Nonfarm payroll data came out yesterday and it was worse than expected.

This data is one of the key data points the Federal Reserve tracks in order to make decisions on interest rate policy.

So consequentially, us as investors need to pay attention too - but a challenge is translating the raw numbers into actual asset allocation takeaways...

What do the raw numbers mean? How should I interpret it in confluence with the myriad of other moving parts? What does this mean for my portfolio?

I am going to show you a technique I use to map historical corollaries using AI through raw data.

The idea is this:

AI fetches the latest raw payroll data
AI interprets the data vs estimates (ie was it a beat or miss vs expectations?)
AI maps historical setups on this raw payroll data to how the Fed reacted and subsequently how equities / credit / commodities reacted afterwards

This is a technique unique to AI investing.

History often repeats itself, but no single human can reasonably map every historical economic reaction to raw data as well as AI can.

The Prompt

Prompt 1: Use ChatGPT Thinking Mode

Objective: Analyze the most recent U.S. nonfarm payroll (NFP) release through the lens of historical parallels. Determine what it may signal for the economy and markets.

Tasks:

Fetch latest data

Report headline NFP number, unemployment rate, and wage growth.

Compare actual vs forecast.

Historical Parallels

Identify past episodes where NFP data showed similar weakness or surprise.

Do not limit to famous recessions—also include lesser-known downturns, soft landings, and cases where slowing or weak job growth was followed by economic resilience or expansion.

For each case, provide:

Date of NFP release and numbers vs expectations

Fed response (rate cuts/holds/other actions)

Short-term market reaction (S&P 500, Treasuries, gold)

Medium-to-long-term economic and market outcomes (recession, slowdown, soft landing, expansion)

Timing of when markets moved relative to NFP and Fed policy

Comparative Framework

Present findings in a structured table format for easy scanning.

Implications for Today

Evaluate which historical episodes most closely match the current setup.

Assess potential positioning implications for equities, bonds, and gold.

Keep conclusions objective, data-driven, and tied to historical precedent.

Output Style:

Structured and analytical, not narrative.

Tables + concise commentary.

Explicit connections between past patterns and today’s setup.

The Result:

Full output here: Link

Our AI analysis gave a huge table of different historical parallels:

Here were the closest historical parallels to the current situation with the payroll miss + likely Fed setup that AI identified:

1998 and 2019 soft-landing templates
Similarities: downside payroll surprise, rapid easing expectations, risk assets stabilizing or rallying after the initial move, bond yields down. Differences: today’s unemployment rate is rising, gold at records, and rate levels are different. Net: still a valid soft-landing analog if subsequent data stabilize.
Late-2007 cautionary template
Similarities: payroll disappointment and deteriorating unemployment trend. Differences: no systemic credit stress visible like 2007’s, and the Fed is poised to cut in an orderly fashion rather than emergency mode. Net: a risk case if the next 1–3 reports confirm a trend of rising joblessness.

If you want to continue down this path of diligence, I would recommend expanding on this prompt to specifically hone in on 1998/2019/2007 setups. For example, looking at data beyond payroll + doing a real double click on exact asset setups.

But directionally this 'historical parallels' technique has narrowed down your research task from entirety of recent history to just a few path dependencies to hone in on!

I recommend trying this technique out as well with other data beyond payroll.