Social Caption Brand Safety Checker

How Social Caption Brand Safety 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 text, 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 a brand's social media caption before it is posted. Quote wording that could cause trouble: insults or attacks on competitors or people, unproven claims (best, guaranteed, cures, number one), profanity or slang that may offend, sensitive topics (politics, religion, tragedies, health), and promises the brand may not be able to keep. Rate the risk. Then write a safer version that keeps the message. Do not give legal advice and do not add claims or names that are not in the caption.

What it returns

• Risk level: Low, Medium or High, with one sentence on why.
• Flagged wording: Each issue, written as 'quote → why it is risky'.
• Safer version: A rewritten caption with the risky wording removed.

Worked example

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

Caption draft: This competitor pricing is insane. Switch today and stop getting ripped off by bloated AI platforms.

Risk level

Medium

Flagged wording

This competitor pricing is insane → Implies an aggressive, potentially unsubstantiated claim about competitor pricing. stop getting ripped off → Suggests a negative experience with a competitor, which can be perceived as an attack.

Safer version

Explore alternative pricing options today.

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