Landing Page Message Match Checker

How Landing Page Message Match Checker works

Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Check locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your two texts, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

The instruction the model gets

You check message match between an ad (first text) and the landing page it sends people to (second text). For each promise or claim in the ad, decide whether the landing page repeats or clearly supports it. A visitor should see the ad's main promise right away; flag promises the page drops or contradicts.

What it returns

• Promises the page keeps: Ad promises the landing page repeats or supports, written as 'promise: where on the page'.
• Promises the page drops: Ad promises the landing page does not mention or contradicts.
• Message match: Strong, partial or weak, with a short reason.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Cut AI inference costs. Route requests to your own GPUs. Automatic cloud fallback when your hardware is busy. Build faster AI apps with a flexible developer dashboard. Track usage analytics for every model. Send requests to the GPUs you already own instead of paying per token. Invite your whole team in minutes.

Promises the page keeps

promise: Send requests to the GPUs you already own instead of paying per token: Send requests to the GPUs you already own instead of paying per token.

Promises the page drops

promise: Cut AI inference costs: No mention of cutting costs. promise: Route requests to your own GPUs: Mentions sending requests to GPUs you already own, but not explicitly routing them to your own GPUs. promise: Automatic cloud fallback when your hardware is busy: No mention of automatic cloud fallback.

Message match

Partial, the page supports one key promise but misses the others.

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

• Triage SEO and digital marketing notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview