# AI use cases for Assay (awss1i/assay)

Repo: [awss1i/assay](https://github.com/awss1i/assay) | Use cases: 3 | Page: https://dedupedai.com/use-cases/awss1i-assay/

assay is an agent-native command-line QA tool that opens a local web page in Chromium, uses every control it finds, and reports what went wrong, with no tests to write and no LLM.

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

- Catch broken controls in a page an agent just wrote: https://dedupedai.com/use-cases/awss1i-assay/check-agent-written-page-before-handoff/
- Produce a visual QA report for a page with screenshots: https://dedupedai.com/use-cases/awss1i-assay/generate-html-qa-report-with-screenshots/
- Stop a build when a page fails Assay checks: https://dedupedai.com/use-cases/awss1i-assay/gate-a-page-build-on-assay-exit-code/

## How to catch broken controls in a page an agent just wrote with Assay

Repo: [awss1i/assay](https://github.com/awss1i/assay) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Run Assay after an agent finishes a page and get a one-line pass or fail result.

**Who it is for:** A developer using a coding agent to build a small web app, who needs to know the page works before accepting the agent's reply.

**The problem:** A page can look right in the code and still throw errors, ignore clicks, or show wrong counts once someone uses it.

**The outcome:** The developer gets a short summary listing the page checked, the number of checks run, and anything flagged.

### Steps

1. Run `pip install assay-ui` to install the tool.
2. Run `assay ./my-app --one-line` against the folder that holds the page, replacing ./my-app with your folder.
3. Read the summary line, which reports the page checked, the number of checks, and anything flagged.
4. If anything is flagged, have the agent fix the listed problem and run the same command again.

### Prompt to paste into your agent

```text
Use the assay CLI from the assay-ui package on the page in <folder path>. Run assay <folder path> --one-line, then report the one-line summary in your reply. Verify that the exit code is zero before you tell the user the page passed.
```

### Caveat

Assay checks whether the page responds and contradicts itself, so it cannot confirm that the page does the wrong or right job for its purpose.

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/awss1i-assay/check-agent-written-page-before-handoff/

## How to produce a visual QA report for a page with screenshots with Assay

Repo: [awss1i/assay](https://github.com/awss1i/assay) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Write an HTML report that shows what Assay checked and what failed, with screenshots.

**Who it is for:** A developer or product owner who wants a readable record of a page's checks to review or share before a release.

**The problem:** A terminal summary does not show which control failed or what the page looked like at that moment.

**The outcome:** An HTML file that lists the checks and includes screenshots, which can be opened in a browser.

### Steps

1. Run `pip install assay-ui` to install the tool.
2. Run `assay ./my-app --report out.html`, replacing ./my-app with your page folder.
3. Open out.html in a browser and review the flagged checks and their screenshots.
4. Share or archive out.html with the team, or re-run after fixes to produce a new report.

### Prompt to paste into your agent

```text
Use the assay-ui package to check the page folder <folder path> and write an HTML report to <report path>. Run assay <folder path> --report <report path>, then confirm the report file exists and list the flagged checks from the terminal output.
```

### Caveat

The report only covers what Assay's rules can observe on the page, so a clean report does not prove the page meets its requirements.

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/awss1i-assay/generate-html-qa-report-with-screenshots/

## How to stop a build when a page fails Assay checks with Assay

Repo: [awss1i/assay](https://github.com/awss1i/assay) | Difficulty: Advanced | Time: 30 minutes | Basis: From the README

Use Assay's non-zero exit code to block a page from moving forward when it has a flagged problem.

**Who it is for:** A developer who maintains a static site and wants a script to refuse a build that contains a broken control.

**The problem:** A broken button or a count that goes wrong can ship unnoticed when nothing checks the built page.

**The outcome:** A script that stops with an error when Assay flags a problem and passes when the page is clean.

### Steps

1. Run `pip install assay-ui` on the machine that runs the build.
2. Run the build step that writes the built page output to a folder.
3. Add `assay <built folder> --one-line` after the build step in your script, replacing <built folder> with the output path. (inferred, check the README)
4. Confirm the script stops when a known broken page is used as input, then keep the step in place.

### Prompt to paste into your agent

```text
Add an assay check to the build script in <repo path>. After the build writes to <output folder>, run assay <output folder> --one-line and stop the script if the exit code is non-zero. Verify by running the script against a page with a known broken control and confirming it stops.
```

### Caveat

Assay only checks built output, so it will not run your build or npm install for you, and the build step must be run first.

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/awss1i-assay/gate-a-page-build-on-assay-exit-code/