//n8n AI Automation Index
How large are AI-built n8n workflows, and which fail validation?
55% of workflows created last week have at least 11 nodes and 21% have 31 or more. The larger the workflow, the less often it fails validation: 2.3% for 2–3 nodes versus 0.11% for 31–100.
- Last updated
- Sep 25, 2026
- Data window
- Sep 7–13, 2026
- Author
- Romuald Członkowski
- 2-3 nodes2.31%
- 4-10 nodes0.75%
- 11-30 nodes0.46%
- 31-100 nodes0.11%
- 101-300 nodes0.13%
The picture of AI producing only simple three-node automations does not hold. The validation result looks counter-intuitive at first: large workflows are built incrementally through many small updates, each of them checked (8 updates per create). Small workflows are often one-off drafts sent without a check.
History
One row per weekly issue. The table grows with every update.
| week | workflows | ≥11 | ≥31 | failed validation |
|---|---|---|---|---|
| 2026-W37 | 118,918 | 55% | 21% | 1.0% |
| 2026-W36 | 98,043 | 49% | 19% | 1.8% |
| 2026-W35 | 98,122 | 55% | 21% | 1.0% |
Methodology · Data and charts may be reused with attribution (CC BY 4.0).