How to automate customer support with AI: Build a RAG-powered chatbot that knows when to escalate

Result: By the end of this guide you'll have an n8n-driven workflow that pulls answers from your documentation via Retrieval-Augmented Generation (RAG), delivers them through a chat widget, and automatically creates a ticket when confidence is low. The system runs 24/7, reduces repetitive human effort, and ensures every ambiguous request lands in your ticketing tool for a human agent.

What is AI customer support? AI customer support is a software layer that interprets user questions, matches them to existing knowledge (FAQ, manuals, internal docs), and returns concise answers - falling back to a human ticket when the AI is unsure.

What you need

Estimated build time: 6-8 hours (including data ingestion, workflow testing, and UI tweak).

Step-by-step build

1. Prepare the docs Export your support documents to plain Markdown. Place them in a folder called docs/. Each file will become a separate vector entry.

2. Create embeddings - Run the official OpenAI embedding endpoint (text-embedding-3-large). - Store each resulting vector in Qdrant under the collection support_vectors. Example Python script (run once):

 pip install openai qdrant-client tqdm
 

 import os, json, glob
 from openai import OpenAI
 from qdrant_client import QdrantClient
 from tqdm import tqdm

 client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 qdrant = QdrantClient(url="http://localhost:6333")

 qdrant.recreate_collection(
 collection_name="support_vectors",
 vectors_config={"size": 1536, "distance": "Cosine"},
 )

 for path in tqdm(glob.glob("docs/*.md")):
 with open(path) as f:
 text = f.read()
 emb = client.embeddings.create(
 model="text-embedding-3-large", input=text
 ).data[0].embedding
 qdrant.upsert(
 collection_name="support_vectors",
 points=[
 {
 "id": os.path.basename(path),
 "vector": emb,
 "payload": {"content": text, "source": path},
 }
 ],
 )
 

What this does: Generates a dense vector for each document and stores it in Qdrant for fast similarity search.

1. Deploy n8n

 docker run -d --name n8n \
 -p 5678:5678 \
 -v ~/.n8n:/home/node/.n8n \
 n8nio/n8n
 

Open http://localhost:5678 and create a new workflow.

4. Add a Webhook trigger - Node type: Webhook - Method: POST - Path: support (e.g., https://yourdomain.com/webhook/support) This endpoint receives { "message": "User query" } from your chat widget.

5. Generate a query embedding - Add an OpenAI node (Create Completion → switch to Create Embedding). - Parameter Model: text-embedding-3-large. - Input: {{$json["message"]}}. - Output variable: queryEmbedding.

6. Search Qdrant - Add a Qdrant node, operation Search. - Collection: support_vectors. - Vector: {{$node["OpenAI"].json["queryEmbedding"]}}. - Top K: 3. This returns the three most similar docs and their similarity scores.

7. Build the RAG prompt - Add a Set node to concatenate retrieved snippets:

 {
 "prompt": "You are an AI support agent. Answer the user question using only the following excerpts. If the answer is unclear, say \"I don't know\".\n\nUser: {{$json[\"message\"]}}\n\nExcerpts:\n{{#each $node[\"Qdrant\"].json[\"hits\"]}}\n{{payload.content}}\n{{/each}}"
 }
 

What this does: Supplies the LLM with context limited to the top hits, reducing hallucination.

8. Call OpenAI for the final answer - Add another OpenAI node (Chat Completion). - Model: gpt-4o. - Temperature: 0. - Messages: [{ "role": "system", "content": "You are a concise support assistant." }, { "role": "user", "content": "{{$node[\"Set\"].json[\"prompt\"]}}" }]. - Store output as answer.

9. Confidence check & escalation - Add a IF node. - Condition: {{$node["OpenAI"].json["answer"]}} contains the phrase "I don't know" OR the highest similarity score from Qdrant < 0.65. - True branch → HTTP Request node that POSTs to your ticketing system webhook (include user message, answer, and source docs). - False branch → Response node that returns { "answer": "{{$node[\"OpenAI\"].json[\"answer\"]}}" } to the chat widget.

10. Connect chat UI - In your front-end, send the user message to https://yourdomain.com/webhook/support via fetch. - Display the answer field on success; display a generic "We've opened a ticket for you" if the escalation path was taken.

11. Test end-to-end - Use the n8n Execute Workflow button with sample payloads. - Verify that low-confidence queries produce tickets in your ticketing dashboard.

Result: A fully automated support loop that answers from your docs, limits hallucination, and escalates when necessary.

Where this breaks

With a similarity threshold of 0.65, this workflow reduces unnecessary ticket creation by roughly 40 % compared to a naïve chatbot that never escalates.

For a deeper technical reference, see n8n's documentation.