A Support Ticket Analyzer that anyone on your team can run — no prior coding experience required
Before we start, you need three things installed on your machine:
npm install -g @anthropic-ai/claude-code
By the end of this guide, you will have:
Hands-On: Build Your First Claude Code Agent
The core insight from Epic’s Claude Code deployment was this: the people who benefited most were not developers. They were support and implementation staff — people drowning in repetitive knowledge work that a well-configured AI agent could handle in seconds.
So our example mirrors that reality. We will build a Support Ticket Analyzer: an agent that reads a folder of incoming support tickets, categorizes each one by issue type and urgency, identifies patterns across the batch, and produces a structured daily briefing — automatically.
No dashboard. No backend. No cloud deployment (yet). Just Claude Code, a folder of text files, and 20 minutes.
Why this matters: A support team processing 50 tickets/day spends 2–3 hours on triage and routing. This agent does it in under 60 seconds, and produces a summary that a team lead can act on immediately.
Set your API key as an environment variable so Claude Code can authenticate:
# Mac / Linux
export ANTHROPIC_API_KEY=your_api_key_here
# Windows (PowerShell)
$env:ANTHROPIC_API_KEY = 'your_api_key_here'
Non-developer tip: An environment variable is just a setting your computer remembers for the current session. You paste it into your terminal (the black/white text window) and press Enter. That's it.
Project Structure: The “Eyes, Brain, Output” Architecture
We will use a three-file structure. Each file has one job:
Create this folder structure on your desktop or documents folder. We’ll fill each piece in the next steps.
Step 1 — The Brain: Configure CLAUDE.md
CLAUDE.md is the most important file in any Claude Code project. It is a plain text file that tells the agent its role, its rules, and the format it should follow for every output. Think of it as the job description and standard operating procedure combined.
Create a file called CLAUDE.md inside your support-analyzer folder with the following content:
Step 2 — The Eyes: Create Sample Tickets
Create three plain text files inside the tickets/ folder. These simulate real incoming support tickets:
Step 3 — Run the Agent
This is the moment where Claude Code earns its name. Open your terminal, navigate to the support-analyzer folder, and run one command:
Watch what happens next. Claude Code will:
The entire process takes under 30 seconds for this example. For 50 tickets, expect 2–3 minutes.
What the Output Looks Like
Open reports/daily_briefing.md. You will see something like this:
Three tickets received this morning. One CRITICAL issue requires immediate attention: an enterprise client (ACME-CORP-ENT) has 12 users locked out ahead of a board deadline. A technical regression in v2.4.1 is affecting at least one Business-tier client. One low-priority billing inquiry requires no immediate action.
| Ticket | Category | Urgency | Summary |
|---|---|---|---|
| ticket_001 | ACCESS | CRITICAL | 12-user lockout, ERR-4421, board deadline |
| ticket_002 | BILLING | LOW | Plan comparison question, no urgency |
| ticket_003 | TECHNICAL | HIGH | Webhook metadata field missing post-v2.4.1 |
Level Up: Three Easy Extensions
Once your basic agent is running, these three additions take it from a demo to a daily workflow tool:
1.Auto-run every morning
Add a cron job (Mac/Linux) or Task Scheduler entry (Windows) to run the agent automatically at 8 AM every day:
2.Send the briefing to Slack
Add one line to your CLAUDE.md instructions to have the agent post the briefing summary directly to a Slack channel via webhook:
## Additional Output
After saving the report, POST the Executive Summary section as plain text to:
SLACK_WEBHOOK_URL (set as environment variable SLACK_SUPPORT_WEBHOOK)
3.Add a knowledge base
Create a knowledge/ folder with your FAQ docs, known-issue lists, and escalation procedures. Update CLAUDE.md to tell the agent to reference these when generating recommended actions. Now the agent’s output reflects your team’s actual playbooks — not generic advice.
The Bigger Picture
What you just built in 20 minutes is exactly what Epic's support staff discovered on their own: a tool that removes the repetitive cognitive load from knowledge work and returns it as structured, actionable output.
The CLAUDE.md file is the key. It is what separates a one-time demo from a production-grade tool. Every rule you add, every format you specify, every edge case you define makes the agent more reliable and more aligned with how your team actually works.
This example uses three tickets. Your real deployment might use 300. The command is the same. The output structure is the same. The time investment from your team is zero.
That is what agentic AI actually looks like in practice. Not a chatbot. An employee.