Kalokoby

All guides › By use case

By use case

Hosted runs: Kaloko checks your pages every morning

Kaloko opens the pages of a read-only scenario on its own browsers every day or week, in every language and viewport, and shares the run as if you had walked it.

The marketing site changes three times a week and none of those changes go through your pull requests. A CI job could walk it every night, but nobody wants to maintain one for a site they do not deploy. Hosted runs do the walking on Kaloko's side.

The problem

Scheduled checks need a machine that runs them: a CI job, a server, a laptop that stays on. For a handful of public pages that is more work than the pages themselves, so the check never gets set up and a broken page is found by a visitor.

What changes with Kaloko

On Business and Enterprise, Kaloko opens the pages of a read-only scenario on its own browsers, every day or week at the hour you choose, takes full-page screenshots in every locale and viewport, checks what can be checked from the page and shares the run under your name. Business includes 2,000 loaded pages a month, Enterprise 10,000.

How it works

  1. Write a read-only scenario

    steps that open a page. kaloko draft https://example.com https://example.com/pricing drafts one from the pages themselves.

  2. Schedule it

    kaloko schedule add --scenario qa/flows/public.yml --env production --every day --at 5 (the hour is UTC). --every week --weekday mon runs it weekly.

  3. Pages behind a gate

    HTTP Basic credentials from the environment are sent once and stored encrypted. For signed-in pages, a person saves a session with kaloko auth save and the schedule uses it with --account.

  4. Manage it

    kaloko schedule list shows the next and last run and the pages used this month; run, pause, resume and remove take the schedule id. Settings → Integrations shows the same.

  5. Read the result

    the run appears like any other, with the comparison against the baseline. Selector, text, title and meta criteria are decided; criteria that need the full walk say "not evaluated" with the reason.

Skills and prompts

Schedule a daily Kaloko check of our public pages at 5 UTC on production, read-only, and tell me how many pages it uses a month.

Expected outcome: a validated read-only scenario, one kaloko schedule add, and an estimate of pages per month from locales × viewports × steps.

Our checkout needs clicks. Give me a GitHub Actions workflow that walks it every Monday instead.

Expected outcome: kaloko schedule export github --scenario qa/flows/checkout.yml --env staging --every week writes the workflow and names the secrets it needs.

What you get

FAQ

What can hosted runs not do?

Click or type: steps that do more than open a page are left out and named. Native apps, local or private addresses, credentials sent as headers and base URLs per locale also need the full walk, which kaloko schedule export github runs on the same schedule.

What counts against the page budget?

Every page loaded: each step in each locale and viewport. A scenario of 10 pages in 2 languages on desktop and mobile loads 40 pages per run.

Is production safe?

Hosted runs only open pages and read them. Nothing is clicked, submitted or created.

More guides

Accepting a task with an AI agent, in the pull requestRegression before a release: compare the run with the accepted baselineSEO and landing-page checks on production, read-only, every dayE-mail flows: capture the message next to the screen that sent it

Install once, then work through your agent

Kaloko runs where your code and your agent are. The service stores and versions the results, shows the canvas and collects approvals.

  1. Add the CLI to the project
    npm install --save-dev kaloko

    Needs Node 20 or newer. Update later with npm update kaloko.

  2. Create the config and install the skill
    npx kaloko init --agent claude --org <your-org>

    The skill is copied to .claude/skills/kaloko. npx kaloko doctor checks Chrome, the config and the token.

  3. Create your organization and a token

    Create an organization; you become its admin. The start page offers a tester token in one click, later under Settings → API tokens. Put it into the project .env:

    KALOKO_TOKEN=qwk_…
    TYPESAFE_API_KEY=…   # optional: semantic evaluator

Then just ask your agent

The skill teaches your agent the whole loop: it writes the acceptance plan and the scenario from the task, walks the screens, evaluates, shares the canvas, reads what reviewers said and fixes it. You don’t type the commands; you look at the canvas.

What the agent runs (or run it yourself, e.g. in CI)

The same loop by hand:

npx kaloko start --scenario docs/tasks/TASK-123/qa/scenario.yml --env local
npx kaloko walk        # playwright steps; agent/manual steps: kaloko capture
npx kaloko evaluate
npx kaloko share --pr
npx kaloko feedback    # what reviewers said, with ids to answer