Analyzing Job Market Trends with Claude Code and BLS Data

If you’re building anything that touches the labor market — a hiring dashboard, a workforce planning tool, an economic research pipeline — you need real employment data to develop against. With AgentPatch connected, Claude Code can pull unemployment rates and payroll figures directly from the Bureau of Labor Statistics, analyze trends, and turn the findings into code or reports without you switching to a browser.

Why This Matters

Job market analysis usually involves juggling multiple data sources. You pull the unemployment rate from one place, nonfarm payrolls from another, then try to line up the time periods and figure out what the numbers mean together. It’s tedious, and if you’re doing it to inform a feature you’re building, you’d rather spend the time on the feature itself.

The BLS Data tool lets Claude Code query up to 5 series in a single call. That means you can pull unemployment, payrolls, and other labor indicators together, get structured data back, and ask Claude Code to analyze it — all in one session. The data comes with optional calculations like net and percent changes, so trend analysis doesn’t require you to compute deltas manually.

Setup

Install the AgentPatch CLI (zero dependencies, Python 3.10+):

pip install agentpatch

Set your API key:

export AGENTPATCH_API_KEY=your_api_key

Then use it:

ap search "web search"
ap run agentpatch google-search --input '{"query": "test"}'

Get your API key from the AgentPatch dashboard.

Run this command to add AgentPatch as an MCP server:

claude mcp add -s user --transport http agentpatch https://agentpatch.ai/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Replace YOUR_API_KEY with your actual key from the AgentPatch dashboard. Claude Code discovers all AgentPatch tools automatically.

Example

You’re building a labor market dashboard and want to prototype the analysis logic against real data. You tell Claude Code:

“Pull the unemployment rate and total nonfarm payrolls for 2024 and 2025 with year-over-year percent changes. Then summarize the job market trend and suggest what metrics we should track on the dashboard.”

Claude Code pulls both series in one call:

Fetching BLS series LNS14000000 and CES0000000001 for 2024-2025
with calculations enabled...

Unemployment Rate (LNS14000000):
  Ranged from 3.7% to 4.1% over the period.
  YoY change: unemployment edged up ~0.3 percentage points through 2025.

Total Nonfarm Payrolls (CES0000000001):
  Grew from 156,100K to 157,600K.
  YoY change: averaging +180K jobs/month in 2025, down from +220K in 2024.

Summary: The labor market is cooling gradually. Unemployment is trending up slowly
while payroll growth is decelerating. Still positive, but the pace is slowing.

Recommended dashboard metrics:
- Unemployment rate (headline + trend)
- Monthly payroll change (bar chart)
- 3-month rolling average of payroll additions
- Unemployment rate vs. payroll growth (dual-axis chart)

Want me to create the TypeScript types and mock data based on these real values?

Claude Code analyzed the data, gave you a plain-English summary of the trend, and proposed concrete dashboard metrics — all grounded in real BLS data. From here you can have it generate the component code, seed test fixtures, or write the data fetching layer.

Wrapping Up

AgentPatch turns Claude Code into a research-capable agent that can pull live government data and act on it in the same session. BLS Data is one tool; the same connection gives you access to FRED, Census data, web search, and everything else on the marketplace. Head to agentpatch.ai to get started.

← Back to blog