Give customers fast, helpful answers inside chat. A smart assistant reads each message, keeps short context, and pulls facts from the web when needed. Support teams use it to reply faster, reduce escalations, and keep users engaged.

New chat messages trigger an AI agent. The agent uses an OpenAI chat model and a short memory that stores the last 20 messages, so it understands the ongoing conversation. When it needs current facts, it can search the web with SerpAPI and look up details on Wikipedia, then reply in clear language. This mix of memory and live data helps handle product questions, pricing checks, policy clarifications, and how to articles without switching tools.

Setup is simple. Connect OpenAI and SerpAPI, pick the model, and confirm the memory window is set to 20. Expect faster first replies, fewer handoffs, and more chats handled per agent. Great for website chat, in app help, or internal support desks that need quick and accurate answers with trusted sources.

• Chat event trigger starts the flow the moment a new message arrives.
• OpenAI chat model gpt 4o mini generates clear and helpful replies.
• Memory buffer keeps the last 20 messages to maintain context.
• SerpAPI tool searches the web for fresh, real time information.
• Wikipedia tool provides quick reference facts and summaries.
• Agent decides when to use tools and when to answer directly.
• Configurable model and memory window to fit your support needs.

• Reduce first reply time from minutes to under 10 seconds
• Automate up to 60 percent of routine chat questions
• Handle up to 5 times more concurrent chats with the same team
• Improve answer accuracy by using live search and Wikipedia
• Connect external knowledge sources without leaving the chat

1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
2. You'll need accounts with OpenAI and SerpAPI. See the Tools Required section above for links to create accounts with these services.
3. In the n8n credentials manager, create an OpenAI credential. Choose API Key, paste your OpenAI API key from your OpenAI account API page, and give the credential a clear name.
4. In the n8n credentials manager, create a SerpAPI credential. Choose API Key, paste your SerpAPI key from the SerpAPI dashboard, and name it so your team knows what it is used for.
5. Open the OpenAI Chat Model node and select your OpenAI credential. Confirm the model is set to gpt 4o mini or choose another model if needed.
6. Open the SerpAPI node and select your SerpAPI credential. Leave default search settings for initial tests.
7. Open the Simple Memory node and confirm the context window length is 20 to keep recent conversation history.
8. Open the AI Agent node and make sure the language model, memory, SerpAPI, and Wikipedia tools are all connected as inputs. Save your changes.
9. Open the When chat message received trigger and ensure it is active. Start the workflow so it can receive chat messages.
10. Send a test message in your n8n chat interface. Check the Executions view to confirm the agent responds and uses tools when needed.
11. If you see invalid key errors, recheck the OpenAI or SerpAPI credentials. If responses time out, review rate limits and reduce tool calls. Adjust the memory window if replies drift off topic.