Agent skill, intermediate

Check AI search visibility, as a skill your agent installs.

AI search visibility API for an agent: it sends a prompt your buyers would ask and a country to a catalog endpoint and reads answer text, cited sources and brands mentioned back. Several providers sell the call, so the agent tries the cheapest first. You pay per call, and a failed call costs nothing.

Give this to your agent
set up looot - https://looot.ai/skill.md

Install

How do I install this skill?

Two steps. Set up looot once, then save this skill file where your agent reads skills.

1. Set up looot once

Give this line to your agent
set up looot - https://looot.ai/skill.md

Works in Claude Code, Cursor, Codex and ChatGPT through MCP. Searching and inspecting are free.

2. Save the skill

Save the skill file for Claude Code
mkdir -p ~/.claude/agent-skills/looot-ai-search-visibility && curl -fsSL https://looot.ai/agent-skills/ai-search-visibility/SKILL.md -o ~/.claude/agent-skills/looot-ai-search-visibility/SKILL.md

Or open the raw SKILL.md and drop it into the skills folder of your own agent.

When it starts

What do I say to start this skill?

Any of these starts it. The agent asks for what is missing, nothing more.

  • Example prompt
    does ChatGPT mention our brand for this prompt

  • Example prompt
    what sources does the AI cite for best project management tools

  • Example prompt
    check how AI answers rank us against competitors

It asks for

  • The prompt a buyer would ask
  • The brand names to look for
  • The country

It hands back

  • Answer text
  • Cited sources
  • Brands mentioned
  • Shopping cards
  • Search queries the engine ran

Say which brands the answer named, in what order, and which sources it cited. One run is one sample, so say that answers vary.

How it runs

What does the agent do when it runs?

Four moves, in this order, with the price known before any money moves.

  1. Step 1

    Discover

    looot discover finds the endpoints that match the task. It is free.

  2. Step 2

    Inspect

    looot inspect shows the price and the exact input before anything is spent. It is free.

  3. Step 3

    Run

    looot run executes the call with an idempotency key, so a retry never charges twice. The agent reads the run status, not the HTTP code.

  4. Step 4

    Fall back

    On a provider error or a timeout the agent tries the next endpoint in the skill, cheapest first. It never retries a bad input elsewhere.

Providers, cheapest first

What actually differs between providers

Today the price runs from $0.0015 to $0.0088 across 6 endpoints. The dearest costs about 5.9 times the cheapest. Price is only one difference. Each entry below says what that endpoint takes or returns that the others do not.

  1. Bright Data logoBright Data

    Asks ChatGPT through a scraper and returns the answer text and its citations, with a follow-up prompt option.

    brightdata-chatgpt-answer
    $0.0015 / result
  2. AnyAPI logoAnyAPI

    Returns the AI Overview Google generates for a prompt, with every source it lists.

    anyapi-run-google-ai-overview
    $0.0018 / call
  3. SearchAPI.io logoSearchAPI.io

    Queries logged-out ChatGPT and returns Markdown and typed text blocks plus the cited links when web search is on.

    searchapi-io-chatgpt
    $0.0040 / call
  4. DataForSEO logoDataForSEO

    Returns Google AI Mode results in the advanced format.

    dataforseo-google-ai-mode-advanced
    $0.0040 / call
  5. Cloro logoCloro

    Runs a prompt through the live Gemini interface and returns the answer with its cited sources, as text, Markdown or HTML.

    cloro-monitor-gemini
    $0.0064 / call
  6. Cloro logoCloro

    Runs a prompt through the live ChatGPT interface from a chosen country, with cited sources, brand entities and, on request, shopping cards and ads.

    cloro-monitor-chatgpt
    $0.0088 / call

Cost

What 100 runs of this skill cost

$0.1500

100 prompts cost about $0.1500 through the cheapest endpoint, at Bright Data, and about $0.8800 through the dearest. Each run is one call. The cheapest endpoint bills per result, so the figure assumes one result per run.

The file

What is inside the SKILL.md?

The whole file, as your agent reads it. No price is written in it: the agent reads the live price with looot inspect.

SKILL.md for Check AI search visibility
---
name: looot-ai-search-visibility
description: Check AI search visibility. Use when the user says things like "does ChatGPT mention our brand for this prompt", "what sources does the AI cite for best project management tools" or "check how AI answers rank us against competitors". Runs through looot, billed per call.
---

# Check AI search visibility

AI search visibility API for an agent: it sends a prompt your buyers would ask and a country to a catalog endpoint and reads answer text, cited sources and brands mentioned back. Several providers sell the call, so the agent tries the cheapest first. You pay per call, and a failed call costs nothing.

This skill needs the looot skill set up first: https://looot.ai/skill.md

## Ask for these inputs

The job takes a prompt your buyers would ask and a country. Example: best project management tools for small teams.

- The prompt a buyer would ask
- The brand names to look for
- The country

## Run it

1. Find the endpoint: `looot discover --mode auto --query "ai search visibility"`. The endpoints listed below are the known matches.
2. Read the price and the input schema before spending: `looot inspect <endpoint-id>`. Tell the user the price, then run.
3. Run it: `looot run cloro-monitor-chatgpt --input '{"prompt":"best project management tools for small teams","country":"US"}' --idempotency-key <new-key> --wait`. Reuse the same key only to retry the same request.
4. Read the run's `status` and `error`, not the HTTP status. A run can return `failed` with a normal response.
5. If a run fails with a provider error or times out, try the next endpoint from the list below, cheapest first. If it fails on your input (a 4xx style error), fix the input. Do not retry it on other providers.

## Endpoints

Each endpoint reads the same job from a different provider. They differ in inputs, fields and price. Run `looot inspect` on the ones that take the input you hold, start with the cheapest, and move to the next on a provider error.

- `cloro-monitor-chatgpt`: runs a prompt through the live ChatGPT interface from a chosen country, with cited sources, brand entities and, on request, shopping cards and ads
- `cloro-monitor-gemini`: runs a prompt through the live Gemini interface and returns the answer with its cited sources, as text, Markdown or HTML
- `brightdata-chatgpt-answer`: asks ChatGPT through a scraper and returns the answer text and its citations, with a follow-up prompt option
- `searchapi-io-chatgpt`: queries logged-out ChatGPT and returns Markdown and typed text blocks plus the cited links when web search is on
- `dataforseo-google-ai-mode-advanced`: returns Google AI Mode results in the advanced format
- `anyapi-run-google-ai-overview`: returns the AI Overview Google generates for a prompt, with every source it lists

## What comes back

- Answer text
- Cited sources
- Brands mentioned
- Shopping cards
- Search queries the engine ran

## Answer rule

Say which brands the answer named, in what order, and which sources it cited. One run is one sample, so say that answers vary.

## Before you start

- Write prompts the way buyers ask, not the way you would search. A long question gets a different answer from a short keyword.
- Run each prompt more than once. An engine can answer differently each time, and Google regenerates its AI Overview on every search.
- Check the country. Each engine refuses a few countries, and an answer from the US is not the answer a buyer in Germany sees.

## Cost rules

- Searching and inspecting are free. Running is billed per call at the price `looot inspect` shows.
- Say the price before the first run, and the total after a batch.
- Never loop a failing call. Stop after two failures and report what failed.

## When not to use this skill

Use `looot-google-serp` instead when you want the classic ranked results, not an AI answer.

Page for people: https://looot.ai/agent-skills/ai-search-visibility

Wrong fit

When should I use a different skill?

Use Read a Google results page when you want the classic ranked results, not an AI answer.

FAQ

What do people ask about this skill?

Run a set of buyer prompts through the AI engines and read the answers. Your agent returns each answer, the sources it cited and whether your brand name appears. Repeat it to see how stable the result is.

ChatGPT, Gemini, Google AI Mode and Google AI Overview, through different endpoints. The notes above say which provider covers which engine.

Language models generate text, so the wording and the sources change. Google regenerates the AI Overview for each search. Run each prompt several times and look for the pattern.

Yes. Most endpoints return the cited sources with the answer. Your agent can list the domains cited most often, which shows where you would need to be mentioned.

It gives you a snapshot each time you run it. Running the set on a timer needs scheduled runs, not available yet, so ask your agent to run it whenever you want a fresh reading.

You pay per call, and the price depends on the provider your agent picks. This page reads the cheapest live price from the catalog and shows no number when the catalog is unreachable.

No. A call that fails at the provider costs nothing, and your agent can retry it or send it to another provider.

No. One looot key reaches every provider in the catalog. You top up once, and each call is billed at the price shown before it runs.

Send a POST to /v1/runs with the endpoint id, the input and a new idempotency key, and your looot token in the Authorization header. With wait set to 30, the answer comes back in the response when the run ends within 30 seconds. Otherwise poll GET /v1/runs/<runId>.

That needs scheduled runs, not available yet. Run it by hand whenever you want fresh results.

No. looot bills per call, and nothing runs while your agent is idle.

The same job as a page with the full price ladder: AI search visibility API for AI agents. Updated 2026-10-04.

Platforms and providers behind this skill

For agents
skill
looot-ai-search-visibility
file
https://looot.ai/agent-skills/ai-search-visibility/SKILL.md
difficulty
intermediate
input
a prompt your buyers would ask and a country
endpoint
cloro-monitor-chatgpt
endpoint
cloro-monitor-gemini
endpoint
brightdata-chatgpt-answer
endpoint
searchapi-io-chatgpt
endpoint
dataforseo-google-ai-mode-advanced
endpoint
anyapi-run-google-ai-overview
setup
https://looot.ai/skill.md
llms.txt
https://looot.ai/llms.txt
updated
2026-10-04

Try this skill with your own agent.

Start your workspace, top up, and save the skill where your agent reads it.