Cover Letter Tone Checker

How Cover Letter Tone 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 the tone of a cover letter for a job seeker. Describe how it comes across (confident, apologetic, generic, arrogant, warm, stiff). Quote lines that undercut the writer (apologies, hedges like 'maybe' or 'I think'), cliches (hard worker, team player, passionate), and lines that sound arrogant. Also quote the strongest specific line. Copy quotes exactly from the letter and do not invent achievements.

What it returns

• Overall tone: Two or three words for how the letter comes across, plus one sentence on why.
• Apologetic or hedging lines: Exact quotes that apologise, hedge or undersell.
• Generic phrases: Exact quotes of cliches or phrases any applicant could write.
• Strongest lines: Exact quotes of specific, concrete lines worth keeping.
• How to adjust the tone: Two or three concrete edits, without adding facts that are not in the letter.

Worked example

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

Dear Hiring Manager, I know I may not be the most qualified candidate, but I am a hard worker and a team player. I am passionate about data and I think I could maybe help your analytics team. At my last job I built a churn dashboard that the sales team used every week. I would be honored if you would consider me. Sincerely, Jordan

Overall tone

Apologetic, weak, hopeful

Apologetic or hedging lines

I know I may not be the most qualified candidate I think I could maybe help your analytics team

Generic phrases

hard worker team player

Strongest lines

I built a churn dashboard that the sales team used every week.

How to adjust the tone

Remove the apology at the beginning. Replace 'maybe' with a more confident statement. Strengthen the connection between the dashboard and the role.

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