Create a new project
From the Dashboard, go to Projects → New project. Name your project “NovaTech Support”, keep the default chat settings, and select Start from scratch.This opens the global agent view, where you’ll configure your agent’s high-level behavior.
Import your FAQ data
Click Knowledge Base in the left sidebar, then Add data sources. Select Table and upload a CSV file containing your support FAQs.Each row in your CSV becomes a separate chunk, and column headers become field names — this makes it easy for the agent to find the right answer for a given question. Use the sample below as a starting point:
Set up the global prompt
Click the Agent tab. In the Global prompt section, define your agent’s personality and behavior. You can click generate to create a prompt from a short description, or write one directly. Use the example below as a starting point:
Create a troubleshooting playbook
In the Agent tab, click + in the Skills panel to create a new playbook. Name it “Troubleshooting”.Set the LLM description so the agent knows when to trigger it:Then write the playbook instructions:
Add agent instructions and test
Go back to the Agent tab. In the Instructions field, add routing logic so the agent knows when to use the playbook:Click Run in the top-right corner to test your agent. Try prompts like:
- “How do I add someone to my team?”
- “My dashboard is super slow, what’s going on?”
- “I need to set up 2FA on my account”
Tips for refining your agent
- Expand your FAQ data. The more Q&A pairs in your CSV, the more questions your agent can handle accurately. Add rows as you discover common support requests.
- Iterate on your prompt. Small tweaks to the global prompt can make a big difference — try adjusting the tone or adding specific guardrails based on what you see in testing.
- Layer on complexity. Once the basics work, you can add more playbooks for different support scenarios (billing disputes, account setup, etc.) and use system tools like Cards or Buttons to make responses more interactive.
What’s next?
You’ve built a support agent grounded in real FAQ data. Now explore more ways to power your agent.Importing data sources
Learn about all the ways to populate your knowledge base.
Playbooks
Build more sophisticated goal-based skills for your agent.