# AI use cases for Scout (outcrawlai/scout)

Repo: [outcrawlai/scout](https://github.com/outcrawlai/scout) | Use cases: 4 | Page: https://dedupedai.com/use-cases/outcrawlai-scout/

Scout is an open-source TypeScript agent that uses a real browser to carry out a task described in plain words and returns the answer.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Pull a ranked list from a website with one task: https://dedupedai.com/use-cases/outcrawlai-scout/research-top-stories-from-a-site/
- Compare prices and stock across product pages: https://dedupedai.com/use-cases/outcrawlai-scout/compare-products-across-pages/
- Fill in a web form and confirm what the site received: https://dedupedai.com/use-cases/outcrawlai-scout/fill-web-form-and-confirm-receipt/
- Sign in to a site and read back the account page: https://dedupedai.com/use-cases/outcrawlai-scout/sign-in-and-read-account-page/

## How to pull a ranked list from a website with one task with Scout

Repo: [outcrawlai/scout](https://github.com/outcrawlai/scout) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Have Scout open a site, read the page and report the items you asked for, with links.

**Who it is for:** An analyst, researcher or founder who needs the current top items from a public site and wants them pulled without manual browsing.

**The problem:** Reading through a site page by page to collect the same few facts is slow and easy to get wrong.

**The outcome:** A short, sourced answer such as the top three stories with their links and comment counts, plus a replay link to check how Scout got there.

### Steps

1. Run `npm i @outcrawl/scout` in your project folder.
2. Run `export OUTCRAWL_API_KEY=your-outcrawl-key`, then set `SCOUT_BASE_URL`, `SCOUT_API_KEY` and `SCOUT_HANDS_MODEL` to your model service.
3. Save the README's three-step example as `task.ts` and change the task text to your research question.
4. Run `npx tsx task.ts` and read `result.data`.
5. Open `result.replayUrl` and confirm the answer matches what the page shows.

### Prompt to paste into your agent

```text
Use the outcrawl/scout repo (TypeScript, npm package @outcrawl/scout). Build a task.ts that opens <target site URL> on Outcrawl's cloud browser and reports <the items you need> with links. Print result.data and result.replayUrl. Verify that result.status is completed and that each reported item appears on the replay.
```

### Caveat

Scout runs model calls against the service you configure, so answer quality depends on the model you choose for the hands job.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/outcrawlai-scout/research-top-stories-from-a-site/

## How to compare prices and stock across product pages with Scout

Repo: [outcrawlai/scout](https://github.com/outcrawlai/scout) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Give Scout two or more products and get back a comparison of price and availability.

**Who it is for:** A shopper or buyer who needs to choose between items on different pages and does not want to copy numbers by hand.

**The problem:** Comparing price and stock across separate pages means opening each one, reading the figures and recording them.

**The outcome:** A written comparison of price and stock for each item, stating which is cheaper, with a replay to check the figures.

### Steps

1. Run `npm i @outcrawl/scout` in your project folder.
2. Run `export OUTCRAWL_API_KEY=your-outcrawl-key`, then set `SCOUT_BASE_URL`, `SCOUT_API_KEY` and `SCOUT_HANDS_MODEL`.
3. Copy the README's example into `task.ts` and replace the task with your two product names or links.
4. Run `npx tsx task.ts`.
5. Check `result.data` against the replay at `result.replayUrl` before you buy.

### Prompt to paste into your agent

```text
Use the outcrawl/scout repo to build task.ts that finds <product A> and <product B> on <site URL> and compares their price and stock, then states which is cheaper. Print result.data and result.replayUrl. Verify that both prices in the answer match the replay before trusting the result.
```

### Caveat

Scout reads what the page shows at run time, so prices and stock can change between the run and your purchase.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/outcrawlai-scout/compare-products-across-pages/

## How to fill in a web form and confirm what the site received with Scout

Repo: [outcrawlai/scout](https://github.com/outcrawlai/scout) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Give Scout the form details and get back exactly what the site recorded.

**Who it is for:** An office or operations worker who must submit the same web form repeatedly and needs proof of what was entered.

**The problem:** Re-keying the same details into a web form is repetitive, and nobody checks what the site actually stored.

**The outcome:** The form is submitted and the answer states what the site showed as received, with a replay as evidence.

### Steps

1. Run `npm i @outcrawl/scout` in your project folder.
2. Run `export OUTCRAWL_API_KEY=your-outcrawl-key`, then set `SCOUT_BASE_URL`, `SCOUT_API_KEY` and `SCOUT_HANDS_MODEL`.
3. Save the README's example as `task.ts` and write your form task, with the exact values to enter.
4. Run `npx tsx task.ts`.
5. Read `result.data` and `result.error`, then open `result.replayUrl` to check the submission.

### Prompt to paste into your agent

```text
Use the outcrawl/scout repo to build task.ts that fills in the form at <form URL> with <the field values> and reports exactly what the site shows as received. Print result.data, result.status and result.replayUrl. Verify that the status is completed and the replay shows the submitted values.
```

### Caveat

Scout submits forms on real sites, so test on a sandbox or low-stakes form first, since a finished run cannot be undone by Scout.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/outcrawlai-scout/fill-web-form-and-confirm-receipt/

## How to sign in to a site and read back the account page with Scout

Repo: [outcrawlai/scout](https://github.com/outcrawlai/scout) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Have Scout log in with your details and report what the account page says.

**Who it is for:** A person who checks an online account regularly and wants a status summary without signing in by hand each time.

**The problem:** Logging in and reading one account page every day takes time, and the same steps repeat.

**The outcome:** A short report of what the signed-in page shows, such as a welcome message or a status line, with a replay.

### Steps

1. Run `npm i @outcrawl/scout` in your project folder.
2. Run `export OUTCRAWL_API_KEY=your-outcrawl-key`, then set `SCOUT_BASE_URL`, `SCOUT_API_KEY` and `SCOUT_HANDS_MODEL`.
3. Copy the README's example to `task.ts` and write the sign-in task, keeping your details in environment variables rather than in the file.
4. Run `npx tsx task.ts`.
5. Open `result.replayUrl` and confirm which page Scout read after signing in.

### Prompt to paste into your agent

```text
Use the outcrawl/scout repo to build task.ts that signs in to <site URL> using the credentials in environment variables and reads the welcome message on the account page. Print result.data and result.replayUrl. Verify that result.status is completed and that the replay shows the signed-in account page.
```

### Caveat

The README gives no details on how Scout stores or protects the credentials you pass, so check that before using a sensitive account.

Risk, credentials: Scout will use your sign-in details and sends the page content to your model service, so use an account you control and keep the details out of source files and shared replays.

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/outcrawlai-scout/sign-in-and-read-account-page/