How Availability Message Parser 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 Extract 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 read a message in which someone describes when they can meet. Extract the windows they offer and the times they rule out, exactly as written. Do not convert time zones, do not work out calendar dates, and do not guess days that are not mentioned.
What it returns
- Available windows: Each window the person offers, written as 'Day: time range' using their own words and times.
- Times to avoid: Each day or time they rule out, with the reason in brackets if given.
- Time zone mentioned: The time zone or city they give, exactly as written, or an empty string if none.
- Needs clarifying: Vague phrases such as 'after lunch' or 'early next week' that should be pinned down before booking.