# AI Usage Rollup — {team_name}

**Period:** {start_date} → {end_date} ({n_days} days)
**Team size in scope:** {n_users} users
**Total invocations:** {n_invocations}

> {data_caveats_line}

This is an **aggregate** view. No individuals are named. If you need a per-user breakdown for a 1:1 or coaching conversation, switch to the `per-user` view — but read the privacy note at the bottom first.

## Headline metrics

| Metric | Value |
|---|---:|
| Invocations / user / day (median) | {median_invocations_per_user_per_day} |
| Distinct tools per user (median) | {median_distinct_tools_per_user} |
| Effectiveness rate (team avg) | {team_effectiveness_rate} |
| Single-shot session rate (team avg) | {team_single_shot_rate} |
| Active users (≥1 invocation in period) | {n_active_users} of {n_users} |

## Adoption distribution

| Engagement tier | Users | What it means |
|---|---:|---|
| **Heavy** (>20 invocations/week) | {n_heavy} | Deep adopters; check whether their effectiveness rate is also high |
| **Moderate** (5–20 / week) | {n_moderate} | The healthy middle |
| **Light** (1–4 / week) | {n_light} | Sampling but not embedded; surface tool-fit conversations |
| **Inactive** (0 / week) | {n_inactive} | No usage; check whether tool access is the blocker |

## Top tools / skills (team-wide)

| Tool | Invocations | % of total |
|---|---:|---:|
{top_tools_rows}

## Effectiveness signal (if available)

{effectiveness_block}

## Where signals are missing

{missing_signals_section}

## Privacy posture

This view is safe to share with audiences who should not see individual usage data (skip-level meetings, broad team reviews, exec rollups). The headline metrics and tier counts cannot be reverse-engineered to identify individuals **as long as `n_users` ≥ 5**. If your team has fewer than 5 users in scope, the script will refuse to generate this view — switch to `per-user` and treat it accordingly.

---
*Generated by `ai-usage-report` on {generated_at}. Input file: `{input_file}`. View: `team-rollup`.*