Promo seeker: Auto-find promo codes with SerpAPI, Gemini & Telegram

Name: Promo seeker: Auto-find promo codes with SerpAPI, Gemini & Telegram
Availability: InStock
Rating: 4.5 (29 reviews)
Author: Khairul Muhtadin

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER 🎉 Early Black Friday Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Promo Seeker automatically finds, verifies, and delivers active promo codes to users via Telegram or email using SerpAPI + Gemini (OpenRouter). Saves hours of manual searching and deduplicates results into an n8n Data Table for fast reuse.

Why Use This Workflow?

Time Savings: Reduces manual promo hunting from ~2 hours to ~5 minutes per query.

Cost Reduction: Cuts reliance on paid scraping tools or manual services — potential savings of $50–$200/month.

Error Prevention: Cross-references sources and enforces a 30‑day recency filter to reduce expired-code hits by ~60% vs single-source checks.

Scalability: Handles hundreds of queries per day with Data Table upserts and optional scheduling for continuous discovery.

Ideal For

Marketing / Growth Managers: Quickly discover competitor or partner discounts to promote in campaigns.
Customer Support / Operations: Respond to user requests with verified promo codes via Telegram or email.
Affiliate / Content Teams: Aggregate and maintain a clean promo feed for newsletters or site widgets.

How It Works

Trigger: Incoming request via Webhook, Telegram message, Google Form submission, or scheduled run.
Data Collection: The LangChain agent uses SerpAPI search results and Gemini (OpenRouter) to locate recent promo codes.
Processing: Filter for recency (last 30 days), extract code, value, terms, and expiry.
Intelligence Layer: Gemini 2.5 Pro (OpenRouter) + LangChain agent structure and verify results, outputting a standardized JSON.
Output & Delivery: If a code exists in the Data Table, notify the requester via Telegram and Gmail; otherwise, return results and upsert them into the Data Table.
Storage & Logging: Results stored/upserted in an n8n Data Table to prevent duplicates and enable fast lookups.

Setup Guide

Prerequisites

Requirement	Type	Purpose
n8n instance	Essential	Execute the workflow — import JSON to your n8n instance
SerpAPI account	Essential	Web search results for promo code discovery
OpenRouter (Gemini) account	Essential	Language model (Gemini 2.5 Pro) for extraction and verification
Telegram Bot (BotFather)	Essential	Receive queries and send promo notifications
Gmail OAuth2	Essential	Send rich email notifications
n8n Data Tables	Essential	Store and deduplicate promo code records

Get your n8n instance here: n8n instance — import the JSON and begin configuration. (Repeat link for convenience) n8n instance

Installation Steps

Import the JSON workflow into your n8n instance.
Configure credentials (use n8n's Credentials UI — do NOT paste keys into nodes):
- SerpAPI: paste your SerpAPI API Key from your SerpAPI dashboard.
- OpenRouter API: paste your OpenRouter API Key (for Gemini 2.5 Pro).
- Telegram API: create bot via @BotFather, then add Bot Token to Telegram credentials.
- Gmail OAuth2: use n8n's Gmail OAuth2 credential flow and authorize the account.
Update environment-specific values:
- Webhook path: /v1/promo-seeker (configured in the Webhook node) or replace with your preferred path.
- Data Table ID: point to your own Data Table
- Form/webhook recipient fields (email/chatId mappings).
Customize settings:
- Adjust the LangChain agent prompt (Promo Seeker Agent) for different recency windows or regional focus.
- Change max results/limit on the Data Table node (default limit = 3).
Test execution:
- Trigger via Telegram or a POST to the webhook with sample payload:
```
{ "platform":"example.com", "email":"[email protected]" }
```
- Confirm notifications arrive and Data Table rows are upserted.

Technical Details

Core Nodes

Node	Purpose	Key Configuration
SerpAPI	Fetch web search results	Provide credential; adjust search params in agent prompt
Gemini 2.5Pro (OpenRouter)	Extract & verify promo details	Use OpenRouter credential; model google/gemini-2.5-pro
Promo Seeker Agent (LangChain)	Orchestrates search + parsing	System prompt enforces 30‑day recency & result format
Structured Output Parser	Validates agent output	JSON schema example for platform/code/value/terms/validUntil
Data Table (Get row(s))	Lookup existing promos	Filters by platform; limit = 3
If (Code Exist?)	Branching logic	Checks existence of platform field
Data Table (Upsert row(s))	Insert or update promo	Mapping from agent output to Data Table columns
Telegram Trigger / Telegram	Receive queries & notify users	Webhook-based trigger; parse_mode = HTML for messages
Gmail	Send rich HTML emails	Uses Gmail OAuth2 credential
Webhook / Form Trigger	Alternate inputs	Webhook path /v1/promo-seeker and Form trigger for manual submissions

Workflow Logic

On trigger, the Platform Set node normalizes the incoming query and receiver.
Get row(s) checks Data Table for existing promos.
- If found: notify via Telegram and send Gmail (email template included).
- If not found: the Promo Seeker Agent runs SerpAPI searches, parses structured output, then Upsert row(s) saves results and notifications are sent.
Structured Output Parser enforces correct JSON to avoid bad upserts.

Customization Options

Basic Adjustments

Recency window: change the agent prompt to 7/14/30 days.
Result limit: increase Data Table Get limit or change Upsert batch size.

Advanced Enhancements

Add Slack or Microsoft Teams notifications (moderate complexity).
Add caching layer (Redis) to reduce repeated SerpAPI calls (advanced).
Parallelize searches across multiple search engines (higher API usage & complexity).

Performance & Optimization

Metric	Expected Performance	Optimization Tips
Execution time	8–30s per new search (depends on SerpAPI + LM response)	Reduce SerpAPI page depth; cache recent results
API calls	3–10 SerpAPI calls per complex query	Batch queries; use higher-quality search params
Error handling	Agent retries on malformed output	Use retry nodes and set onError strategy for downstream nodes

Troubleshooting

Problem	Cause	Solution
No results returned	Query too vague or rate-limited API	Improve query specificity; check SerpAPI quota
Gmail send fails	OAuth scope not granted or token expired	Reconnect Gmail OAuth2 credential in n8n
Telegram webhook not firing	Incorrect bot token or webhook setup	Recreate Telegram credential and check bot permissions
Duplicate rows	Upsert mapping mismatch	Ensure promoCode mapping in Upsert matches structured output
Agent returns malformed JSON	LM prompt too permissive	Tighten the agent system prompt and validate with Structured Output Parser

Created by: khaisa Studio Category: Marketing Automation

Tags: promo-codes, coupons, serpapi, telegram, gmail, openrouter, data-tables

Need custom workflows or help adapting this template? Contact us

Khairul Muhtadin

0 workflows

Nodes

set gmail telegram agent google-gemini

Complexity

advanced

Published 02 Oct 2025

Likes 0

View on n8n.io Download Workflow

✨

Share Your Workflow

Have a great workflow to share? Join the n8n Creator Hub and help the community!

Submit Your Template How to Submit

Related Workflows

Build a Telegram AI assistant with MemMachine, OpenAI, and voice support

# Build a Telegram assistant with MemMachine and voice support An AI assistant that NEVER forgets using MemMachine for persistent cross-session memory, with voice transcription support and productivity tools. **⚠️ Important Deployment Note:** This workflow is designed for **self-hosted n8n** instances. If you're using n8n Cloud, you'll need to deploy MemMachine to a cloud server and update the HTTP Request URLs in nodes 4, 5, and 9. ## What This Template Does This workflow creates an intelligent personal assistant that maintains perfect memory across all conversations, whether you message today or weeks from now. It supports both text and voice messages, automatically transcribes voice using OpenAI Whisper, and provides tools for Gmail, Google Sheets, and Google Calendar. ## Key Features - 🧠 **Perfect Memory** - Remembers every conversation using MemMachine - 🎤 **Voice Transcription** - Supports voice messages via OpenAI Whisper - 📧 **Gmail Integration** - Send and read emails - 📊 **Google Sheets** - Read and write spreadsheet data - 📅 **Google Calendar** - Create and manage events - 🔧 **MCP Tools** - Extensible tool architecture - 💬 **Smart Context** - References past conversations naturally ## Real-World Example **Day 1 - Text Message:** - User: "Send an email to [email protected] about the Q1 report" - AI: *Uses Gmail tool* "Email sent to John about the Q1 report!" **Day 3 - Voice Message:** - 🎤 User: "What did I ask you to do for John?" - AI: "On January 5th, you asked me to email John about the Q1 report, which I sent." **Day 7 - Text Message:** - User: "Follow up with John" - AI: "I'll send a follow-up email to [email protected] about the Q1 report that we discussed on Jan 5th." The AI remembers who John is, what you discussed, and when it happened - all without you having to repeat yourself! ## How It Works ### Message Flow **For Text Messages:** 1. Telegram Trigger receives message 2. Extract user data and message text 3. Store message in MemMachine 4. Search conversation history (last 30 memories) 5. AI processes with full context + tools 6. Store AI response for future reference 7. Send reply to user **For Voice Messages:** 1. Telegram Trigger receives voice message 2. Download voice file 3. OpenAI Whisper transcribes to text 4. Extract transcribed text and user data 5. Store in MemMachine (same as text flow) 6. Process with AI + tools 7. Send reply to user ## Requirements ### Services & Credentials - **MemMachine** - Open-source memory system (self-hosted via Docker) - **Telegram Bot Token** - From @BotFather - **OpenAI API Key** - For AI responses and voice transcription - **Gmail OAuth** - For email integration (optional) - **Google Sheets OAuth** - For spreadsheet access (optional) - **Google Calendar OAuth** - For calendar management (optional) ### Installation ## MemMachine Setup ```bash # Clone and start MemMachine git clone https://github.com/MemMachine/MemMachine cd MemMachine docker-compose up -d # Verify it's running curl http://localhost:8080/health ``` ## Workflow Configuration ### Deployment Options This workflow supports two deployment scenarios: **Option 1: Self-Hosted n8n (Recommended)** - Both n8n and MemMachine run locally - Best for: Personal use, development, testing - Setup: 1. Run MemMachine: `docker-compose up -d` 2. Use `http://host.docker.internal:8080` in HTTP Request nodes (if n8n in Docker) 3. Or use `http://localhost:8080` (if n8n installed directly) **Option 2: n8n Cloud** - n8n hosted by n8n.io, MemMachine on your cloud server - Best for: Production, team collaboration - Setup: 1. Deploy MemMachine to cloud (DigitalOcean, AWS, GCP, etc.) 2. Expose MemMachine via HTTPS with SSL certificate 3. Update HTTP Request URLs in nodes 4, 5, 9 to: `https://your-memmachine-domain.com` 4. Ensure firewall allows n8n Cloud IP addresses ### Configuration Steps 1. **Import this template** into your n8n instance 2. **Update MemMachine URLs** (nodes 4, 5, 9): - **Self-hosted n8n in Docker**: `http://host.docker.internal:8080` - **Self-hosted n8n (direct install)**: `http://localhost:8080` - **n8n Cloud**: `https://your-memmachine-domain.com` 3. **Set Organization IDs** (nodes 4, 5, 9): - Change `your-org-id` to your organization name - Change `your-project-id` to your project name 4. **Add Credentials:** - Telegram Bot Token (node 1) - OpenAI API Key (nodes 4, 7) - Gmail OAuth (Gmail Tool node) - Google Sheets OAuth (Sheets Tool node) - Google Calendar OAuth (Calendar Tool node) ## Use Cases ### Personal Productivity - "Remind me what I worked on last week" - "Schedule a meeting with the team next Tuesday" - "Email Sarah about the proposal" ### Customer Support - AI remembers customer history - References past conversations - Provides contextual support ### Task Management - Track tasks across days/weeks - Remember project details - Follow up on action items ### Email Automation - "Send that email to John" (remembers John's email) - "What emails did I send yesterday?" - "Draft an email to the team" ### Calendar Management - "What's on my calendar tomorrow?" - "Schedule a meeting with Alex at 3pm" - "Cancel my 2pm meeting" ## Customization Guide ### Extend Memory Capacity In **Node 5 (Search Memory)**, adjust: ```json "top_k": 30 // Increase for more context (costs more tokens) ``` ### Modify AI Personality In **Node 7 (AI Agent)**, edit the system prompt to: - Change tone/style - Add domain-specific knowledge - Include company policies - Set behavioral guidelines ### Add More Tools Connect additional n8n tool nodes to the AI Agent: - Notion integration - Slack notifications - Trello/Asana tasks - Database queries - Custom API tools ### Multi-Channel Memory Create similar workflows for: - WhatsApp (same MemMachine instance) - SMS via Twilio (same memory database) - Web chat widget (shared context) All channels can share the same memory by using consistent `customer_email` identifiers! ## Memory Architecture ### Storage Structure Every message is stored with: ```json { "content": "message text", "producer": "[email protected]", "role": "user" or "assistant", "metadata": { "customer_email": "[email protected]", "channel": "telegram", "username": "john_doe", "timestamp": "2026-01-07T12:00:00Z" } } ``` ### Retrieval & Formatting 1. **Search** - Finds relevant memories by customer email 2. **Sort** - Orders chronologically (oldest to newest) 3. **Format** - Presents last 20 messages to AI 4. **Context** - AI uses history to inform responses ## Cost Estimate - **MemMachine**: Free (self-hosted via Docker) - **OpenAI API**: - Text responses: ~$0.001 per message (GPT-4o-mini) - Voice transcription: ~$0.006 per minute (Whisper) - **n8n**: Free (self-hosted) or $20/month (cloud) - **Google APIs**: Free tier available **Monthly estimate for 1,000 messages (mix of text/voice):** - OpenAI: $5-15 - Google APIs: $0 (within free tier) - Total: $5-15/month ## Troubleshooting ### Deployment Issues **n8n Cloud: Can't connect to MemMachine** - Ensure MemMachine is publicly accessible via HTTPS - Check firewall rules allow n8n Cloud IPs - Verify SSL certificate is valid - Test endpoint: `curl https://your-domain.com/health` **Self-Hosted: Can't connect to MemMachine** - Check Docker is running: `docker ps` - Verify URL matches your setup - Test endpoint: `curl http://localhost:8080/health` ### Voice not transcribing - Verify OpenAI API key is valid - Check API key has Whisper access - Test with short voice message first ### AI not remembering - Verify `org_id` and `project_id` match in nodes 4, 5, 9 - Check `customer_email` is consistent - Review node 5 output (are memories retrieved?) ### Tools not working - Verify OAuth credentials are valid - Check required API scopes/permissions - Test tools individually first ## Advanced Features ### Cloud Deployment Guide (For n8n Cloud Users) If you're using n8n Cloud, follow these steps to deploy MemMachine: **1. Choose a Cloud Provider** - DigitalOcean (Droplet: $6/month) - AWS (EC2 t3.micro) - Google Cloud (e2-micro) - Render.com (easiest, free tier available) **2. Deploy MemMachine** For DigitalOcean/AWS/GCP: ```bash # SSH into your server ssh root@your-server-ip # Install Docker curl -fsSL https://get.docker.com -o get-docker.sh sh get-docker.sh # Clone and start MemMachine git clone https://github.com/MemMachine/MemMachine cd MemMachine docker-compose up -d ``` **3. Configure HTTPS (Required for n8n Cloud)** ```bash # Install Caddy for automatic HTTPS apt install caddy # Create Caddyfile cat > /etc/caddy/Caddyfile << 'CADDYEND' your-domain.com { reverse_proxy localhost:8080 } CADDYEND # Start Caddy systemctl start caddy ``` **4. Update Workflow** - In nodes 4, 5, 9, change URL to: `https://your-domain.com` - Remove the `/api/v2/memories` part is already in the path **5. Security Best Practices** - Use environment variables for org_id and project_id - Enable firewall: `ufw allow 80,443/tcp` - Regular backups of MemMachine data - Monitor server resources ### Semantic Memory MemMachine automatically extracts semantic facts from conversations for better recall of important information. ### Chronological Context Memories are sorted by timestamp, not relevance, to maintain natural conversation flow. ### Cross-Session Persistence Unlike session-based chatbots, this assistant remembers across days, weeks, or months. ### Multi-Modal Input Seamlessly handles both text and voice, storing transcriptions alongside text messages. ## Template Information **Author:** David Olusola **Version:** 1.0.0 **Created:** January 2026 ## Support & Resources - **MemMachine Documentation**: https://github.com/MemMachine/MemMachine - **n8n Community**: https://community.n8n.io - **OpenAI Whisper**: https://platform.openai.com/docs/guides/speech-to-text ## Contributing Found a bug or have an improvement? Contribute to the template or share your modifications with the n8n community! --- **Start building your perfect-memory AI assistant today!** 🚀

View

Build a prospecting list with LeadIQ and save it to Airtable CRM

## **Who this is for** B2B companies, including: - Founders - Marketing and sales professionals - Recruiters involved in people search and B2B outreach With this workflow: - No more manual list building - No time spent researching what each company does - No manual CRM work — all found data is saved to a spreadsheet automatically ## **What it does** This workflow helps you quickly **build a list of prospects for outreach** using the **LeadIQ** provider. It collects: - Full name - LinkedIn profile - Company website and description - Emails (when available in the LeadIQ database) You can start contacting people via LinkedIn manually right away. You simply **provide a natural language prompt**, for example: *“Founder at a software engineering firm, 11–50 employees, based in New York, using AI technologies.”* The embedded AI agent transforms your input into a GraphQL query, which is then used to pull leads from the database. 📹 Video walkthrough: [Click Here](https://vimeo.com/1151100805) **Benefits:** - LeadIQ is an affordable database, with a cost per lead of approximately $0.03–$0.05 USD, depending on your plan and volume - No credit card or paid plan is required to start using the LeadIQ API — just sign up and access the API - The API includes 50 free credits, which is enough to test the workflow - The workflow enriches company details from the open web (company description, HQ address) - No need to manually configure filters — use a simple natural language prompt - All data is saved automatically to Airtable CRM (using their standard CRM template from the template library) ⚠️ **Important:** This workflow is not ideal if email addresses are the only data you need, as LeadIQ does not always provide emails. It works best when you need: - A curated list of people based on specific criteria - Their LinkedIn profiles - Automated saving of leads to a database You can later enrich email data using other paid databases by pulling records from Airtable. ## How to customize the workflow 1. Sign up for **LeadIQ**: https://leadiq.com - Obtain the API string called “**Secret Base64 API key**” 2. Add the API key to all **HTTP** nodes: - Method: POST - URL: https://api.leadiq.com/graphql - Enable “**Send Headers**” and add: ``` Authorization: Basic <your API string here> Content-Type: application/json ``` 3. Sign up for Airtable - Find the template: *Left panel → Templates & apps → Marketing → “Sales CRM”* 4. In Airtable, generate an API key: - Builder Hub → Developers → Personal access token - Add your Sales CRM database to the token scope 5. Set the correct base and sheet in all Airtable nodes 6. Use the Code node called “Manage number of leads” to control how many records are pulled from the database - Default value: 1 (to save LeadIQ credits) - To change it, edit: ``` input.limit = 1; ``` Replace 1 with the desired number of leads 7. Launch the workflow using the “Open Chat” trigger node - Enter a prompt containing the criteria below **Prompt structure:** 📌 **Contact-level criteria (optional)** - **Job titles**: “Founder” - **Roles**: “Entrepreneurship”, “Business Development”, “Information Technology”, “Legal”, “Accounting”, etc. - **Seniority**: Executive, VP, Director, Manager, Senior Individual Contributor, Other - **Location (city and country only)**: “New York, United States” 📌 **Company-level criteria (optional)** - **Employee count range**: “1–10”, “50–200”, or terms like “small startup”, “SMB”, “mid-market”, “enterprise” - **Industry**: “Business Consulting and Services”, “IT Services and IT Consulting”, etc. - **Technologies**: “AI”, “HubSpot” (may not always work if the database has limited overlap) - **Revenue range (in millions USD)**: “0–1M”, “1–10M”, etc. (availability may vary) The workflow includes **two AI agents** that map your natural language input to the closest existing database filters, so you can write prompts in your own words. ## Email enrichment note The lower part of the workflow (“**Enrichment: Search Data & Email**”) attempts to pull emails from the LeadIQ database for existing leads. Not every lead has an email available, so this step is **optional and limited**. ## Workflow updates I will continue to add new functionality and improve this workflow, including: - Additional enrichment sources - New lead databases - Email sending infrastructure The latest version will always be available on my [Patreon](https://www.patreon.com/growspireagency)

View

Analyze crypto markets with CoinGecko MCP and C1

## Analyze crypto markets with interactive graphs using CoinGecko and C1 by Thesys This n8n template can answer questions about **real-time prices, market moves, trending coins, and token details** with **interactive UI in real time** (cards, charts, buttons) instead of plain text using C1 by Thesys. Data is fetched through the **CoinGecko Free MCP tool**. ### [Check out a working demo of this template here](https://www.thesys.dev/n8n?url=https://www.thesys.dev/n8n?url=https%3A%2F%2Fasd2224.app.n8n.cloud%2Fwebhook%2F51638b0c-7765-4fa8-9b95-a0422128e203%2Fchat). ### What this workflow does 1. A user sends a message in the **n8n Chat** UI (public chat trigger). 2. The **AI Agent** interprets the request. 3. The agent calls **CoinGecko Free MCP** to fetch market data (prices, coins, trending, etc.). 4. The model responds through **C1 by Thesys** with a **streaming, UI** answer. ### Example prompts you can try right away Copy/paste any of these into the chat: - “What’s the current price of Bitcoin and Ethereum?” - “Give me today’s market summary: total market cap, BTC dominance, top gainers/losers.” - “Compare ETH vs SOL over 30 days with a chart.” > Note: This template is for information and visualization, not financial advice. ### How it works 1. User sends a prompt 2. C1 model based on prompt will use CoinGecko MCP to fetch live data 3. C1 Model generates a UI Schema Response 4. Schema is rendered as UI using Thesys GenUI SDK on the frontend ### Setup Make sure you have the following: #### 1️⃣ Thesys API Key You’ll need an API key to authenticate and use Thesys services. 👉 Get your key [here](https://console.thesys.dev/keys) ### What is C1 by Thesys? C1 by [Thesys](https://www.thesys.dev/) is an API middleware that augments LLMs to respond with **interactive UI (charts, buttons, forms)** in real time instead of text. ### Facing setup issues? #### If you get stuck or have questions: - #### 💬 Join the [Thesys Community](https://discord.com/invite/Pbv5PsqUSv) - #### 📧 Email support: [email protected]

View

👨‍💻

Need Custom Automation?

N8N Automation Expert

Specialized in N8N automation, I design custom workflows that connect your tools and automate your processes.