# Our agent looks at your store the way each AI agent does.

> Aiscovery Scout, our own agent, reads your store's key tasks as a screenshot, page text, page without scripts and robots.txt, and shows each trap with the agents it affects and who should fix it.

- Canonical URL: https://aiscovery.io/product/scout
- Markdown version: https://aiscovery.io/product/scout.md
- Last updated: 2026-10-21

Aiscovery Scout · our agent

Aiscovery Scout reads each key task as a screenshot, as page text, without scripts and through robots.txt, then shows you the traps before an agent runs into them.

- [Request a demo](https://aiscovery.io/demo)
- [Look through the lenses](https://aiscovery.io/product/scout#lenses)

## Example Scout check

> Interactive demo on the HTML page: the same example product page side by side: what people see on one side and one of Scout's lenses (Screenshot, Page text, Page without scripts, robots.txt) on the other, with a handle to drag between them and Scout's note for the chosen lens. Its content is written out below.

> Example data, not a real store. Store: northwind-outdoor.example/products/court-low-sneaker.

### Screenshot

What computer use agents get: one screenshot of the first screen.

```
Northwind
New Men Women Sale
Search for: [Search]
--- First screenshot ends here ---
Court Low Sneaker
75.00 Add to cart
```

**Trap found: Price and Add to cart are not in the first screenshot.** The page draws without its styles, so a big logo fills the first screen and the search box is the only thing left to click.

- Affects: Computer use agents
- Fix on your website. Fix: Let agents load your theme files. See the robots.txt lens.
- Clear in this lens: Search box, store name

### Page text

What page-text agents read: the text and links once the page has loaded.

```
GET /products/court-low-sneaker
img: court-low.jpg
h1: Court Low Sneaker (Clear)
price: 75.00 (Clear)
sizes: US 8, US 9, US 10 (Clear)
button: Add to cart (Clear)
delivery: calculated at checkout (Trap found)
```

**Trap found: The delivery cost isn't in the page text.** The key task asks what delivery costs. The page only says it is calculated at checkout, and agents stop before checkout.

- Affects: All agents
- Fix on your website. Fix: Put delivery prices as text on the product page or a linked shipping page.
- Clear in this lens: Product name, price, sizes, Add to cart

### Page without scripts

The page before any script runs. Scout follows its links to every page the key task needs.

```
GET /products/court-low-sneaker 200
scripts: not run
h1: Court Low Sneaker (Clear)
price: 75.00 (Clear)
sizes: added later by a script (Not in this lens)
button: added later by a script (Not in this lens)
link: Returns, /pages/return-policy 404 (Trap found)
```

**Trap found: The footer's Returns link leads to a missing page.** The link points to /pages/return-policy, which answers 404. The real returns page isn't linked from anywhere Scout could reach.

- Affects: All agents
- Fix on your website. Fix: Point the Returns link at the policy page that exists.
- Clear in this lens: Product name, price

### robots.txt

Your robots.txt, read before anything else, the way a browser that follows it does.

```
GET /robots.txt 200
read before any page
User-agent: *
Disallow: /cart
Disallow: /checkout
Disallow: /assets/theme/ (Trap found)
blocks: theme.css, product.js (Not in this lens)
```

**Trap found: robots.txt blocks the theme's style and script files.** A browser that follows robots.txt loads the page without them. That is why the screenshot looks broken.

- Affects: Computer use agents
- Fix on your website. Fix: Remove Disallow: /assets/theme/ or allow its .css and .js files.
- Clear in this lens: Product pages, images

## The traps Scout looks for

In your dashboard: Possible traps for AI agents (Available)

Each one comes with the evidence Scout saw, the agents it affects and who should fix it.

### The fact isn't on the page

The price, stock or delivery cost a key task looks for is missing from the page, or has changed.

- Lenses: Page text, Page without scripts
- Affects: All agents
- Owner: Fix on your website, Update the key task

### No path by links

The page an agent needs isn't linked from where the task starts, or a link on the way is broken.

- Lenses: Page without scripts
- Affects: All agents
- Owner: Fix on your website

### Page files blocked

robots.txt blocks the styles and scripts a page needs, so a browser that follows it draws the page broken.

- Lenses: robots.txt
- Affects: Computer use agents
- Owner: Fix on your website

### The screenshot shows less

One element fills the first screen, or every page looks the same, so an agent working from screenshots has nothing useful to click.

- Lenses: Screenshot
- Affects: Computer use agents
- Owner: Fix on your website, On our side

### Rules that close the way in

Search is the main way to find the product, but the task rules don't let agents type, or robots.txt closes search.

- Lenses: Task rules, robots.txt
- Affects: Agents that type in search
- Owner: Change the task rules, Fix on your website

### Not enough time

An agent usually needs longer than the key task allows, so it would stop halfway through.

- Lenses: Task rules
- Affects: Agents that need longer
- Owner: Change the task rules

### Still being calibrated (Coming later)

Pop-ups over the price, prices only in an image, buttons without names, content inside frames, bot walls and duplicate buttons. We show them once real agent runs back them up.

## How Scout works

The same four moves on every key task, so a trap means the same thing next time.

1. **Read the key-task path.** Scout takes a key task and the pages it should pass through, inside the rules the store owner approved.
2. **Look through each agent's eyes.** On every page it takes a screenshot, reads the page text, loads the page without scripts and checks robots.txt and the task rules. Lenses: Screenshot, Page text, Page without scripts, robots.txt.
3. **Evidence, owner and fix.** Each trap shows what Scout saw, which agents it affects and who should act: your website, the key task, the task rules or us.
4. **Real agent runs confirm or refute.** When agents try the same task, their runs show whether Scout was right: a real agent run failed here too, or agents got past it.

## Two jobs on the same store.

A shopper's agent and Scout look at your pages for different reasons. You need both.

### A shopper's agent tries the task once.

- Reads the page one way: its own
- Follows one path to an answer
- Shows where it got stuck, after it happened

### Aiscovery Scout checks every way agents read the page.

Lenses: Screenshot, Page text, Page without scripts, robots.txt, Task rules.

- Sees each page the way different agents do
- Walks the key-task path page by page
- Points at the trap, who it catches and who fixes it, before a run

Scout doesn't replace real agent runs. It shows where to look, and the runs show whether it was right.

## Read-only, inside the rules you approved.

Scout reads public pages on the key tasks the store owner approved. It reads robots.txt first, goes one page per second and stops before login, cart, checkout and payment. It never logs in, fills in forms or pays.

If a bot wall or a firewall stops it, Scout says Couldn't check and never tries to get around it. Your agent test runs come first: Scout waits while one is running on your site.

- Read-only
- Only what the owner approved
- robots.txt first
- One page per second
- Never logs in or pays

Scout stops before: Login, Cart, Checkout, Payment, Forms that send data.

## What runs today

Scout runs for launch partners now. Everything else is labelled.

| Capability | Status |
| --- | --- |
| Scout on your key tasks, for launch partners | Available |
| Traps with evidence, affected agents, owner and fix | Available |
| More traps: pop-ups, prices in images, unnamed buttons | Coming later |
| Weekly Scout with alerts | Coming later |
| Choosing the AI model that double-checks screenshots | Coming later |

## Questions about Scout

**Q: Is Scout a score for my store?**

A: No. Scout gives no single score. It shows concrete traps, each with evidence, the agents it affects and who should fix it. Clear means Scout found no trap in that lens, not that agents will succeed.

**Q: Does Scout replace real AI agent test runs?**

A: No. Real agents try your key tasks and show what happens. Scout looks first, so you can fix the obvious traps before you spend a test run on them, and the runs show whether Scout was right.

**Q: Does a Scout check use up my test runs?**

A: No. Scout runs separately and doesn't count against your plan's monthly test runs.

**Q: What if Scout can't see a page?**

A: If a bot wall, a firewall or robots.txt stops it, Scout says Couldn't check for that page. It never gets around protection, and it never counts that against your site.

## See the traps on your own store.

Leave three details. We run Scout on your key tasks first, then walk you through what it found.

[Request a demo](https://aiscovery.io/demo)

Have a real workflow to test now? [Apply as a launch partner](https://aiscovery.io/partners)

---

This is the Markdown version of the page for AI agents. The HTML page at the canonical URL is authoritative. Site index: https://aiscovery.io/llms.txt