Anatomy of a ticket
Anatomy of a ticket — ADS
Window: 30d · All 52 · AI 0 · Human 52
AI vs Human comparison
Bars proportional within each row (max = 100%). Δ% lower-is-better — green = AI faster.
Not measurable (one cohort has zero samples):
- ·Jira Flow Lead Time (raw / wall-clock) — no AI cohort samples (no completed tickets with an AI assignee, or no PRs by AI authors)
- ·Lead Time (active, ÷ pauses) — no AI cohort samples (no completed tickets with an AI assignee, or no PRs by AI authors)
- ·Time to Ready — no AI cohort samples (no completed tickets with an AI assignee, or no PRs by AI authors)
- ·Cycle Time (raw / wall-clock) — no AI cohort samples (no completed tickets with an AI assignee, or no PRs by AI authors)
- ·Cycle Time (active, ÷ pauses) — no AI cohort samples (no completed tickets with an AI assignee, or no PRs by AI authors)
- ·Time to First PR — no AI cohort samples (no completed tickets with an AI assignee, or no PRs by AI authors)
- ·PR Review Duration — no AI cohort samples (no completed tickets with an AI assignee, or no PRs by AI authors)
- ·Lead Time for Changes — no AI cohort samples (no completed tickets with an AI assignee, or no PRs by AI authors)
Cohort breakdown
âš marker when AI or Human cohort sample size is below 10.
| Metric | All p50 | n | AI p50 | n | Human p50 | n | Δ (AI vs Human) |
|---|---|---|---|---|---|---|---|
| Jira Flow Lead Time (raw / wall-clock) | 112h | 52 | — | 0 ⚠| 112h | 52 | — |
| Lead Time (active, ÷ pauses) | 112h | 52 | — | 0 ⚠| 112h | 52 | — |
| Time to Ready | 93h | 52 | — | 0 ⚠| 93h | 52 | — |
| Cycle Time (raw / wall-clock) | 0.0h | 52 | — | 0 ⚠| 0.0h | 52 | — |
| Cycle Time (active, ÷ pauses) | 0.0h | 52 | — | 0 ⚠| 0.0h | 52 | — |
| Time to First PR | 0.6h | 13 | — | 0 ⚠| 0.6h | 13 | — |
| PR Review Duration | 3.1h | 7 | — | 0 ⚠| 3.1h | 7 ⚠| — |
| Lead Time for Changes | 3.5h | 29 | — | 0 ⚠| 3.5h | 29 | — |
All = every measurable ticket / PR in the window. AI = agent-owned cohort (ticket assignee or PR author is an active agent at completion). H = human cohort (everyone else, including unassigned). Δ compares AI vs Human p50 — negative = AI faster.
Side metrics
🧠AI deep analysis
Generate an LLM-driven explanation of WHY the AI cohort is faster / slower on each lane. Cites specific tickets from the evidence pack, suggests next steps.
Active variants use business hours minus pause statuses (same formula as the per-project Cycle / Lead pages). Raw variants are pure wall-clock. AI cohort = ticket assignee (or PR author) is an active agent at completion time. Sample-size suppression marks values directional only when AI or Human cohort drops below 10 — the value is still shown for context but trust it less.