Marketplace
3,557 ready-made workflow files you can download, plus 10,661 source-linked n8n references.
Capture and deduplicate inbound leads with webhooks and Google Sheets
Quick overview Capture inbound leads via webhook, validate and sanitize the data, deduplicate against Google Sheets, and store only clean leads ready to feed an AI-powered email/SMS nurture sequence. How it works Webhook receives the lead POST request from any form builder or landing page. Validation Missing email or phone returns a 400 and stops execution. Sanitize & normalize Trims whitespace, lowercases email, normalizes phone to international format, sets lead stage to 1, fills defaults for optional fields. Dedupe check Looks up the email in Google Sheets; flags duplicates safely even when the sheet returns zero rows. Duplicate → 200 "Already Registered", execution ends. New lead → appended to Sheets, 200 "Lead Accepted" returned. Setup Import all 4 workflows they share one Google Sheet. Create a sheet with these exact headers: Name, Email, Phone, Stage, Next Followup At, Has Replied, Lead Source, Service of Interest, SMS Consent Connect Google Sheets OAuth2 in the Lookup and Append nodes; paste your Sheet ID/tab into the 🔧 CONFIG nodes. Copy the webhook URL into your form builder. Map fields to: name, email, phone, lead_source, service_of_interest, sms_consent Requirements Go
Classify workflow errors with Claude and deduplicate Jira and Slack alerts
Quick overview This global error-handling workflow classifies n8n execution failures with Anthropic Claude, deduplicates incidents in Jira using a hash label, and posts a detailed alert to Slack with links to the affected execution and Jira issue. How it works Triggers whenever any n8n workflow execution or trigger fails (when set as the instance Error Workflow). Normalizes the error event into a consistent payload that includes workflow details, error message, truncated stack trace, and an execution log URL. Sends the normalized payload to Anthropic Claude to return a structured JSON classification (category, severity, root cause, recommended action, and transient flag). Parses the classification, falls back to an UNKNOWN classification if the LLM response is invalid, and generates a deduplication hash used to group similar errors. Searches Jira for an open issue in the configured project that already has the matching deduplication label. If an open issue exists, appends a recurrence comment with the latest execution details; otherwise, creates a new Jira Bug with labels, priority, and a full incident description. Builds a Slack Block Kit message summarizing the incident and sends
WExtract and validate invoice PDFs with OpenAI, Google Sheets, and Gmail
Quick overview This workflow collects an invoice PDF via an n8n Form, extracts text from the PDF, uses OpenAI to convert it into structured invoice JSON, logs invoice headers and line items to Google Sheets, validates totals, and emails a formatted extraction report via Gmail. How it works Receives an invoice submission through an n8n Form that includes the uploader’s name, email address, currency, notes, and a PDF file. Extracts text content from the uploaded PDF. Sends the extracted text to OpenAI (Chat Completions) to return invoice fields and all line items as a strict JSON object. Parses and validates the returned JSON, enriching it with the form metadata and stopping the run if key fields (like invoice number or line items) are missing. Appends a single invoice “header” row to the Invoices tab in Google Sheets. Splits the extracted line items, adds per-line metadata and a unique key, and appends each line item as a row to the Line Items tab in Google Sheets. Aggregates all line items, verifies that their summed totals match the invoice total within a tolerance, builds an HTML report, and emails it to the submitter via Gmail. Setup Add an OpenAI API credential and ensure the O
Generate an FAQ MP3 library from form input with OpenAI TTS, Google Drive, Sheets and Gmail
Quick overview This workflow collects up to five FAQ questions and answers from an n8n Form, converts each entry to an MP3 using OpenAI text-to-speech, uploads the files to Google Drive, logs links in Google Sheets, and emails a summary with listen and download links via Gmail. How it works Receives an n8n Form submission containing the requester’s email, a FAQ category, and up to five question-and-answer pairs. Splits the submitted FAQ pairs into individual items, generating a TTS script and a safe MP3 filename for each valid question and answer. Calls the OpenAI Audio Speech API (tts-1) to generate an MP3 file for each FAQ script. Uploads each generated MP3 to a specified Google Drive folder. Builds Google Drive view and direct-download URLs for each uploaded file and appends the FAQ details and links to a Google Sheets tab. Aggregates all processed FAQs into a single HTML summary and sends it to the submitter via Gmail with listen and download links. Setup Add an OpenAI API credential for the HTTP request to the OpenAI Audio Speech endpoint. Create (or choose) a Google Drive folder for the audio files, connect Google Drive OAuth2, and replace YOUR_AUDIO_FOLDER_ID with the target
Trigger Coolify deployments from new Docker Hub and GHCR image digests
Quick overview 🔄 Monitor Container Images from Docker Hub or GHCR. This workflow checks Docker Hub or GitHub Container Registry (GHCR) image tags for new digests. When an update is detected, it calls your Coolify API to restart the mapped service so the latest image is deployed. How it works Runs on a schedule to check for new image versions automatically. Loads configured Docker Hub image tags and their matching Coolify service UUIDs, then checks Docker Hub for each tag’s current digest. Skips Docker Hub digests already seen in previous workflow executions and prepares standardized metadata for any new digests. Loads configured GHCR image tags and their matching Coolify service UUIDs, fetches a GHCR auth token, and then retrieves each tag’s current OCI digest from the response headers. Skips GHCR digests already seen in previous workflow executions and prepares standardized metadata for any new digests. Combines new updates from both registries and calls the Coolify “restart service” endpoint for each matching service UUID (with latest image enabled). Setup Add an HTTP Bearer Auth credential for your Coolify API token and replace https://your-coolify-instance.com and the endpoint
WLog Strava zone 2 and 5K test runs to Google Sheets
Quick overview This scheduled workflow pulls your latest running activities from Strava, classifies them as Zone 2 runs or 5K tests based on pace and distance, and writes the formatted results into specific cells in a Google Sheets training log while tracking processed activity IDs. How it works Runs on a daily schedule. Fetches recent activities from the Strava API for the authenticated athlete. Processes each activity to calculate pace (min/km) and routes it into “Zone 2” or “Test Run” based on sport type, duration, pace, and distance rules. Formats the selected activities into sheet-ready fields (date, pace string, moving time, and distance) and labels them as ZONA 2 or TEST 5KM. Reads the target Google Sheets range to find the next available slots and checks an “IDs Registrados” list to avoid reprocessing activities. Updates Google Sheets with the activity details in the appropriate cycle columns and appends new Strava activity IDs to the “IDs Registrados” cell. Setup Connect your Strava OAuth2 credentials and ensure the athlete has permission to read activities. Connect your Google Sheets OAuth2 credentials and update the spreadsheet URL/ID and sheet (tab) selection used for r
Handle clinic appointments via MCP tools for Vapi and Retell voice agents
Quick overview This workflow exposes appointment management tools through an n8n MCP Server webhook so an external AI voice agent (for example, Vapi or Retell) can check availability, book appointments, suggest alternate slots, and cancel or reschedule existing bookings. How it works Receives an MCP tool request via the MCP Server Trigger webhook endpoint. When asked to verify a requested date and time, calls the “Check Slot Availability” sub-workflow to confirm whether the appointment slot is open. If the slot is available and caller details are confirmed, calls the “Book Appointment” sub-workflow to create the appointment. If the slot is unavailable, calls the “GET Alternate Slot” sub-workflow to return alternative available appointment times. For changes to existing bookings, calls either the “Cancel Appointment” or “Reschedule Appointment” sub-workflow using the caller’s phone number and appointment details. Setup Configure your external AI voice agent (for example, Vapi or Retell) to connect to this workflow’s MCP webhook URL and send tool requests to it. Publish and configure the referenced sub-workflows (“Check Slot Availability”, “Book Appointment”, “GET Alternate Slot”, “C
Enrich CRM contacts in Google Sheets with Tomba firmographic data
Quick overview This workflow watches a Google Sheets contacts list for new rows and enriches each contact using Tomba to find a likely email address, company firmographics, and a phone number, then writes the enriched fields back to the same spreadsheet. How it works Triggers when a new row is added to a specified Google Sheets worksheet (polled every minute). Processes new contacts one at a time to control throughput. Uses Tomba to find an email address for the contact based on the provided domain, company, and name. Uses Tomba to enrich the company with firmographic details such as industry, company size, revenue, and location. Uses Tomba to look up a company phone number from the contact’s domain. Combines the enrichment results into a single contact record and sets a status like “Enriched” or “Not Found.” Updates the matching row in Google Sheets with the enriched Email, Phone, Industry, Company Size, Revenue, Country, and Status fields. Setup Connect Google Sheets credentials and select the target spreadsheet and worksheet to monitor. Add Tomba API credentials to each Tomba step used for email, company, and phone enrichment. Ensure your Google Sheet includes the destination co
Track and notify lead callbacks with Tomba, Google Sheets, and Slack
Quick overview This workflow receives new lead details via a webhook, looks up a company phone number with Tomba using the lead’s domain, updates a Google Sheets lead tracker, and sends a formatted callback alert to a Slack channel. How it works Receives lead data in a POST webhook request. Processes incoming leads in batches to handle multiple items safely. Uses Tomba to find a phone number for each lead based on the provided company domain. Formats the lead details and enrichment results into tracker fields and a Slack-ready message. Updates the matching lead row in Google Sheets (matched by Domain) with the phone, status, and “Slack Notified” flag. Posts the callback alert message to a selected Slack channel and continues until all leads in the batch are handled. Setup Configure the source system to send lead payloads to the workflow’s webhook URL (path: /GHL) with fields like Full name, Email, Company name, and Company domain. Add your Tomba API credentials to enable phone lookup by domain. Connect your Google Sheets credentials and set the target spreadsheet and sheet, ensuring columns like Domain, Phone, Status, and Slack Notified exist. Connect your Slack credentials and cho
W
Index and query financial documents with Qdrant and Mistral
Quick Overview This workflow ingests local financial documents into a Qdrant vector database using Mistral Cloud embeddings, keeping the index in sync when files are added, changed, or deleted. How it works Runs when you manually start the workflow (for testing) and sets the working folder path and Qdrant collection name. Routes the run based on whether a file was added, changed, or deleted. For changed or deleted files, searches Qdrant for existing vectors matching the file path and deletes the corresponding points. For added files (and changed files after cleanup), reads the file from disk and prepares a text payload that includes file metadata and contents. Splits the text into chunks, generates embeddings with Mistral Cloud, and inserts the vectors into the specified Qdrant collection. Setup Create a Qdrant API credential in n8n and ensure your Qdrant instance is reachable at the host/port used in the HTTP requests (for example, http://qdrant:6333). Add a Mistral Cloud API key credential for the Mistral embeddings node. Update the folder path in the variables (for example, /home/node/BankStatements) and make sure n8n has filesystem access to that directory. Create (or update) t
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
Detect visual regressions with Apify, Google Gemini, Sheets and Linear
Quick overview This workflow generates baseline website screenshots with Apify, stores them in Google Drive, and logs the file IDs in Google Sheets, then runs scheduled visual regression checks by comparing new screenshots against the baselines with Google Gemini Vision and creating a consolidated Linear issue when changes are detected. How it works Manually starts to backfill missing baselines by reading URLs from Google Sheets that do not yet have a stored base image. For each missing baseline URL, calls Apify’s screenshot actor, downloads the rendered image, uploads it to Google Drive, and updates the matching Google Sheets row with the Drive file ID. Runs weekly on a schedule and reads the list of webpages to test from Google Sheets. For each webpage, downloads the baseline image from Google Drive and captures a fresh screenshot via Apify. Sends both images to Google Gemini (vision) to detect visual differences and returns a structured list of regressions (text, number, image, color, or position). Filters out pages with no detected changes, aggregates the remaining results, and creates a Linear issue containing the regression report. Setup Add an Apify API token as HTTP Query A
Sync Google Drive documents to Pinecone RAG with Google Gemini embeddings
Quick overview This workflow runs on a schedule to sync files from a Google Drive folder into a Pinecone vector index for RAG, extracting text from PDFs, XLSX, Google Docs, and spreadsheets, generating embeddings with Google Gemini, and tracking file state in a Google Sheets log to handle updates and deletions. How it works Runs on a schedule and fetches the current file list from a target Google Drive folder and the existing file log from Google Sheets. Compares Google Drive files with the Google Sheets log to detect new/updated files to ingest and files that were deleted from Drive. For new or updated files, deletes any existing vectors in Pinecone for the file ID, downloads the file from Google Drive, and routes it by MIME type. Extracts text from PDFs, XLSX/Google Sheets, and plain text/Google Docs files and maps the extracted content with file metadata (file ID, name, modified time, and MIME type). Chunks the document text, generates embeddings with Google Gemini, and inserts the resulting vectors and metadata into a Pinecone index. Appends or updates the Google Sheets log with the latest file metadata, and for deleted Drive files it deletes matching vectors in Pinecone and re
WSend daily SEO digest from Google Search Console to Discord with heartbeat alerts
Quick overview This workflow runs daily to pull Google Search Console performance data, log it to Google Sheets, send a daily SEO digest to Discord with day-over-day deltas, and ping an external heartbeat endpoint; if any step errors, it immediately pings the heartbeat service’s /fail endpoint. How it works Runs every day at 08:00 on a schedule trigger. Queries the Google Search Console Search Analytics API for query-level data from two days ago. Aggregates the results into totals (clicks, impressions, average position) and the top queries. Appends the day’s metrics to Google Sheets and reads the sheet to fetch the previous day’s row for comparison. Calculates percentage changes vs yesterday and sends a formatted SEO digest to Discord, including a warning when clicks drop sharply. Posts a success ping with the key metrics to an external heartbeat service (for example, checkilo or Healthchecks.io) so missing runs can be detected. If any node throws an error, an error-triggered branch posts a /fail ping to the heartbeat service with the error message and failing step. Setup Add a Google OAuth2 credential with the https://www.googleapis.com/auth/webmasters.readonly scope and replace 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
Label incoming Gmail messages with Google Gemini and Telegram alerts
Quick overview This workflow polls Gmail for new emails, uses Google Gemini via an n8n AI text classifier to categorize each message by subject and snippet, and automatically applies the matching Gmail label, sending a Telegram alert if classification errors occur. How it works Checks Gmail every minute for new emails using the Gmail Trigger. Sends the email subject and snippet to a Google Gemini-powered text classifier to assign a category (Personal, Job, Study Related, Bank, Social, OTP, or Misc). Adds the corresponding Gmail label to the message in Gmail based on the predicted category. Sends a Telegram message to the configured chat ID if the classifier step produces an error. Setup Connect your Gmail account using Gmail OAuth2 and ensure the trigger has access to the mailbox you want to label. Add a Google Gemini (PaLM) API key credential for the AI classification step. Create (or choose) the target Gmail labels and replace the label IDs in each “addLabels” action with your own. Add Telegram bot credentials and set the correct chat ID in the Telegram message step (or disable it if you don’t want error alerts).
Build hospitality lead lists from Booking.com using Apify and Google Sheets
Quick Overview This workflow uses Apify and Google Sheets to find accommodation leads from Booking.com, enrich them with Google Maps contact details, discover official websites via Google Search, scrape additional contacts from those sites, and then append the finalized partner list to a Google Sheets spreadsheet. How it works Manually triggers and sets the destination, maximum number of results, and property type to search. Runs the Apify Booking Scraper actor for the configured destination and retrieves the Booking.com dataset results. Maps each Booking.com result into a normalized lead record, using Booking trader details (when available) for initial email and phone fields. Runs the Apify Google Maps with Contact Details actor for leads missing email and merges any найден emails, phones, websites, and social links into the lead records. For leads still missing both email and website, runs the Apify Google Search Scraper actor to find an “official website” candidate and assigns the best non-OTA domain. Scrapes those candidate websites with the Apify Contact Info Scraper actor to extract emails/phones/socials and merges the results into the final lead rows. Appends the finalized l
WSummarize unread Gmail into a daily Slack digest with Claude
Quick overview This workflow runs on a daily schedule, pulls your unread Gmail from the last 24 hours, and uses Anthropic Claude to sort and summarize it by Gmail category — then posts a clean, triage-ready digest to a Slack channel so you can scan your inbox at a glance. How it works Runs automatically on a daily schedule (default 8am). Fetches up to 50 unread emails from Gmail that arrived in the last 24 hours. A Code node combines them into a single prompt block, tagging each message with its Gmail category (Primary, Promotions, Social, Updates, Forums) and flagging multi-message threads. Anthropic Claude turns that into a concise, Slack-ready digest: active threads flagged at the top, Primary mail listed individually with a needs-reply note, and Promotions/Social condensed to a single count. A Code node extracts the summary text from Claude's API response. The digest is posted to your chosen Slack channel. Setup Connect a Gmail OAuth2 credential to the Gmail node, and adjust the search query (e.g. is:unread newer_than:1d) or 50-email limit if needed. Add your Anthropic API key as an HTTP Header Auth credential named x-api-key, used for requests to https://api.anthropic.com/v1/m
Generate personalized franchise PDF letters from Excel with Google Drive and Docs
Quick overview This workflow collects an uploaded XLSX list of franchise owners via an n8n form, then uses Google Drive and Google Docs to generate a personalized letter for each row and saves the resulting PDF files back to a Google Drive folder. How it works Receives a form submission with an uploaded .xlsx file containing franchise owner details. Extracts rows from the Excel file into individual items. Iterates through each row in batches to process one franchise record at a time. Copies a Google Docs template in Google Drive and names the new document using the franchise name. Replaces placeholders in the copied Google Doc (owner, franchise, city, fee, and today’s date) with values from the current Excel row. Downloads the updated Google Doc as a PDF. Uploads the generated PDF to the target Google Drive folder and continues until all rows are processed. Setup Connect Google Drive OAuth2 credentials and set the template file ID and destination folder in the Google Drive copy/upload steps. Connect Google Docs OAuth2 credentials and ensure the template contains the placeholders (for example: [Dear Owner], [Franchise], [City], [Fee], [Date Today]). Ensure the uploaded XLSX has colu
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
Send weekly narrative client reports with Google Sheets, Claude, and Gmail
Quick overview This workflow runs every Friday at 9:00 AM, pulls active client status data from Google Sheets, uses Anthropic Claude to generate a narrative weekly report with structured HTML and plain text output, and sends the finished report to each client via Gmail. How it works Runs every Friday at 9:00 AM on a schedule trigger. Reads all client rows from a specified Google Sheets document. Filters out paused/inactive or incomplete rows, extracts any “Metric:” columns, and builds a reporting week label for each client. Sends each client’s normalized data to Anthropic Claude to write a 3–4 paragraph narrative report and return JSON containing an email subject plus HTML and plain-text bodies. Emails the generated HTML report to each client’s email address using Gmail. Setup Create a Google Sheet with the required columns (at minimum “Client Name” and “Client Email”) and optional “Status” plus any “Metric:” columns you want included. Add Google Sheets OAuth2 credentials in n8n and replace the placeholder Sheet ID in the Google Sheets read step. Add an Anthropic credential for the Claude chat model used to generate the structured report. Add Gmail OAuth2 credentials and confirm th
CScore and route inbound leads with Claude, Airtable, Slack, and Gmail
Quick overview This workflow receives inbound form leads via a webhook, normalizes the submission, optionally scrapes the lead’s website with Jina AI Reader, and uses Anthropic Claude to score and summarize the lead. It logs results to Airtable, posts a Slack alert, and creates a Gmail draft for hot leads. How it works Receives a POST webhook when a new lead submission comes in and immediately returns a JSON receipt response. Normalizes the incoming payload (Typeform, Tally, JotForm, or custom JSON) into consistent lead fields like name, email, company, website, and message. If a website is provided, fetches up to 2,000 characters of page content using Jina AI Reader and attaches it to the lead. Sends the lead details and scraped content to Anthropic Claude to produce structured JSON including a score, tier (hot/warm/cold), red flags, an enriched summary, and a first-reply draft. Builds a formatted Slack message and prepares a complete lead record (including routing flags) from the AI output. Creates a new record in Airtable and posts the lead alert to a Slack channel. If the lead is classified as hot, creates a Gmail draft using the generated first-reply text. Setup Copy the webho
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