AI automation & no-code
Add LLM steps to business automations
Classify emails, extract fields from documents, draft replies inside n8n/Zapier/Power Automate flows.
~10 focused hours·beginner
Tools: n8n AI nodes / LangChain node, OpenAI/Anthropic API, Zapier AI actions, Power Automate AI Builder
Market relevance — share of job ads asking for this
What employers mean
You should be able to…
- Classify inbound emails or tickets using an LLM step inside a workflow
- Extract structured fields from unstructured documents (invoices, forms) inside an automation
- Draft a reply or summary using an LLM step, with a human-approval gate before sending
- Prompt-engineer an LLM step to return reliable structured output (JSON) an automation can parse
- Control cost by choosing the right model size/provider per automation step
- Handle LLM step failures (bad JSON, timeout) without breaking the whole flow
Needs first: Automate workflows with n8n / Zapier / Make, Design and version prompts systematically
Learn — free, link-checked
The few resources that matter
Use · beginner · 30 min · n8n.io
n8n workflow template library
Hundreds of real, importable workflows (including AI ones) to reverse-engineer instead of starting blank. — n8n
Read · beginner · 30 min · docs.anthropic.com
Prompt Engineering Overview
Official, up-to-date techniques (system prompts, few-shot, chain-of-thought) with before/after examples you can copy. — Anthropic
Course · beginner · 90 min · deeplearning.ai
ChatGPT Prompt Engineering for Developers
Hands-on notebook exercises that turn prompting principles into a repeatable, testable workflow. — DeepLearning.AI (Andrew Ng, Isa Fulford)
Read · intermediate · 60 min · docs.n8n.io
Advanced AI in n8n
Official docs for wiring LLM nodes, agents and memory into a workflow — the exact skill 'AI + automation' JDs ask for. — n8n
Build from · intermediate · 90 min · github.com
OpenAI Cookbook
Battle-tested example notebooks (chat apps, vision, retries) you can lift directly into a real project. — OpenAI
Practice
AI-powered Hindi/English support-ticket triage automation
Build a workflow (n8n or Zapier) that ingests a support ticket in Hindi or English, uses an LLM step to classify category and urgency and extract key fields into structured JSON, drafts a suggested reply, and routes high-urgency tickets to a human-approval step before any auto-reply is sent.
Done when
- LLM step reliably returns valid structured JSON (test with at least 10 varied ticket examples)
- Workflow handles both Hindi and English input correctly
- High-urgency tickets are routed to a human-approval step, not auto-sent
- Malformed LLM output is caught and logged rather than crashing the workflow
Prove it
Evidence a recruiter can check
- Exported workflow with README
- Sample input/output pairs (at least 10) showing classification accuracy
- Screen-recording showing the human-approval gate in action
Interview
Questions you'll get asked
- How would you add an LLM step to classify incoming support emails inside n8n or Zapier?
- How do you get an LLM to reliably return structured JSON an automation can parse?
- What happens in your workflow when the LLM step returns malformed output?
- How do you decide between a cheap/fast model and a more capable one for a given automation step?
- Tell me about a workflow where you added a human-approval gate before an AI-drafted action executed.