Phrase Prioritizer

Paste a list of phrases you're considering. The AI scores each phrase against your current state — you pick the top ones to play.

Score your phrases Describe yourself · Find areas to dig into or score your own phrases · Send selected to Phrase Player
Type a few sentences ✓ using saved snapshot from your session
Write whatever's on your mind — what you're noticing, what you've been doing, or anything at all. On this page the text isn't sent to the AI; what's captured is your typing rhythm as you write. The content matters less than simply typing naturally for a bit.

Tip: Just type at a natural pace for a few lines — that's enough to capture a usable keyboard signal.
Type naturally for a few lines — your typing rhythm informs the signals.
Signals Included in AI Scoring
The channels the AI uses to score your phrases on this page — all behavioral signals (your typed words are not sent here):

Keyboard — your typing-rhythm signals (keys/sec, backspace rate, gaps, jitter) captured from the box above.
Mouse — pointer-movement signals (speed, jitter, pauses).
Voice — vocal dynamics from a short recording: average pitch and how much it moves, energy, pace, and silence. Captures how your voice moves, not what you say — no transcription. Click "Record voice", speak, click Stop (auto-stops at 10s).

Keyboard and Mouse are always on; Voice is optional. Scoring runs on these signals alone — experimental by design; it's the honest test of whether signals carry usable state information.
Pick which channels feed the AI. Each is independent.
| using saved snapshot from your session
typing:2.11 kpsgap:162 msbackspaces:1.8%over:53smouse:53 px/sjitter:0.57pauses:4captured:June 4, 2026
Find areas to dig into experimental — not proven
Not sure which phrases to consider yet? This scores whole areas of the library against your current state, so you can see where to focus before picking individual phrases.

Click Select Areas to Score to open the picker. Choose a level using the tabs — Type, Family, Focus, or Tag — then check the specific areas you want, or leave none checked to score every area at that level. It's one level per run: switching tabs starts a fresh selection. Your choice shows as a summary on the page (e.g. "Family · 6 selected"), and Reset clears it.

Hit Score areas and each area is scored by sampling the phrases inside it (by default an adaptive sample — about a third of the area, at least 50, capped at 200), scoring that sample with the AI, and rolling up to a single area score (the average of its top 5 phrases). You can change the sample size in the testing controls. Areas come back ranked. On any area, ← Load phrases pulls all of its phrases into the "Phrases to score" box (to the left), where you can score them individually as usual; or check several areas and use ← Load selected.

This uses one AI call per area and reads your description + signals the same way phrase scoring does. Scoring many areas (e.g. all tags) means many calls — you'll get a warning first. Experimental: results are exploratory, not a diagnosis.
Score whole areas of the library against your state to decide where to focus.
Select a level and areas to begin
temporary · testing → score 33% (min 50, ≤200) phrases, top-5 mean
Phrases to score
Paste a list of phrases you're already considering — could be from your saved configurations, an AI Generator session, a custom TSV, or hand-typed. You can also fill this box from Find areas to dig into (right) using ← Load phrases. The AI will score each one against your description and the inputs you've selected. One phrase per line. Empty lines are ignored. Duplicates (case-insensitive) are dropped silently and a note appears under results. Special characters are stripped on paste.

How the AI scores (what it's told): the prompt asks the model to rate each phrase 0–100 for how well it resonates with your state, plus a short reason. It's assembled from a few fixed pieces:
· Scoring discipline — use the full 0–100 range; reserve 90+ for only the top 3–5, 70–89 for good matches, 40–69 for partial, under 40 for poor; don't cluster scores.
· What these phrases are — the model is told they're calm, materially-grounded taxonomy labels (a named-identity form like "Residual Aspergillus Burden Resolution" or an architectural form like "Residual Lymphatic Congestion Resolution"), and that endpoints like Resolution are calm anchors, not claims. It scores resonance only — it is explicitly told not to reward or penalize how well-formed a phrase is (form is the Generator's job).
· How to read your description — not applicable here: this page does not send your typed words to the AI (signal-only scoring). The description box captures typing rhythm only.
This page runs in signals-only mode: the AI scores against your typing/mouse/voice dynamics with no description text (experimental by design — the honest test of whether signals carry usable state info; chosen because it aligned better with offline results). Output is a strict JSON array, one entry per phrase, in input order.

Note: this scoring prompt lives in the page code (unlike the Generator's ai-prompt.txt, which is an editable file). It is not currently ontology-aware beyond the framing above.
Paste the phrases you're considering, one per line.
Clear
What is the Phrase Prioritizer?

A tool that scores a set of phrases against what you're noticing — so you can see which ones resonate most before sending them to the Phrase Player. You describe your state, optionally add signals (typing rhythm, mouse, voice), and the AI ranks each phrase 0–100 with a short reason.

How to use it: type a few sentences about what you're noticing, paste or load the phrases you're considering into Phrases to score, pick which signal channels feed the AI, then Score these phrases. Or use Find areas to dig into to score whole areas of the library and decide where to focus. Selected phrases can be sent to the Phrase Player.

How the AI scores: it rates each phrase for how well it resonates with your state — using the full 0–100 range (90+ reserved for the top 3–5). It's told these phrases are calm, materially-grounded taxonomy labels and to judge resonance only, not how well-formed a phrase is. When you provide a description it weighs emotional tone and process stage, not just keywords. The exact inputs depend on the channels you check; the ⓘ next to Phrases to score has the full breakdown.

Beta · experimental. Whether the captured signals actually move the ranking is an open question this page is built to test — treat the scores as a starting point, not a verdict.

Your data stays with you. This page runs entirely in your browser. Your phrases, description, signals, and scoring runs are stored only on this device. Clearing your browser data (or using private/incognito mode) wipes everything.

For personal exploration. Not a medical device and not intended to diagnose, treat, cure, or prevent any condition.

Getting Started · How Scoring Works · Signals in Scoring · Scoring Prompt · Scoring Runs

Session Cost: $0.20359 Reset

Last updated: June 4, 2026