Week 35 / 2026.
A short record of changes between issues. Full answers and charts live on the question pages.
- Data window
- Aug 25–31, 2026
- Last updated
- Sep 10, 2026
- Author
- Romuald Członkowski
Changes versus the previous issue
This is the first issue, so there is no comparison yet.
| figure | value | change |
|---|---|---|
| Workflows created | 98,122 | — |
| Workflows per day | 14,017 | — |
| Tool calls | 1,870,624 | — |
| Calls ending in error | 0.23% | — |
| Failed validation | 1.0% | — |
| Active installs | 120,544 | — |
| Week-1 retention | 69.0% | — |
| Workflows added to corpus (week) | 32,797 | — |
This week's answers
- Which LLM powers n8n AI agents: OpenAI, Anthropic, Gemini or Ollama?
In n8n workflows built last week, OpenAI holds 37% of model nodes, Anthropic 21%, Google Gemini 18% and OpenRouter 11%. In Mar 2026 OpenAI had 48% and Anthropic 12%.
- Which n8n nodes do AI agents use most, and which trigger nodes start their workflows?
The most used node in AI-built n8n workflows is Code, present in 74% of last week's workflows, followed by HTTP Request (60%) and Webhook (55%). The median workflow has 7 nodes.
- Which n8n node is growing fastest?
The fastest-growing n8n node is Data Table: its share of AI-built workflows rose from 4.3% in May 2026 to 8.6% in Aug 2026, a 2.0× increase. Convert to File is second (1.8×). Last week Data Table was the most searched node among AI agents.
- Do AI-built n8n workflows handle errors?
Rarely. 1.8% of AI-built n8n workflows from last week contain an Error Trigger node, and 2.0% of those built in Aug 2026. Since March the share has never exceeded 2.5%.
- Do AI agents build n8n workflows from nodes or from code?
From code. The Code node appears in 74% of AI-built n8n workflows from last week and HTTP Request in 60%. In Aug 2026 the Code share was 73%. Agents would rather write JavaScript and call an API than look for a ready-made integration.
- 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: 2.2% for 2–3 nodes versus 0.18% for 31–100.
- Which n8n nodes do AI agents search for?
Last week the most searched n8n node was data table (286 installs), ahead of webhook (172) and http request (95). The ranking counts unique installs, not queries.
- How do AI agents (Claude Code, Cursor) build n8n workflows through MCP: build or maintain?
Maintain. Of 1,870,624 tool calls last week, 57% read workflows, executions and lists, and 15% write. Fetching executions alone is 28% of calls. In the same week 98,122 workflows were created, 14,017 a day.
Most searched nodes
data table (286) · Webhook (172) · http request (95) · schedule trigger (86) · google sheets (80) · ai agent (74) · Gmail (66) · Telegram (55) · form trigger (53) · whatsapp (53)
Never use append on sheets with formula columns
Google Sheets append operation writes raw values including formula results as plain text. If the sheet has formula columns (like calculated totals), appending will overwrite formulas with their last computed values. Use update operation with specific cell ranges instead.