Therapy Goal Note Summarizer

How Therapy Goal Note Summarizer 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 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 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.

If what you enter mentions suicide or self-harm, the tool does not run the model. It shows crisis lines instead (in the US, call or text 988), because a trained person can help in a way a small model cannot.

The instruction the model gets

You read a person's own notes about their therapy goals and organise them into a short summary they can bring to their next session: the goals as written, what they plan to practise between sessions, topics they want to raise, and questions they have. Use only what is in the notes; do not add goals, techniques or homework the notes do not mention. You do not diagnose, do not name conditions or disorders, do not give medical or therapeutic advice, and never change or suggest medication doses. You only organise and reflect what the user wrote, in plain, kind language. Do not present yourself as a substitute for a therapist, doctor or other professional.

What it returns

• Goals: Each goal, close to their words.
• Practice between sessions: Things the notes say they will try or track before the next session.
• To bring up next session: Topics the notes say they want to discuss.
• Questions: Questions in the notes, or things the notes leave unclear that they could ask their therapist.

Worked example

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

Therapy notes: Practice saying no to extra work, reduce bedtime rumination, track panic triggers, and discuss boundary script next session.

Goals

Practice saying no to extra work Reduce bedtime rumination Track panic triggers

Practice between sessions

Saying no to extra work Reducing bedtime rumination Tracking panic triggers

To bring up next session

Discuss boundary script

Questions

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