Job Offer Clause Summarizer

How Job Offer Clause Summarizer works

Press Load model once: your browser downloads Gemma 3 1B instruction-tuned (web build) (728 MB) from this site and keeps it in its cache. Then add your text and press Summarize 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 3 1B 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 also carries one worked example: the built-in sample with the answer the larger Gemma 4 E2B model gave for it. That example is what lets this smaller model follow the answer format reliably.

The instruction the model gets

You explain one clause from a job offer or employment agreement in plain English for the candidate. Say concretely what it requires or forbids and when. Copy numbers, amounts, durations and dates exactly as written; do not calculate anything. Do not give legal advice and do not say whether the clause is enforceable or legal where the candidate lives.

What it returns

• Plain English: One or two short sentences on what the clause makes the candidate or the company do.
• Clause type: One of: non-compete, non-solicitation, confidentiality, IP assignment, at-will, bonus or commission, equity vesting, clawback or repayment, notice period, benefits, other.
• Numbers and time limits: Each amount, percentage, duration or date exactly as it appears.
• Worth a closer look: Broad wording, missing limits or one-sided terms a candidate should notice.
• Questions to ask: Two or three questions to take to the employer or a lawyer.

Worked example

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

Employee agrees that for a period of twelve (12) months following termination for any reason, Employee shall not, directly or indirectly, solicit any customer of the Company with whom Employee had material contact during the last two (2) years of employment.

Plain English

After you leave, you cannot contact any customers you had significant contact with during the last two (2) years for a period of twelve (12) months.

Clause type

non-solicitation

Numbers and time limits

twelve (12) months

Worth a closer look

What constitutes 'material contact'?

Questions to ask

Can you provide examples of 'material contact'?

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.

You can switch models in the tool. Also available: Gemma 4 E2B instruction-tuned (web build) (2.0 GB). The larger language model gives more thorough answers but is a bigger download and needs a stronger device.

Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms.

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 4 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