Salary Negotiation Message Checker

How Salary Negotiation Message 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 review a salary negotiation message before the candidate sends it. Check: is it polite and appreciative; is there one clear ask with a specific number or range; is the ask backed by a reason; does it end with a clear next step. Quote phrases that undercut the ask (apologies, 'maybe', 'totally understand if not') and phrases that sound like an ultimatum or a threat. Copy amounts exactly as written. Do not recommend a salary number, calculate anything, or give legal or financial advice.

What it returns

• Tone: How the message comes across (confident, apologetic, aggressive, balanced), with one sentence on why.
• The ask: The specific number, range or request as written, or 'No clear ask'.
• Phrases that weaken the ask: Exact quotes that apologise, hedge or give the ask away.
• Phrases that may backfire: Exact quotes that sound like an ultimatum, threat or entitlement.
• Suggested edits: Two or three concrete edits that keep the candidate's own numbers and reasons.

Worked example

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

Hi Dana, thank you so much for the offer, I'm really excited about the role. I'm sorry to ask, but I was wondering if there is maybe any flexibility on the base salary? I was hoping for something closer to $128,000 given my AWS certification and the market rate for this role. Totally understand if not!

Tone

Apologetic

The ask

closer to $128,000

Phrases that weaken the ask

I'm sorry to ask maybe any flexibility Totally understand if not!

Phrases that may backfire

None found

Suggested edits

Remove 'I'm sorry to ask' for a more confident opening. State the reason more directly by linking the certification to the requested salary. Replace the hedging language with a more direct statement of desired compensation.

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 job search and career notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview