterioration risk value or a low sentiment score and waits briefly before continuing. Uses Google Gemini to generate a concise engagement strategy (recommended action, draft opening message, and follow-up timeline), then parses it and formats a Slack-ready alert. Sends the alert to a selected Slack user and appends th
CWRoute insurance quote leads with OpenAI, Airtable, Sheets, Teams, Slack and Twilio
Quick overview This workflow receives insurance quote submissions via a webhook, normalizes and deduplicates them against Airtable and/or Google Sheets, uses OpenAI to score and classify the lead, then routes hot/warm leads to Microsoft Teams and/or Slack (plus Twilio SMS for hot leads) and logs the quote. How it works Receives an insurance quote request through a webhook endpoint. Applies configurable settings (log destination, notification channels, thresholds) and normalizes the incoming form payload into a standard quote format. Checks Airtable and/or Google Sheets for recent matching email/phone/hash entries to detect duplicate submissions. If the quote is new and has contact details, sends the quote data to OpenAI to generate a lead score, priority, underwriting flags, missing info, and recommended next steps. Routes the quote as hot, warm, or cold based on the score/priority and prepares formatted alert messages for Microsoft Teams and Slack. Posts hot/warm alerts to Microsoft Teams and/or Slack, and sends a Twilio SMS to an agent for hot leads. Creates a quote log record in Airtable and/or appends a row to Google Sheets, then returns a JSON response with logging and notific
Schedule weekly focus-time blocks with Google Calendar, OpenAI, and Slack
Quick overview This workflow runs every Sunday at 18:00 to scan your Google Calendar for next week, find free gaps of at least two hours within your working hours, auto-book them as “🧘 Focus Time” events, and then DM you a personalized deep-work plan in Slack using OpenAI. How it works Runs every Sunday at 18:00 on a schedule. Loads your working-hour preferences and fetches all events from your Google Calendar. Calculates weekday-only free gaps within your working hours and keeps only gaps that meet the minimum block length. If no qualifying gap exists, sends you a Slack DM warning that next week is too fragmented for a focus block. If gaps exist, limits the number of blocks for the week and creates “🧘 Focus Time (protected by n8n)” events in Google Calendar for each selected slot. Uses OpenAI to generate a short, personal Slack message that lists the protected blocks and suggests what kind of work fits each. Sends the generated deep-work plan to you as a Slack DM. Setup Add Google Calendar credentials, select the calendar to read from and the calendar to create “🧘 Focus Time” events in. Add Slack credentials and set your target Slack username in both the plan DM and warning mes
Extract Twilio voice donation details with Groq, Gemini, and Google Sheets
Quick overview This workflow receives Twilio call recording callbacks, transcribes the audio with Groq Whisper, uses Google Gemini/Groq LLMs to extract structured donation details, and appends the results (with transcript and review flag) to Google Sheets. How it works Receives a Twilio Recording Status Callback webhook and immediately responds with TwiML (``). Captures call metadata (CallSid, caller number, recording URL/SID, and duration) and continues only if the recording exists and is at least 2 seconds long. Waits briefly for Twilio to finalize the media, then downloads the recording MP3 using Twilio HTTP Basic Auth. Sends the audio file to Groq’s Whisper transcription endpoint to generate a text transcript. Uses a LangChain prompt with Google Gemini and Groq chat models to extract donation amount, fee (if mentioned), beneficiary name, currency, a needs-review flag, and a short summary from the transcript. Parses the model output as JSON and falls back to an error summary with needs_review=yes if parsing fails. Checks Google Sheets for an existing row matching the CallSid/RecordingUrl and, if not found, appends a new row with the extracted fields, transcript, and call details