One minute a day.
Employees post the way they already do, in chat. InRoots does the rest, in your language, on your infrastructure.
1. Post or speak
"Signed in. Shipped the export fix. Blocked on invoice PDFs." One line in K9 Chat, Slack or Microsoft Teams, or said to the assistant. Any language; the parser handles typos and shorthand.
2. The AI reads and verifies
Intent, hours, tasks, blockers and location are extracted. Claimed work is cross-checked against Jira, GitHub and GitLab activity. Presence is confirmed with a light, consented ping, never a screenshot.
3. Goals and coaching
Personal objectives get automatic follow-ups. Stuck tasks get a nudge. Improvement suggestions cite the person's own work, not a generic playbook. Managers receive a weekly digest instead of hovering daily.
4. One fair score, seen by all
Five weighted pillars (Progress 40, Presence 25, Reliability 15, Integrity 10, Responsibility 10, plus an optional manager-feedback pillar), per-role profiles, and a line-by-line breakdown behind every point. The employee sees it first; typing "/pulse me" in chat returns it any time.
What it runs on
- One container, SQLite or Postgres
- 448 API routes and 64 scheduled jobs running the workday
- 16 AI providers, including local Ollama for air-gapped installs
- Matrix-native; Slack and Teams bridged; WhatsApp for on-call reach