Skip to main content
Beta. Signals is in Beta. It works today and the ideas are real, but the interface and wording on these pages can still change as we refine it. If something reads differently in your dashboard, trust the dashboard and email support@abtestly.com so we can fix the page.
Signals is ABTestly’s AI CRO audit. You scan a page of your own site, and the AI hands back a ranked list of test ideas, each one a hypothesis with the evidence behind it. You organize those ideas on an idea board, keep the ones worth running, and turn them into real ABTestly experiments with one button. It answers the question every optimization program starts with: what should I test next, and why.

The four steps

Scan a page

A browser extension captures the page from your own live site, desktop and mobile. Walk several steps of a funnel in one pass.

Connect Google Analytics

One click, read only. Adds a behavioral second signal so ideas can be confirmed by what visitors actually do.

Read a scan

The idea board. Ranked by a PXL score, grouped into campaigns, triaged New, Approve, or Dismiss.

Build a test from an idea

Build this creates a real experiment draft, prefilled from the hypothesis. Its result feeds back into the next scan.

Two signals, and honesty about them

This is the part that matters most, so read it before you read a scan. Every scan reads the page structure. That is the DOM: the headings, buttons, forms, copy, and layout the browser actually rendered. Structure is the first signal, and it is always present. It is enough to spot a buried call to action, a form asking for too much, a value proposition that never appears above the fold. Connecting Google Analytics 4 adds a second, independent signal: behavior. What visitors actually do. Where they fall out of a funnel, how conversion differs by device, where revenue comes from by channel. Structure tells you what the page is. Behavior tells you what is happening on it. An idea is marked Test ready only when a second independent signal confirms what the structure suggests. Until then it stays Validation required: an honest finding for you to check, not a promise that it will win. Signals never invents a statistic when the data to support it is not there. When the number exists, you see it. When it does not, the idea says so plainly.
A Test ready badge means two signals agree, not that the test will win. Nothing predicts a winner except running the experiment. Signals finds the strong candidates. The results page settles them.

The closed loop

Most audit tools stop at the report. They never see whether their idea worked, so they cannot get smarter about your site. ABTestly owns both ends, the idea and the experiment, so it can close that loop. When an experiment you built from an idea runs to a conclusion, its outcome, won, lost, or inconclusive, feeds back into future scans of the same site as ground truth. The next scan already knows what worked on your pages and what did not, so its ideas get sharper over time. A standalone tool cannot do this, because it never learns the result. See Build a test from an idea for how the handoff works.

Inside a scan, step by step

Inside a single scan, the audit works through seven stages, from the URL you hand over to the ranked backlog it hands back. Here is what happens at each one.

01 · Intake

You start by giving ABTestly the URL you want audited, plus any context you have: your niche, average order value, the goal that matters, your device split. How you connect your data decides how far the scan can go. Connect GA4 and it reads real behaviour; skip it and the scan stays structural, working only from what it can see on the page. It also confirms the page is on your own site before it runs.

02 · Capture

A browser extension captures the page the way a real visitor sees it, from your own logged in session, so the scan reads the rendered page and not a bare URL. It picks up more than twenty structural signals, from page type and heading order to form fields, calls to action, review counts and trust badges. Three screenshots follow, on desktop, on mobile, and on a throttled connection, each reconciled against what it read. It only ever reads: it never submits payment and never tries to get around a site’s bot protection.

03 · Behaviour

If you connected GA4, the scan reads where real visitors actually drop off. That is the behavioural half of every recommendation: funnel drop off, conversion by device, revenue by channel, plus new against returning visitors and your busiest pages. It matters because a finding is only promoted once behaviour agrees with what the page showed, the two signal rule.

04 · Payload

Everything gathered so far is assembled into a single prompt the model can reason over, so it works from real evidence rather than a bare URL. That prompt carries the three screenshots next to a block of structured text: your business context, the page signals, the live picture from GA4, and any earlier test results from this same site. It is framed as evidence to weigh, not a list of claims to accept.

05 · Generation

Now the model proposes ideas that speak to the problem you named, each grounded in a behavioural mechanism and scored, not guessed. Every idea arrives as a structured hypothesis with 23 fields behind it, among them a PXL score from 0 to 14, the effort, a research citation and a tracking spec. Each one sits under one of five CRO pillars and is read through a named model such as Fogg or Cialdini. When the evidence is thin the idea is flagged rather than dropped, with the single cheapest check that would confirm it, the two signal gate.

06 · Falsification

Before an idea reaches you, it goes through a pass that argues against it. This adversarial step names the most likely way the idea could fail, the confounder most likely to mislead you, another explanation for the same evidence, and the one test that would tell them apart. You get that counter argument attached to the recommendation, so a weak idea cannot arrive dressed as a strong one.

07 · Output

What comes back is a ranked backlog, ordered by that PXL score so the best return for the effort sits at the top. Each item carries its confidence tier, a rough size for the opportunity, the effort, a suggested run time, and the tracking you would need to set up. Confidence runs across six tiers, from verified down to purely structural, so you can see how much weight any one recommendation should carry. Signals writes the backlog and the plan; it never starts the test for you, so what ships stays your call.

What Signals does not do

  • It does not run tests on its own. Nothing goes live until you click Build this, fill in the details, and start the experiment yourself.
  • It does not fabricate numbers. No statistic appears unless the connected data supports it.
  • It does not need your passwords. The scan runs in your own browser, on your own logged in session. See Scan a page.

Where to go next

Run your first scan

Install the extension and capture a page in a couple of minutes.

Add the behavioral signal

Connect GA4, read only, so ideas can reach Test ready.
Last modified on August 11, 2026