How FocusUp scores work

A score you cannot inspect is a score you cannot trust. This page publishes exactly how every FocusUp number is computed — the same formulas that run in production. Most axes are deterministic (no AI), so they are reproducible and comparable across days and members; the AI's role is narrow and clearly bounded.

The five daily score axes

Each member's day gets five 0–100 axes. Four are measured; one is the AI's overall verdict, constrained by the measured four.

Focus — AI-assessed, time-weighted

After each session the AI reads the activity log (and sampled screenshots when enabled) and assigns the session a focus score. The daily Focus axis is the duration-weighted average of those session scores — longer sessions count for more.

Activity — deterministic

The share of tracked time with real keyboard/mouse input, scaled by input intensity: score = active share × (0.5 + 0.5 × intensity ÷ 100). Intensity comes from input counts only (keystrokes, clicks, scrolls — never content). Presence earns most of the credit; sustained input pushes it to the top.

Relevance — weighted app mix

The AI classifies each app and site used in a session as high, medium, low or unrelated to work; the axis is the usage-weighted average with fixed weights: high = 100, medium = 60, low = 30, unrelated = 0. The same app can be work or distraction — classification follows the actual context, not a static category list.

Deep work — deterministic

Long uninterrupted blocks score high; fragmented days score low. The expected block length of a random tracked minute (Σ duration² ÷ Σ duration) is compared to a 50-minute target for up to 80 points, then adjusted: +20 for focus-block sessions, −15 for context switching, −10 for long idle — clamped to 0–100.

Overall — the AI's one verdict

The only axis the AI decides. It is instructed to stay consistent with the four measured axes and the written narrative — it cannot contradict the evidence.

Burnout risk — 100% deterministic

The burnout/retention radar contains no AI at all. Every point of the 0–100 risk score over the trailing 28 days is explainable by a named signal:

  • Overwork — up to 40 pts: share of tracked days over 9 hours (half of all days over 9h = maximum).
  • After-hours — up to 25 pts: share of session time between 22:00 and 06:00 in the org timezone (12.5% = maximum).
  • Weekend work — up to 15 pts: share of session time on Saturday and Sunday (10% = maximum).
  • Score decline — up to 20 pts: recent 14-day average efficiency versus the previous 14 days (a 20-point drop = maximum).
  • Disengagement — up to 20 pts: tracked days collapsing versus the previous period (+10) and active share dropping more than 15 points (+10).

Bands: 40+ = watch, 70+ = alert. The radar exists to start caring conversations early — never for discipline — and members always see their own signals too.

What the AI does — and does not

It reads session evidence to write the factual work narrative, assign session focus scores, classify app relevance and write coaching suggestions — in plain language, never accusatory.

It does not decide the deterministic axes, never sees keystroke content (input is counted, not logged), and writes nothing a member cannot read themselves — data parity covers every score and report on this page.

Auditable by design

Every number traces back to sessions, activity samples and analyses the member can open themselves. If a score looks wrong, its evidence is one click away — that is the difference between a published methodology and a black box.

Read our security & privacy commitments