Attrition Risk

Private beta

The resignation letter is the last thing that happens, not the first

By the time someone gives notice, the damage is done — knowledge walks out, teams scramble, projects stall. Gitrevio detects the behavioral shifts weeks or months earlier, giving you time to act.

GitRevio Overview Risk Reports AI Chat AA ATTRITION RISK Sarah Chen HIGH James Park MED Full Team View MONITORING Engagement Scope Changes Social Signals Schedule Shifts Attrition Risk Assessment — March 2026 47 engineers monitored · 2 high risk · 5 medium risk High risk engineers 0 engineers requires immediate attention Medium risk 5 engineers monitor closely Avg risk score (team) 0.61 up from 0.44 last month Est. departure window 4–8 wks Sarah Chen (top signal) Risk Scores — March 2026 HIGH RISK Sarah Chen (Backend) 0.78 review frequency −45% (8 wks) · cross-team interactions −60% scope narrowing · 1:1 skip rate increasing Est. departure: 4–8 weeks MEDIUM RISK James Park (Frontend) 0.52 velocity stable · code review depth declining meeting attendance sporadic Est. departure: 2–4 months Shapley Factor Decomposition — Sarah Chen Risk score: 0.78 HIGH engagement decline 38% reduced scope 27% social withdrawal 22% schedule pattern change 13% Suggested intervention: → New project assignment (addresses top 2 factors) → 1:1 conversation re: growth trajectory Impact if leaves: −38% review capacity · 3 orphaned services

How It Works

How it works

HIGH RISK

Sarah Chen (Backend)      Score: 0.78

  Signals: review frequency -45% (8 weeks), commit

  scope narrowing, cross-team interactions -60%,

  1:1 skip rate increasing

  Contributing factors (Shapley):

    engagement decline      38%

    reduced scope          27%

    social withdrawal      22%

    schedule pattern change  13%

  Estimated departure window: 4-8 weeks

  Impact if leaves: -38% review capacity, 3 orphaned services

MEDIUM RISK

James Park (Frontend)       Score: 0.52

  Signals: velocity stable but code review depth

  declining, meeting attendance sporadic

  Estimated departure window: 2-4 months

Attrition risk is not a single metric — it is a constellation of behavioral shifts detected across multiple dimensions simultaneously. No single signal is conclusive. A drop in commit frequency alone means nothing. The model looks at the pattern.

Each engineer's baseline is calibrated individually. A senior architect who reviews 20 PRs a week dropping to 12 is a very different signal than a junior developer whose review count fluctuates naturally.

The model updates continuously. Risk scores aren't a monthly snapshot — they adjust as new data arrives, so you see emerging patterns in real time.

Signal Categories

What the model watches

A focused set of behavioral signals derived from engineering activity. The model weighs them relative to each individual's established baseline. Signals marked planned are on the private-beta roadmap.

Commit cadence

Fewer commits per week versus the individual's own recent baseline. Raw velocity decline is the core computed signal.

Review withdrawal

Declining PR comments, shorter reviews, fewer review requests accepted — disengagement from the team's shared work.

Weekend / schedule shift

Changed working hours and weekend activity patterns, decreased overlap with team core hours.

Vacation imbalance

Unused or lopsided time-off relative to the team, a known correlate of burnout and disengagement.

Team-relative deviation

How far an individual's activity has drifted from their team's norm, not just their own baseline.

Scope narrowing

Working on fewer repos, avoiding new features, maintenance-only commits. Planned — on the roadmap.

Social disengagement

Fewer cross-team interactions, slower Slack response times, reduced discussion participation. Planned — on the roadmap.

Learning cessation

Stopped exploring new parts of the codebase — no new file touches or technology adoption. Planned — on the roadmap.

Mentorship withdrawal

Stopped answering questions, fewer pair-programming sessions, reduced onboarding involvement. Planned — on the roadmap.

Shapley attribution: know why, not just what

A raw risk score of 0.78 is not actionable. You need to know what is driving the risk so you can address it. Shapley values decompose the score into contributing factors with mathematically rigorous attribution.

This transforms a vague sense of concern into a targeted conversation. Sarah's risk is driven by engagement decline and reduced scope — not compensation or work-life balance. A challenging new project might help more than a raise.

Different root causes demand different interventions. The Shapley breakdown tells you which lever to pull.

# Shapley factor decomposition

Sarah Chen — Risk score: 0.78

Factor breakdown:

  engagement decline   ████████████░░░░  38%

  reduced scope       ████████░░░░░░░░  27%

  social withdrawal   ███████░░░░░░░░░  22%

  schedule change     ████░░░░░░░░░░░░  13%

Suggested intervention:

  → New project assignment (addresses top 2 factors)

  → 1:1 conversation re: growth trajectory

Privacy & Ethics

Privacy and ethics

This is about organizational health, not surveillance.

Attrition risk scoring exists to help managers have better conversations and make proactive decisions — not to monitor individuals.

Risk scores are visible only to direct managers and above.

Individual activity patterns stay private — only aggregated risk signals surface. Engineers can see their own profile and understand what data informs their score.

No keystroke monitoring. No screenshot capture. No individual hour tracking.

Gitrevio works from commit metadata, PR activity, and review patterns — artifacts the team already produces as part of normal work.

Early Warning

What you can do with early warning

01

01

Proactive 1:1 conversations

Address concerns before they calcify into a decision to leave

02

02

Project reassignment

Move someone to work that reignites their engagement

03

03

Mentorship pairing

Connect disengaging engineers with senior mentors

04

04

Career development

Create a growth path that makes staying the better option

05

05

Compensation review

When pay is the driver, act before a competing offer arrives

06

06

Team restructuring

Reorganize around people's strengths and interests

Ready to See Your Engineering work clearly?

Get started free