The dashboard is at http://localhost:3000 (or your Tandemu Cloud URL). Log in to see your organization’s data.
Dashboard Home
The home page shows summary cards:
- Total Sessions — Number of Claude Code sessions across the team
- AI Code Ratio — Percentage of code generated by AI vs written manually
- Avg Cycle Time — Average time from task start to completion
- Active Developers — Team members who had sessions recently
AI Insights
Path: /ai-insights
Shows the ratio of AI-generated code to manually written code:
- Pie chart — Current split (e.g., 72% AI, 28% manual)
- Trend line — How the ratio changes over time
- Per-developer breakdown — Who uses AI more or less
This helps quantify the ROI of AI tooling. A high ratio means Claude Code is being leveraged effectively. A low ratio might indicate developers need training or the codebase has areas where AI struggles.
Friction Map
Path: /friction-map
Identifies files and components where developers get stuck:
- Repository paths ranked by friction score
- Prompt loop count — How many times developers re-prompted Claude on the same issue
- Error count — Tool execution failures
- Color coding — Green (low friction), yellow (moderate), red (high)
High friction on a file usually means:
- The code is complex or poorly documented
- There are subtle bugs that AI can’t easily fix
- The architecture needs refactoring
Use this to prioritize tech debt cleanup — focus on the files that slow your team down the most.
DORA Metrics
Path: /dora-metrics
Four key metrics from the DORA (DevOps Research and Assessment) framework:
| Metric | Elite | High | Medium | Low |
|---|---|---|---|---|
| Deployment Frequency | Multiple/day | 1/day–1/week | 1/week–1/month | Less than 1/month |
| Lead Time for Changes | Under 1 hour | 1 day–1 week | 1 week–1 month | Over 1 month |
| Change Failure Rate | 0–15% | 16–30% | 31–45% | Over 45% |
| Time to Restore | Under 1 hour | Under 1 day | Under 1 week | Over 1 week |
Each metric shows the current value and a performance level badge (Elite/High/Medium/Low).
Timesheets
Path: /timesheets
Automatic time tracking from Claude Code sessions:
- Daily entries — Date, developer, active time, session count
- Weekly totals — Aggregate hours per developer
- AI-assisted time — How much of the session involved AI-generated code
No manual timesheets needed. Developers just use Claude Code and the time is tracked automatically.