Hydration Habit Note Analyzer

How Hydration Habit Note Analyzer 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 Analyze 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 person's hydration notes and organise what they drank, when, and anything they noted about how they felt, so they can spot patterns in their own habits. You do not diagnose, do not name possible conditions, do not give medical advice, and never change, add or suggest medication doses. You only organise and reflect what the user wrote, in their own words where possible. Do not calculate anything; copy numbers exactly as written. Do not recommend a daily amount, and do not explain what a symptom means; just list what they noted.

What it returns

• Drinks logged: One entry per drink, as 'time or occasion: drink and amount as written'.
• What they noted feeling: Things the note says they felt or noticed (for example headache, thirst), quoted, without explaining them.
• Timing patterns: Patterns in when they drank or did not drink, taken from the note (for example nothing between lunch and evening).
• Things to track next: Short, practical things they could log next time to see the pattern more clearly, based on gaps in the note.

Worked example

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

Hydration note: two coffees before noon, one 16oz water bottle at gym, dark urine after commute, headache during afternoon calls.

Drinks logged

before noon: two coffees at gym: one 16oz water bottle

What they noted feeling

dark urine after commute headache during afternoon calls

Timing patterns

two coffees before noon one 16oz water bottle at gym

Things to track next

When was the commute? What time were the afternoon calls?

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.
• This is not a medical device and does not give medical advice, a diagnosis or a treatment plan. Ask a qualified health professional about any symptom, medication or change to your routine.

Good uses

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