n8n competitor AI-visibility monitor (ChatGPT & Gemini)

An n8n competitor AI-visibility monitor answers the question a mention tracker cannot: when a buyer asks ChatGPT or Gemini for a recommendation, do you win, or does a rival get named first? Knowing you appear 40% of the time means little on its own. Knowing you rank third behind two competitors, and that one of them is named first in almost every answer, is something you can act on. This guide builds a free workflow that runs weekly, sends the same buyer questions to both assistants, scores every brand you name, and emails you a ranked leaderboard with mention counts and average position. It takes about 45 minutes to build, or a couple of minutes with the template at the end.

What it does

Each week the workflow sends a set of neutral buyer prompts, the questions people ask before choosing a product like yours, to Google Gemini and OpenAI’s ChatGPT through their official APIs. For every answer it scans for your brand and each competitor you listed, records who was mentioned, and notes the order they appeared in. Being named first in an answer counts for more than being named last, so the workflow tracks position, not just presence.

It then rolls everything into a leaderboard: one row per brand with Gemini mentions, ChatGPT mentions, total mentions, a mention rate across all answer slots, and an average position. The board is sorted so the brand the assistants recommend most sits on top, with average position breaking ties. That snapshot is appended to Google Sheets, so each brand’s standing trends over time, and the same board arrives in your inbox as a table headed by your own rank.

This is the competitive layer of AEO, answer engine optimization. If you only want to know whether your own brand shows up, the simpler brand-mention tracker is the place to start. This monitor is for when you already know you are in the race and want to see the standings. New to n8n? Begin with how to set up n8n.

Why it beats the default

The default competitive check is to open ChatGPT, ask “what is the best tool for X,” eyeball whether you or a rival shows up, and move on. It is a guess, not a measurement. You cannot tell whether a competitor beats you consistently or you just caught a bad answer, and you have no record to compare against next month.

Paid AEO platforms will build a competitor leaderboard, but they cost a monthly subscription, track a prompt list you do not fully control, and keep the history locked in their tool. This workflow ranks exactly the brands you care about, on the exact buyer questions that matter to your market, across both major assistants, for a few cents a run, and writes the history to a sheet you own. Add a competitor, change a prompt, or plug in a third assistant whenever you like. For more AI workflows you can import, see the best n8n AI agent templates and the full template library.

What you need

• An n8n instance (Cloud or self-hosted, version 1.0 or newer).
• A Google Gemini API key (free tier is fine to start). Used as an HTTP Header Auth credential with header x-goog-api-key.
• An OpenAI API key. Used as an HTTP Header Auth credential with header Authorization and value Bearer YOUR_KEY.
• A Google account for Sheets and a Gmail account for the report.
• A blank Google Sheet with a header row matching the field names below.

Time: about 45 minutes from scratch, or under 5 minutes with the template.

Node-by-node list

Eight nodes: a schedule, a config node, two AI calls per prompt, a single scorer that builds the leaderboard, and a fork that both logs and emails.

Weekly schedule (Mon 7am)
        |
   Prompts & brands  (Code: you + competitors + prompt list)
        |
    Ask Gemini  ──►  Ask ChatGPT
                          |
                   Build leaderboard  (Code: score + rank every brand)
                       |            |
        Log leaderboard to Sheets   Build email
                                        |
                               Send digest email (Gmail)
  

1. Weekly schedule (Schedule Trigger) fires every Monday at 7am.
2. Prompts & brands (Code) holds your brand, competitors, and prompts, one item per prompt.
3. Ask Gemini (HTTP Request) sends each prompt to the Gemini API.
4. Ask ChatGPT (HTTP Request) sends the same prompt to the OpenAI API.
5. Build leaderboard (Code) reads every answer, scores all brands, and outputs one ranked row per brand.
6. Log leaderboard to Sheets (Google Sheets) appends the snapshot.
7. Build email (Code) formats the board and highlights your rank.
8. Send digest email (Gmail) emails you the leaderboard.

Step-by-step build

1. Add the weekly schedule

Add a Schedule Trigger, interval Weeks, every 1 week, day Monday, hour 7. Weekly matches how slowly AI answers shift and keeps API usage tiny.

2. Set your brand, competitors, and prompts

Add a Code node. It emits one item per prompt and carries the full brand list on each item so the scorer can rank everyone.

const YOU = 'Acme Analytics';
const COMPETITORS = ['DataPulse', 'Insightly', 'MetricForge'];
const BRANDS = [YOU, ...COMPETITORS];
const PROMPTS = [
  'What are the best analytics tools for a small ecommerce store?',
  'Which tools help a SaaS startup track marketing ROI?',
  'Recommend affordable business intelligence software for a small team.',
  'What is a good tool for automated weekly sales reports?',
  'Best alternatives to a spreadsheet for tracking KPIs?'
];
return PROMPTS.map(p => ({ json: { prompt: p, brands: BRANDS, you: YOU } }));

3. Ask Gemini

Add an HTTP Request node, method POST. Under Authentication choose Generic Credential Type then Header Auth, and store your key under the header x-goog-api-key. Set the body to JSON:

URL:  https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent

JSON body:
={{ JSON.stringify({ contents: [ { parts: [ { text: $('Prompts & brands').item.json.prompt } ] } ] }) }}

4. Ask ChatGPT

Add a second HTTP Request node, method POST. Store your OpenAI key under the header Authorization with value Bearer then your key. Body JSON:

URL:  https://api.openai.com/v1/chat/completions

JSON body:
={{ JSON.stringify({ model: 'gpt-4o-mini', messages: [ { role: 'user', content: $('Prompts & brands').item.json.prompt } ] }) }}

5. Build the leaderboard

Add a Code node. It runs once for all items, reads every Gemini and ChatGPT answer, and for each brand counts mentions and averages the order it was named. It outputs one ranked row per brand.

const cfgAll = $('Prompts & brands').all().map(i => i.json);
const gem = $('Ask Gemini').all().map(i => i.json);
const oa = $('Ask ChatGPT').all().map(i => i.json);
const brands = cfgAll[0].brands;
const you = cfgAll[0].you;
const N = cfgAll.length;

const txt = v => (v == null ? '' : String(v));
const geminiText = i => txt(gem[i]?.candidates?.[0]?.content?.parts?.[0]?.text);
const openaiText = i => txt(oa[i]?.choices?.[0]?.message?.content);

const stat = {};
for (const b of brands) stat[b] = { brand: b, gemini_mentions: 0, chatgpt_mentions: 0, pos_sum: 0, pos_count: 0 };

function scoreAnswer(text, assistant) {
  const lower = text.toLowerCase();
  const found = brands
    .map(b => ({ b, idx: lower.indexOf(b.toLowerCase()) }))
    .filter(x => x.idx >= 0)
    .sort((a, b) => a.idx - b.idx);
  found.forEach((x, rank) => {
    if (assistant === 'gemini') stat[x.b].gemini_mentions++;
    else stat[x.b].chatgpt_mentions++;
    stat[x.b].pos_sum += (rank + 1);
    stat[x.b].pos_count++;
  });
}

for (let i = 0; i < N; i++) { scoreAnswer(geminiText(i), 'gemini'); scoreAnswer(openaiText(i), 'chatgpt'); }

const reportDate = new Date().toISOString().slice(0, 10);
const totalSlots = N * 2;
const rows = brands.map(b => {
  const s = stat[b];
  const total = s.gemini_mentions + s.chatgpt_mentions;
  return {
    report_date: reportDate, brand: b, is_you: b === you ? 'yes' : 'no',
    gemini_mentions: s.gemini_mentions, chatgpt_mentions: s.chatgpt_mentions,
    total_mentions: total, mention_rate_pct: Math.round((total / totalSlots) * 100),
    avg_position: s.pos_count ? Math.round((s.pos_sum / s.pos_count) * 10) / 10 : ''
  };
});
rows.sort((a, b) => b.total_mentions - a.total_mentions || ((a.avg_position === '' ? 99 : a.avg_position) - (b.avg_position === '' ? 99 : b.avg_position)));
return rows.map(r => ({ json: r }));

A leaderboard row looks like this:

{
  "report_date": "2026-08-24",
  "brand": "DataPulse",
  "is_you": "no",
  "gemini_mentions": 4,
  "chatgpt_mentions": 5,
  "total_mentions": 9,
  "mention_rate_pct": 90,
  "avg_position": 1.3
}

6. Log to Google Sheets and email the board

Add a Google Sheets node (operation Append Row, mapping Map Automatically) with a header row of report_date, brand, is_you, gemini_mentions, chatgpt_mentions, total_mentions, mention_rate_pct, avg_position. Then add a Code node to format the board and a Gmail node (Email Type HTML) mapping the subject and message from it. The email leads with your rank: “You rank #3 of 4 with a 50% mention rate.”

Save and activate. Every Monday you get a standings table you can actually plan against.

Common mistakes

• Naming a brand in the prompt. It rigs the result. Prompts must be neutral buyer questions.
• Short or generic brand names. They match inside other words and inflate scores. Track full, distinctive names and tighten the match to whole words if needed.
• Reading $json for Gemini in the scorer. After the ChatGPT node, $json is the OpenAI item. Pull both answer sets with $('Ask Gemini').all() and $('Ask ChatGPT').all().
• Comparing runs with different prompt lists. Change the prompts and the trend breaks. Lock a core set and only add to it deliberately.
• Mismatched Sheet headers. Automatic mapping needs exact column names, or columns land blank.

Cost at realistic volume

Two API calls per prompt, one Sheets append per brand, one email per run.

A competitive AI-visibility leaderboard for a few cents a month. The paid platforms that produce the same board start around fifty dollars a month.

Frequently asked questions

Related guides

• Track brand mentions in ChatGPT and Gemini — the simpler yes/no self-check to start with.
• Best n8n AI agent templates — more AI workflows you can import.
• How to set up n8n — the setup prerequisite if you are starting out.
• Browse all n8n templates.
• More AI agent and chatbot guides.