Screenery / Compare / Promptless

Promptless alternative for docs screenshots

Promptless is an AI agent that keeps customer-facing docs up to date. Its Capture feature signs in to your app with a test account and re-takes screenshots when the UI changes. Screenery does one narrower job. It publishes the screenshots your own Playwright tests take in CI, at URLs your docs embed once.

The short answer

• Pick Promptless if you want an agent to write and update the words in your docs, and screenshots are one part of that. It suits a docs team that has no screenshot tests, and it crops and annotates for you.
• Pick Screenery if you only need the images to stay current and you already run Playwright. Screenshots come from code you review, run in your CI, and pass a visual regression gate before Screenery publishes them. No agent signs in to your app.

Side by side

Promptless details checked October 2026 on its own site. See Sources.

What Promptless does well

• It writes the docs too. Screenshots are one part of a tool that drafts text updates from pull requests, Slack and support tickets, then delivers them to your docs platform.
• No test suite needed. Navigation guidance in plain language replaces test code.
• Crops and annotations. Its editor handles the finishing work a docs writer would otherwise do by hand.
• Triggered by code changes. It watches pull requests and commits, so re-captures follow the work that changed the UI.
• Honest docs. Its own guide lists the failure modes to watch for, such as a login page or a loading spinner in the shot, and how to fix each one.

Where Screenery is different

Tests, not an agent

A Playwright test takes the same steps every run. It waits for the screen to be ready, with an assertion you wrote, before it captures. If a step stops working, the test fails in CI, and the engineer who changed the screen fixes it in the same pull request.

test('billing settings', async ({ page }) => {
  await page.goto('/settings/billing');
  await expect(page.getByRole('heading', { name: 'Billing' })).toBeVisible();
  await page.screenshot({ path: 'test-results/settings/billing.png' });
});

permissions:
  id-token: write
  pull-requests: write
steps:
  - uses: screenery/push@v1
    with:
      project: acme/dashboard
      path: test-results

No credentials handed over

Promptless needs a test account it can sign in with. Screenery never opens your product. Your CI runs the tests, often against a build it started itself with seeded data, and sends Screenery the image files. On GitHub Actions the push signs in with GitHub's OIDC token, so there is no Screenery secret in CI either. See Credentials.

One URL, any docs tool

Each screenshot gets a stable URL that follows your default branch. Paste it into your docs once. The next push on the default branch changes the image behind it, and no docs file changes.

![Billing settings](https://cdn.screenery.dev/acme/dashboard/settings/billing@latest.png)

See Screenshot URLs.

A gate before publish

Point the push at a committed baseline, and it compares every screenshot with that baseline, pixel by pixel, before it publishes. A visual regression fails the job, and nothing reaches @latest. See Visual testing.

Using both

The two can split the work. Promptless keeps the words current. A Screenery URL in the page keeps the image current without a file change. We have not tested how Promptless treats an image it did not capture, so try it on one page first.

Which to pick

Promptless is the better pick when:

• stale text is as big a problem as stale screenshots;
• your docs team has no Playwright tests and no engineer to write them;
• you want cropped, annotated images, with no editing step of your own;
• your docs already live on a platform it integrates with.

Screenery is the better pick when:

• you already run Playwright in CI, or are willing to write a few screenshot tests;
• you would rather not store app credentials with a vendor;
• you want the same screenshot every run, reviewed in the pull request that changed it;
• you want a visual regression gate, and previews on pull requests;
• the images belong in a README or marketing page as well as the docs.

Screenery does not annotate, crop or resize images today, and it does not write docs. If you need an agent for the whole page, Promptless is built for that.

Sources

We checked the Promptless facts on this page in October 2026, on these pages:

• promptless.ai, the home page.
• promptless.ai/pricing: plans, page counts and which plans include Capture.
• Keep screenshots current with Promptless Capture: sign-in, triggers, the editor and failure modes.
• Promptless on Y Combinator, Winter 2025 batch.

The docs describe how Screenery behaves. Start with Getting started or Playwright goldens.