10 LLM Agents Every Small Business Can Run on Self-Hosted n8n

You don't need an agent framework to get value from LLMs. Most useful "agents" for a small business are one structured call inside a workflow you already trust. Here are 10 I run on self-hosted n8n, and the pattern behind all of them.

The pattern

1. Trigger: a webhook or a schedule.
2. Build Prompt: a Code node with a strict system prompt and a JSON output contract.
3. LLM: an HTTP Request to any OpenAI-compatible /chat/completions, in JSON mode, with 3 retries.
4. Parse: safe JSON.parse with a fallback.
5. Act: Slack, Sheets, a CRM, or a webhook response.

The 10

1. Lead qualifier: BANT score, Slack alert for hot leads.
2. Support FAQ agent: answers only from your KB, escalate flag for humans.
3. Cold email personalizer: ≤110 words, no invented facts.
4. Invoice extractor: vendor, totals, GSTIN, line items, with null instead of guesses.
5. Daily market digest: RSS → the 5 items that matter, plus one action.
6. Meeting notes → actions: decisions, owners, due dates.
7. Review replies: sentiment and a brand-safe reply.
8. Content repurposer: blog → LinkedIn, X thread, newsletter, SEO meta.
9. Resume screener: evidence-only scoring with bias guardrails, human in the loop.
10. Weekly metrics narrator: JSON metrics → a plain-English Monday brief.

Lessons

• Ask for JSON and say what to do when data is missing ("use null, never guess"). That one line removes most hallucinations in extraction tasks.
• Keep the model swappable. A Config node holding baseUrl and model lets you move between a paid API and local Ollama in seconds.
• Put humans on outbound actions. Draft, don't auto-send.

Grab them

Two of these workflows are free on GitHub, with import instructions: https://github.com/arkintof/n8n-ai-agent-workflows

Which of these would you trust to run unattended, and which would you keep a human on? Tell me in the comments.

Written with AI assistance; workflow built and tested by me.