HTTP Request workflow'ları
1.200 sonuç — 3 indirilebilir workflow dosyası, 1.197 kaynağa bağlı n8n referansı
Assess visa eligibility and send PDF checklists with Claude and SendGrid
Quick overview This workflow receives visa eligibility requests via webhook, uses Anthropic Claude to extract passport details and assess visa requirements, generates a purpose-specific document checklist, converts it to a PDF via PDFShift, logs each request to Google Sheets, and emails the PDF to the applicant using SendGrid. How it works Receives a webhook POST with applicant details, travel plan, and raw passport OCR text. Uses Anthropic Claude to extract and validate passport data (name, nationality, passport number, expiry) and scores whether the passport text is readable. If passport data is insufficient, immediately returns a webhook response asking the applicant to resubmit a clearer passport scan. If passport data is sufficient, waits briefly and uses Anthropic Claude again to determine whether a visa is required, the visa category, a recommended visa type, processing time, risks, and confidence. Builds a document checklist from a standard base list plus purpose-specific items and any AI-flagged eligibility risks, then renders it into HTML. Sends the HTML to PDFShift to generate a PDF, formats a summary row, and appends the application record to a Google Sheets tab. Emails
Detect LLM prompt regressions with Data Tables, OpenAI APIs, and Telegram
Quick overview Continuous quality checks for your production LLM prompts. Keeps a golden test set in n8n Data Tables, runs it on a schedule against any OpenAI-compatible API, compares each run to a blessed baseline, and pings Telegram only when quality actually changes. How it works A Schedule Trigger starts each run. The Execute workflow button runs it on demand. Prompt profiles (system prompt, model, temperature) and test cases (input, expected output, check type) load from two Data Tables. When both tables are empty the workflow seeds demo rows, so the first run works immediately. Every case calls its own model through a generic OpenAI-compatible HTTP request with retries. Failed calls are recorded and reported, never silently dropped. Deterministic checks (exact, contains, regex, numeric) grade most answers for free. An LLM judge scores only the free-form cases marked llm-judge on a 1-5 scale. The run is aggregated, snapshotted to an eval history table, and compared to the blessed baseline: a flipped case must fail two runs in a row to count, while a broad pass-rate or judge-score drop alerts at once. A Telegram digest goes out on baseline capture, regression, recovery, or an o
WTranslate audio transcripts with Gladia, Google Drive, and Google Sheets
Quick overview This workflow collects a public media URL and target language via an n8n form, sends the audio/video to Gladia for transcription and translation, then saves a Markdown transcript file to Google Drive and logs the outcome (success or failure) to Google Sheets. How it works Receives a form submission containing a publicly reachable audio/video URL and a target language code. Starts a Gladia pre-recorded job with transcription enabled and translation configured for the requested target language. Waits and repeatedly polls Gladia’s result URL until the job finishes, errors, or reaches the maximum number of attempts. When Gladia reports the job as done, builds a Markdown file containing the original transcript, the translated transcript, and language metadata. Uploads the Markdown file to Google Drive. Appends a “Translated” row to Google Sheets with the media URL, detected language, target language, and a Drive link, or logs a “Failed” row with error details if any step fails. Setup Add a Gladia API key using an HTTP Header Auth credential (header name x-gladia-key) and select it for both Gladia HTTP Request steps. Connect Google Drive OAuth credentials and choose the de
WTranscribe speaker-labeled recordings with Gladia, Google Drive, and Slack
Quick overview This workflow collects a public media URL via an n8n form, sends it to Gladia for diarized transcription, formats the result as a speaker-labeled Markdown note, saves it to Google Drive, and posts the Drive link (or any failure reason) to a Slack channel. How it works Receives a form submission containing a public audio/video URL and an optional hint for the number of speakers. Starts an asynchronous Gladia pre-recorded transcription job with speaker diarization enabled. Waits and repeatedly polls Gladia for the job status until it is done, errors, or reaches the configured maximum number of attempts. When complete, converts Gladia’s diarized utterances into a readable Markdown transcript grouped by speaker and timestamped. Uploads the transcript file to Google Drive and posts a Slack message with the share link. If the Gladia requests fail or the job times out/errors, posts a Slack message describing the failure. Setup Create an HTTP Header Auth credential for Gladia (header x-gladia-key) and select it on both Gladia HTTP Request steps. Connect a Google Drive OAuth2 account and choose the target Drive/folder where transcripts are uploaded. Connect a Slack account an
CWExtract and log Gmail admin tasks with OpenAI, Google Sheets and Airtable
Quick overview This workflow monitors Gmail for messages labeled “Admin”, redacts sensitive data, uses OpenAI to extract structured admin tasks and reminders, skips duplicates by checking Google Sheets and/or Airtable, sends optional Slack or Microsoft Teams alerts for urgent items, and logs the clean task details. How it works Triggers every minute when a new Gmail message matches the query label:Admin newer_than:7d. Loads configurable settings (log destination, alert channels, due-soon window, dedupe window, and redaction toggle) and normalizes the email into a clean text body. Redacts sensitive patterns (such as SSNs, card-like numbers, phone numbers, email addresses, and addresses) and generates an “admin hash” fingerprint for deduplication. Checks Google Sheets and/or Airtable for recent matching Message IDs or admin hashes and skips processing if the email appears to be a duplicate. Sends the redacted email content to OpenAI to classify whether it is an admin item and to extract fields like task title, summary, priority, due date/time, and recommended next step. If the item is valid, optionally posts an alert to Slack and/or Microsoft Teams for urgent/high-priority, due-soon,
CWExtract and log Gmail receipt expenses with OpenAI, Sheets and Airtable
Quick overview This workflow monitors a Gmail “Receipts” label, downloads attachments, uses OpenAI to extract expense data from receipt emails and images, skips duplicates and non-receipts, fails safely when extraction is unreadable, sends Slack/Teams alerts for high-value, warranty, or review-needed receipts, and logs valid receipts to Sheets or Airtable. How it works Triggers every minute when Gmail finds new emails matching the query label:Receipts newer_than:2d. Normalizes the email into consistent fields (message ID, subject, sender, received date, plain-text body) and generates a receipt hash for stable matching. Searches Airtable and/or Google Sheets for existing records matching the message ID or receipt hash and marks the email as a duplicate if it falls within the configured duplicate window. For new receipts, sends the email content to OpenAI to extract receipt details like merchant, total, category, line items, tax hints, and return/warranty dates. Evaluates the extraction to flag high-value, warranty/return-relevant, or needs-review receipts and formats alert messages. Posts alerts to Slack and/or Microsoft Teams when enabled and the receipt is not “standard.” Appends
WCreate personalized videos from Google Sheets with iLoveVideoEditor and Gmail
Quick overview This workflow watches Google Sheets for new rows, renders a personalized video with iLoveVideoEditor using the row data, uploads the finished MP4 to Google Drive, writes the Drive link back to the same sheet row, and emails the link to the recipient via Gmail. How it works Triggers on a schedule when a new row is added to a specified Google Sheets worksheet. Skips rows where the Title field is empty. Starts a video render in iLoveVideoEditor from the cinematic-title template using the row’s Title and Subtitle as template variables. Polls iLoveVideoEditor every 60 seconds (up to 20 attempts) until the render status becomes completed, or stops early if the status becomes failed. When completed, downloads the MP4 from the render URL, uploads it to a specified Google Drive folder, and generates a shareable Drive view link. Updates the original Google Sheets row (matched by ID) with the Video URL and sends the Drive link to the row’s Email address via Gmail. If the render fails, times out, or errors, sends a failure alert email via Gmail with the row details. Setup Install the community node n8n-nodes-ilovevideoeditor (required for self-hosted n8n) and add your iLoveVideo
W
Scrape and score Amazon products with Apify, OpenAI, and Google Sheets
Quick overview This workflow manually scrapes product results from an Amazon search URL via the Apify Amazon Crawler actor, uses OpenAI to generate a structured product analysis (category, key feature, verdict, value score), and appends the enriched results to a Google Sheets spreadsheet. How it works Runs when you manually click “Test workflow” in n8n. Sends the configured Amazon search URL and scraping limits to the apify Amazon Crawler actor and retrieves the dataset items. Filters out any scraper items that are missing a title or contain an error. Uses OpenAI to analyze each product’s title, brand, price, rating, and review count and returns a structured category, key feature, buyer verdict, and 1–10 value score. Combines the scraped fields and AI analysis into a single row format and adds a timestamp. Appends each enriched product as a new row in Google Sheets. Setup Create an apify API token and add it as an HTTP Header Auth credential used by the Apify request. Add an OpenAI API key as an OpenAI credential and choose the model to use in the configuration. Connect a Google Sheets OAuth2 account and select the target spreadsheet, sheet tab, and columns for appending rows. Upda
WGenerate weekly Pinterest content opportunity briefs with Apify, OpenAI and Google Sheets
Quick overview Research a Pinterest niche with FetchCat's Pinterest Search Scraper, preserve every source pin in Google Sheets, and use one evidence-controlled OpenAI call to identify recurring themes, underrepresented angles, and five production-ready content briefs without claiming search volume or trend growth. How it works Starts manually with one research niche and one to five exact Pinterest search phrases, plus locale, country, and a configurable result limit. Runs fetch_cat/pinterest-search-scraper through a Cloud-compatible HTTP Request and collects 20 to 500 public pins per search with public detail enrichment enabled. Validates, normalizes, and deduplicates returned pins. It stops before AI or destination writes when fewer than ten usable pins remain. Builds stable Google Sheets rows, deterministic phrase counts, and a bounded evidence packet, then uses one structured gpt-5.4-mini request for analysis. Removes invalid pin citations and rejects any finding that retains no supplied evidence, preventing unsupported recommendations from reaching the destination. Upserts source pins and a readable brief into separate Pins and Research Brief tabs using stable same-day research
Find and verify business emails with ScraperCity, OpenAI, Google Sheets, and Gmail
Quick overview This workflow reads contacts from Google Sheets, finds and verifies their business emails via the ScraperCity Email Finder API, generates a short personalized icebreaker with OpenAI, appends the enriched leads to another Google Sheet, and emails a run summary via Gmail. How it works Starts manually to run an email enrichment job. Reads contacts (first name, last name, domain) from an input Google Sheets worksheet and aggregates them into a single payload. Submits the contacts to the ScraperCity Email Finder API, then waits and repeatedly checks the job status until it succeeds or fails/times out. When the job succeeds, downloads the result CSV from ScraperCity, parses it, normalizes key fields (name, domain, email, verification status, provider), and keeps only rows with an email. For each verified contact, prompts OpenAI to generate one short, company-referencing cold-email opening line in the configured language. Appends the enriched lead (including email, status, and icebreaker) to an output Google Sheets worksheet and sends a summary email via Gmail. Setup Create a ScraperCity account with Email Finder credits and add an HTTP Header Auth credential that sends you
W
Find YouTube creator emails with Apify, OpenAI and Google Sheets
Quick overview This workflow searches YouTube via Apify for videos matching a keyword, deduplicates the resulting channels, scrapes each channel’s About description, uses OpenAI to extract contact email addresses, and appends channels with emails to a Google Sheets tab. How it works Starts when you manually execute the workflow. Sends a keyword-based search request to the Apify YouTube Scraper to retrieve recent YouTube results and their channel URLs. Deduplicates the results so each channel URL is processed only once. Scrapes each channel’s About/description data using an Apify YouTube Scraper request. Uses OpenAI to extract and de-obfuscate any email addresses found in the channel description. Keeps only channels where at least one email address was extracted. Appends the channel name, channel URL, extracted emails, search query, and the current date to Google Sheets. Setup Add an Apify API token using an HTTP Header Auth credential (Authorization: Bearer ) and connect it to both Apify HTTP Request steps. Add an OpenAI API key credential and choose the model name you want to use in the Configuration values. Connect your Google Sheets OAuth credential, then set the target spreadsh
Draft and stage LinkedIn re-engagements with HeyReach, Twain, and Slack
Quick overview This workflow runs weekly (or manually) to pull tagged “cold” HeyReach conversations, uses Twain to draft context-aware re-engagement messages, then stages leads in a HeyReach list and notifies Slack for review while tagging processed leads to avoid duplicates. How it works Runs on a weekly schedule or via a manual trigger. Fetches all conversations from the HeyReach Inbox API using pagination. Filters conversations by HeyReach lead tags (include tags like “Cold”/“Not interested” and exclude tags like “Re-engaged”) and extracts each lead’s LinkedIn URL, name, and prior message thread. Sends the conversation context to Twain to generate a re-engagement sequence draft and add the contact to the specified Twain campaign. Adds the lead to a HeyReach re-engagement list and stores the first Twain draft message in a custom user field. Posts the drafted re-engagement message to a Slack channel for review. Tags the lead as “Re-engaged” in HeyReach to prevent reprocessing. Setup Add HeyReach API credentials for HTTP Header Auth and ensure the header matches HeyReach requirements (for example, X-API-KEY). Add Twain API credentials for HTTP Header Auth and ensure the header matc
WMonitor ad campaign health daily with Spendict, Google Sheets, and Slack
Quick overview This workflow runs every morning to read ad campaign metrics from Google Sheets, send each campaign to Spendict for performance diagnosis against benchmarks, log the verdicts back to Google Sheets, and post Slack alerts when a campaign needs attention. How it works Runs daily at 08:00 on a schedule trigger. Reads campaign metric rows from a Google Sheets spreadsheet. Builds a Spendict request per campaign by normalizing platform/objective fields and including only numeric metrics present in each row. Sends each campaign’s metrics to the Spendict analyze-performance API to get a verdict, score, bottleneck, and diagnosis. Routes results by verdict so healthy or insufficient-data campaigns are only logged, while fix_first and kill_or_rebuild campaigns are also prepared for alerting. Appends a dated health-check row for every campaign to a Google Sheets “health log” sheet. Posts a Slack Incoming Webhook message for fix_first and kill_or_rebuild campaigns including the score, primary bottleneck, and diagnosis. Setup Add Google Sheets credentials and select the document and sheet for both reading campaign metrics and appending to the health log. Ensure your metrics sheet h
Draft incident postmortems with PagerDuty, Confluence, Slack and Google Sheets
Quick overview This workflow creates a Confluence postmortem draft for resolved PagerDuty incidents, then notifies the incident owner in Slack and optionally logs the draft in Google Sheets. How it works Triggers manually for testing or receives a PagerDuty webhook when an incident is resolved. Loads shared configuration values like PagerDuty and Confluence URLs, Confluence space and parent page, Slack channel, and optional Google Sheets settings. Normalizes the incoming incident payload and fetches the incident details and log entries from the PagerDuty API. Builds an HTML postmortem draft containing an incident summary, placeholders for impact and root cause, a basic timeline, and action-item prompts. Creates a new Confluence page under the configured parent page using the generated postmortem content. Posts a Slack message to the configured channel and optionally appends a row to a Google Sheets “Postmortems” tab with key incident metadata. Setup Add PagerDuty API credentials to the PagerDuty HTTP Request steps and configure a PagerDuty webhook pointing to this workflow’s webhook URL for resolved incidents. Add Confluence (Atlassian) credentials and set your Confluence base URL,
Analyze URLs and extract SEO metadata with forms and HTTP requests
Quick Overview This workflow collects a URL via an n8n Form, follows HTTP redirects to the final destination, extracts page and Open Graph/Twitter metadata from the final HTML, and displays the results back in a form response using only built-in n8n nodes. How it works Receives a URL submission from the n8n Form trigger. Normalizes the input so it includes an http/https scheme. Requests the URL with redirect-following disabled to capture the HTTP status and Location header. If the response is a redirect (301/302/307/308), tracks visited URLs and redirect count, detects loops or exceeding the redirect limit, and either continues to the next Location URL or shows a redirect/loop error. If the response is 200 OK, parses the HTML to extract the title, meta description, canonical URL, language, Open Graph tags, Twitter Card tags, and common tracking parameters. Displays the extracted metadata and final URL in a results form, then redirects back to the input form page. Setup Activate the workflow so the n8n Form trigger has a Production URL. Copy the Form trigger Production URL and paste it into the Set URL value to replace REPLACE_WITH_PRODUCTION_FORM_URL so the completion step redirect
Generate sales research briefs from Google Sheets with Claude and Slack
Quick overview This workflow polls a Google Sheets prospect queue, researches each new company via SerpAPI and enrichment/contact APIs, then uses Anthropic Claude to generate a structured sales brief and outreach draft, logs the result back to Google Sheets, marks the prospect as researched, and notifies a sales rep in Slack. How it works Runs every 15 minutes and reads rows from the Prospects tab in Google Sheets. Filters for prospects with Status set to "New" and processes each prospect as an individual item. Researches each prospect in parallel by pulling recent news via SerpAPI, company funding/technology data via a company enrichment API, and decision-maker contacts via a people data API. Combines the research signals into one profile per prospect and calculates a priority score and a research completeness score. Skips prospects with insufficient data and sends the rest to Anthropic Claude to generate a JSON sales brief and first-touch outreach message. Appends the brief to the SalesBriefs tab in Google Sheets, updates the original prospect’s Status to "Researched", and posts a summary plus the draft message to Slack via an incoming webhook. Setup Create a Google Sheets OAuth2
Route procurement helpdesk tickets from Gmail with Groq and Slack
Quick Overview This workflow monitors a Gmail inbox for procurement requests, uses Groq (Llama 3.1) to classify and route each ticket with SLA logic, escalates high-risk items to Slack, creates a ticket via HTTP, sends an auto-reply from Gmail, and logs the full record to Google Sheets. How it works Triggers every minute when a new email arrives in a Gmail inbox. Extracts the sender, subject, body, timestamps, and Gmail thread/message IDs, and generates a procurement ticket ID. Looks up the email thread ID in Google Sheets to identify whether the request already exists. Uses Groq (Llama 3.1) to classify the request (category, urgency, sentiment, risk, team) and applies routing rules to set SLA deadlines, queues, and escalation flags. If escalation is required, posts a detailed alert to a Slack channel and creates an escalated ticket via an HTTP request; otherwise, creates a standard ticket via an HTTP request. Generates a short agent-facing status summary with Groq, emails the customer an acknowledgement and suggested reply via Gmail, and appends the full ticket and AI outputs to Google Sheets. Setup Connect your Gmail OAuth2 credential for both the inbox trigger and the customer a
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
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
Draft personalized welcome emails for new signups with Twain, Gmail, and Slack
Quick overview This workflow receives new signup events, enriches each contact with Twain (and optionally a LinkedIn lookup), drafts a personalized welcome email in Gmail, and posts review-ready previews to Slack, with optional LinkedIn-step handoff to HeyReach. How it works Receives a new signup via a POST webhook secured with header authentication (with optional disabled schedule-based backfills from Google BigQuery or Google Firestore). Normalizes the signup fields (email, name, UID, timestamps, LinkedIn URL) and de-duplicates signups by UID across workflow executions. If the signup has no LinkedIn URL but does have an email, looks up a LinkedIn profile URL via Findymail (or other disabled provider alternatives) and merges the resolved profile back into the contact. If the contact has a usable work email or LinkedIn URL, calls the Twain Generate Sequence API to research the person and generate a personalized welcome sequence, otherwise posts a “skipped” notice to Slack. Builds a formatted draft payload and previews (email steps vs LinkedIn steps) from the Twain response, including any warning flags and a link back to the lead in Twain. If a work email is available, creates a Gma
Create Shopify product videos from tagged photos with Dreem.ai and Slack
Quick overview This workflow turns a product photo into a short product video with Dreem AI. Tag a product dreem-video in Shopify and the finished clip arrives in Slack for approval, then lands in the product's media. How it works The workflow fires when a product update carries the tag dreem-video. The tag is swapped immediately so the workflow cannot re-trigger itself. The Dreem node animates the product's newest image into a 5-10 second video. Use an on-model photo for best results. Dreem renders in the background (up to 20 minutes) and calls the workflow back. The video link posts to Slack with Upload / Skip buttons. No click within 12 hours counts as Skip - nothing reaches the store without a yes. Posts the finished video link to Slack and sends an approval message with buttons to either upload the video to Shopify or skip. If approved, downloads the video file, creates a staged Shopify upload via the Shopify Admin GraphQL API, uploads the video to the staged target, and attaches it to the product’s media. If rendering times out or does not complete, posts a timeout message to Slack and stops without uploading anything to Shopify. Setup Add a Shopify Admin access token credent
Draft security questionnaire answers with Notion, Google Docs, and Slack
Quick overview This workflow runs on demand to match security questionnaire questions against an approved-answer library in Notion, then creates a Google Docs draft and notifies reviewers in Slack, optionally updating a Notion tracker page. How it works Starts manually to run a test questionnaire and load configuration values like the Notion database ID, Google Drive folder ID, and confidence threshold. Loads a list of questionnaire questions and queries the Notion database for answers whose Status equals the configured approved value. Compares each questionnaire question to the approved Notion questions, selects the closest match, and marks low-confidence matches as “Needs review” instead of auto-answering. Branches based on whether any answers need review and posts a corresponding Slack notification to the configured review channel. Builds a formatted draft body containing each question, match confidence, owner, and either the approved answer or a “Needs review” placeholder. Creates a new Google Docs document for the draft and optionally updates a Notion questionnaire tracker page with “Draft ready for review” and the needs-review count. Setup Add Notion credentials and set the a
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