Telegram + Google Gemini, competitor ad intel on demand

Checking competitor ads shouldn’t feel like detective work. But it does, because you’re bouncing between ad libraries, taking screenshots, and trying to remember what “changed” since last week.

This Telegram Gemini ads setup hits performance marketers first, honestly. E-commerce owners and agency leads feel it too, because fast creative decisions depend on fresh intel. The payoff is simple: you ask for a brand in Telegram and you get a clear scorecard back in minutes.

Below you’ll see exactly what this workflow does, what you need to run it, and how teams use it to spot scaling competitors before the scroll gets crowded.

How This Automation Works

The full n8n workflow, from trigger to final output:

n8n Workflow Template: Telegram + Google Gemini, competitor ad intel on demand

Click to explore

flowchart LR

    subgraph sg0["User Sends Message to Bot Flow"]
        direction LR
        n0@{ icon: "mdi:brain", form: "rounded", label: "Validate inputs", pos: "b", h: 48 }
        n1@{ icon: "mdi:robot", form: "rounded", label: "Structured Output", pos: "b", h: 48 }
        n2@{ icon: "mdi:robot", form: "rounded", label: "Analyze user Input", pos: "b", h: 48 }
        n3@{ icon: "mdi:robot", form: "rounded", label: "Structured Output1", pos: "b", h: 48 }
        n4["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Send Message to User Chat"]
        n5["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>User Sends Message to Bot"]
        n6@{ icon: "mdi:cog", form: "rounded", label: "Scrape Ads from Meta and Goo..", pos: "b", h: 48 }
        n7@{ icon: "mdi:robot", form: "rounded", label: "Process Ad Data", pos: "b", h: 48 }
        n8@{ icon: "mdi:brain", form: "rounded", label: "Gemini", pos: "b", h: 48 }
        n9["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Process Initialization Alert"]
        n8 -.-> n7
        n8 -.-> n1
        n7 --> n4
        n0 -.-> n2
        n0 -.-> n3
        n1 -.-> n7
        n2 --> n6
        n2 --> n9
        n3 -.-> n2
        n5 --> n2
        n6 --> n7
    end

    %% Styling
    classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
    classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
    classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
    classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
    classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
    classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
    classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
    classDef disabled stroke-dasharray: 5 5,opacity: 0.5
    class n5 trigger
    class n1,n2,n3,n7 ai
    class n0,n8 aiModel
    classDef customIcon fill:none,stroke:none
    class n4,n5,n9 customIcon

The Problem: Competitor ad research is slow, messy, and easy to skip

You already know you should “keep an eye on competitors.” The problem is the way most teams do it is painful: open an ad library, search a brand, click around, guess what’s new, then paste bits into a doc that nobody reads. Do that for a handful of brands and it quietly eats an hour. Do it every week and you’re spending real time just to end up with a fuzzy conclusion like “they’re running a lot of ads.” Meanwhile, your creative decisions still happen fast, so the intel arrives late or not at all.

The friction compounds. Here’s where it breaks down in the real world.

People rely on screenshots, then can’t search or compare anything later.
Ad counts and “what’s running” get stale fast, so you’re reacting to last week’s reality.
Hooks and angles are subjective when you’re scanning manually, which means your team debates opinions instead of patterns.
No one wants to do this daily, so you miss the moment a competitor starts scaling.

The Solution: Ask in Telegram, get an AI scorecard back

This workflow turns a simple Telegram message into a competitor ad intelligence report. You send a request like “Check ads for Nike” (or any brand). An AI agent interprets your message and extracts the company name, even if you type casually. Then BrowserAct runs a background scrape using your saved “Competitor Ad Activity Monitor” template to pull active campaign listings from ad libraries (such as Facebook or Google, depending on how your BrowserAct template is set). A second AI agent reads what came back and summarizes what matters: how many ads are active, what hooks show up repeatedly, which copy patterns look strongest, and a strategic verdict like “ADVERTISE NOW” or “WAIT.” Finally, n8n sends the formatted HTML scorecard straight back to Telegram so you can act immediately.

The workflow starts with a Telegram bot message. Gemini helps turn messy human input into a clean “brand” value, BrowserAct retrieves the ad listings, and the analyst agent turns that raw scrape into a decision-ready briefing. The only thing you do is ask.

What You Get: Automation vs. Results

What This Workflow Automates

Results You’ll Get

Reads a Telegram message and validates the request.
Extracts the correct brand name from natural language using a Gemini-powered agent.
Scrapes active competitor ad listings via BrowserAct in the background.
Generates a formatted scorecard and sends it back to Telegram automatically.

Most teams get back about 1 hour a week per competitor they track.
You stop losing “good finds” to random screenshots and half-finished notes.
Your team sees hook patterns faster, so new angles come from evidence.
You can spot “scaling vs. inactive” without opening an ad library.
Decisions happen in the same place you already talk (Telegram), which boosts follow-through.

Example: What This Looks Like

Say you track 6 competitors and you do a quick check twice a week. Manually, even a “fast” review is maybe 10 minutes per competitor once you include searching, clicking, and jotting notes, so that’s about 2 hours a week. With this workflow, you send 6 Telegram messages (about 1 minute total), wait a few minutes for the scrape and analysis to finish, and you’re done. You still review the scorecards, but the busywork is gone.

What You’ll Need

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Telegram to send requests and receive scorecards.
BrowserAct for scraping active competitor ad listings.
Google Gemini account (get it from Google AI Studio / Gemini API in Google Cloud)

Skill level: Intermediate. You’ll connect a few credentials, then tweak prompts if you want different verdict logic.

Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).

How It Works

You message your Telegram bot. A Telegram Trigger listens for new messages like “Spy on Higgsfield” or “Check ads for Nike,” and the workflow kicks off immediately.

The workflow understands what you meant. A Gemini chat model plus a structured parser pulls out the brand/company cleanly, so you don’t need to type a strict command format.

BrowserAct retrieves the ad listings. n8n launches your BrowserAct “Competitor Ad Activity Monitor” task in the background and waits for the result to come back with ad data your analyst can use.

An analyst agent writes the scorecard. The second AI agent reviews the scraped listings, counts active ads, summarizes top hooks/copy, and generates a verdict you can act on. Then n8n sends the formatted response back to Telegram (and you can also route it to Slack or a spreadsheet if you want a paper trail).

You can easily modify the verdict rules to match your media buying style based on your needs. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Telegram Trigger

Set up the workflow entry point so incoming Telegram messages start the automation.

Add and open Telegram Message Trigger.
Set Updates to message.
Credential Required: Connect your telegramApi credentials.

Tip: Use the same Telegram bot credentials for both trigger and reply nodes to keep chat context consistent.

Step 2: Connect Telegram and BrowserAct Services

Wire up outbound Telegram responses and the BrowserAct workflow that fetches competitor ads.

Open Send Processing Notice and set Text to =Hello, ok i will look for {{ $json.output.company_name }} ads. i will be rigth back..
Set Chat ID to ={{ $('Telegram Message Trigger').first().json.message.chat.id }}.
Credential Required: Connect your telegramApi credentials in Send Processing Notice.
Open Retrieve Ad Listings and set Type to WORKFLOW and Workflow ID to 70626184596326140.
In workflowConfig.value.input-Company, use ={{ $json.output.company_name }}.
Credential Required: Connect your browserActApi credentials in Retrieve Ad Listings.

⚠️ Common Pitfall: If the BrowserAct workflow expects different input field names, the ads lookup will fail. Ensure input-Company matches the BrowserAct schema.

Step 3: Set Up User Request Interpretation

Configure the AI interpretation layer that extracts the company name from the Telegram message.

Open Interpret User Request and set Text to ={{ $json.message.text }}.
Keep Prompt Type as define and ensure Has Output Parser is enabled.
Open Parsed Company Output and set JSON Schema Example to { "company_name": "company_name" }.
In Input Validation Model, ensure the language model is connected to Interpret User Request and Parsed Company Output.
Credential Required: Connect your googlePalmApi credentials in Input Validation Model.

Tip: Parsed Company Output is a parser sub-node; credentials should be added to the parent model Input Validation Model, not the parser.

Step 4: Configure Parallel Processing and Ad Retrieval

Ensure the workflow runs the ad lookup and the processing notice simultaneously.

Connect Telegram Message Trigger to Interpret User Request.
Interpret User Request outputs to both Retrieve Ad Listings and Send Processing Notice in parallel.
Verify Retrieve Ad Listings connects to Generate Ad Intelligence.

⚠️ Common Pitfall: If the parallel branch is not connected correctly, users won’t receive the “processing” notice while ads are being retrieved.

Step 5: Set Up Ad Intelligence Generation

Analyze ads with the AI agent, then format a Telegram-ready report.

Open Generate Ad Intelligence and set Text to ={{ $json.output.string }}.
Keep Prompt Type as define and ensure Has Output Parser is enabled.
Open Parsed Telegram Payload and set JSON Schema Example to { "TelegramText": "TelegramText" }.
Ensure Gemini Chat Engine is connected as the language model for Generate Ad Intelligence and Parsed Telegram Payload.
Credential Required: Connect your googlePalmApi credentials in Gemini Chat Engine.

Tip: Parsed Telegram Payload is a parser sub-node; credentials should be added to the parent model Gemini Chat Engine.

Step 6: Configure Telegram Reply Output

Send the formatted intelligence report back to the user.

Open Dispatch Telegram Reply and set Text to ={{ $json.output.TelegramText }}.
Set Chat ID to =parameters.chatId=={{ $('Telegram Message Trigger').first().json.message.chat.id }} (Use Channel ID or Chat ID from the Telegram Trigger node).
Enable Parse Mode with HTML to support formatting from the AI response.
Credential Required: Connect your telegramApi credentials in Dispatch Telegram Reply.

Step 7: Test and Activate Your Workflow

Validate the end-to-end flow before turning it on for production.

Click Execute Workflow and send a Telegram message like check ads for Nike to your bot.
Confirm you receive an immediate “processing” notice from Send Processing Notice.
Verify that Dispatch Telegram Reply returns a formatted HTML report with ad counts and a verdict.
When satisfied, toggle the workflow to Active to enable live monitoring.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Common Gotchas

Telegram bot credentials can be correct but still fail if you’re using the wrong chat ID or the bot was never started in that chat. Check the Telegram node settings and your bot conversation first.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Gemini and agent prompts ship generic. Add your brand voice and what you mean by “scaling” early, or you’ll be editing verdicts and summaries every time.

Frequently Asked Questions

How long does it take to set up this Telegram Gemini ads automation?

About 30 minutes if your Telegram bot and BrowserAct template are ready.

Do I need coding skills to automate Telegram competitor ad intel?

No. You’ll connect accounts and paste in a few credentials. The rest is prompt tuning if you want different verdict logic.

Is n8n free to use for this Telegram Gemini ads workflow?

Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in Gemini API usage and your BrowserAct plan.

Where can I host n8n to run this automation?

Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.

Can I customize this Telegram Gemini ads workflow for Slack alerts and a Google Sheets archive?

Yes, and it’s a common upgrade. Keep Telegram as the trigger, then add a Slack node after “Generate Ad Intelligence” to post the verdict to a channel, and add a Google Sheets row creation step to store brand, ad count, hooks, and the raw summary. If you want the scorecard to look different, change the response formatting in the “Dispatch Telegram Reply” step. You can also adjust the “Senior Marketing Analyst” prompt so verdicts prioritize video ads, new angles, or fast ad volume changes.

Why is my Telegram connection failing in this workflow?

Usually it’s the bot token or chat permissions. Regenerate the token in BotFather if you suspect it leaked, then update the Telegram credentials in n8n. Also make sure the bot has been started in the chat you’re trying to message, because Telegram won’t deliver messages to a chat the bot hasn’t been introduced to yet.

How many competitor checks can this Telegram Gemini ads automation handle?

A lot, as long as your BrowserAct and Gemini limits can keep up.

Is this Telegram Gemini ads automation better than using Zapier or Make?

For competitor ad intel, n8n is usually the better fit because you’re combining scraping, AI analysis, and conditional logic in one place. Zapier and Make can do parts of it, but they get clunky when you need multi-step AI prompts, structured parsing, and custom formatting. Self-hosting also changes the math if you run a lot of checks. That said, if you only want a simple “message in, summary out” flow and you hate managing anything, those tools can be fine. Talk to an automation expert if you want a fast recommendation based on volume and team workflow.

Competitor research works best when it’s routine, not a project. Set this up once, then let Telegram deliver the scorecards while you focus on testing and shipping new creative.

Telegram + Google Gemini, competitor ad intel on demand

How This Automation Works

n8n Workflow Template: Telegram + Google Gemini, competitor ad intel on demand

The Problem: Competitor ad research is slow, messy, and easy to skip