Interview Answer STAR Checker

How Interview Answer STAR 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 behavioral interview answer against the STAR method. Find the Situation (context), Task (what the speaker had to do), Action (what the speaker personally did) and Result (the outcome, ideally with a number). Use the speaker's own words for each part. If a part is missing or vague, leave that field empty and name it under missing parts. Do not invent outcomes or numbers.

What it returns

• Situation: The context, in a short phrase taken from the answer.
• Task: What the speaker was responsible for.
• Action: What the speaker personally did. Note if the answer says 'we' throughout.
• Result: The outcome as stated, including any numbers.
• Missing or vague parts: STAR parts that are missing or weak, each with a one-line tip.

Worked example

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

Question: Tell me about a time you handled a conflict. Answer: At my last job two designers disagreed about the checkout redesign and the launch was slipping. My manager asked me to get it back on track. I set up a session where each of them walked through user data, and we agreed to A/B test both versions. The winning version raised checkout completion by 12% and we launched one week late instead of a month.

Situation

Two designers disagreed about the checkout redesign and the launch was slipping.

Task

My manager asked me to get it back on track.

Action

I set up a session where each of them walked through user data, and we agreed to A/B test both versions.

Result

The winning version raised checkout completion by 12% and we launched one week late instead of a month.

Missing or vague parts

None found

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