AI Prompt Library for Russell 2000 (IWM)

The Russell 2000 underperformed the S&P 500 by more than 15 percentage points in 2023, yet IWM options volume hit record highs — meaning traders were active in the space even as price lagged. That divergence is precisely where AI-assisted analysis earns its keep: identifying when small-cap weakness is a macro signal versus a tradeable dislocation.

IWM is not a passive index bet. With 2,000 components spanning micro-cap industrials, regional banks, and speculative biotech, the ETF is a live readout of domestic economic confidence. Rate sensitivity, credit spreads, and USD strength all hit IWM before they register in large-cap indexes. Misread the setup and you’re fighting the Fed. Read it correctly and you’re trading the leading edge of a risk-on or risk-off regime shift.

This page is a working prompt library built specifically for IWM. Each prompt is designed to extract a concrete analytical output — not a summary, not a definition — from any major AI model. Use them sequentially as a pre-trade workflow or pull individual prompts when you need a fast read on a specific variable.

Why IWM Demands a Different Analytical Framework

Large-cap ETFs like SPY or QQQ are dominated by a handful of mega-cap names that can mask underlying market conditions. IWM has no such concentration risk — its top 10 holdings rarely exceed 3% of total weight. That equal-weight character means IWM price action is genuine breadth data. When IWM drops, it is telling you that hundreds of smaller companies are repricing simultaneously, not that one earnings miss dragged the index lower.

This structural difference changes what you should be asking an AI. For SPY, macro narrative and earnings revisions dominate. For IWM, the questions that matter are: How is credit availability trending for small-cap borrowers? What is the spread between IWM implied volatility and realized volatility signaling about institutional hedging? Is the regional banking sub-sector — historically 15-18% of IWM — acting as a leading indicator or a laggard? The prompts below are built around these IWM-specific leverage points.

One additional factor: IWM is the most actively traded small-cap vehicle, which means its options market is deep enough to generate reliable flow data. Dark pool prints on IWM are closely watched by institutional desks. Any AI workflow for this ETF should incorporate options positioning as a core input, not an afterthought.

• IWM top-10 holdings weight: typically under 3% — true breadth exposure
• Regional banks comprise 15-18% of index weight — a critical sub-sector to isolate
• IWM correlates negatively with USD strength more than SPY or QQQ
• Small-cap earnings revision cycles lead large-cap by 4-6 weeks historically
• IWM options open interest spikes often precede directional moves by 48-72 hours

Prompt 1: Macro Regime Classification for IWM

Before any directional trade on IWM, you need to establish which macro regime you are operating in. Small caps are highly sensitive to the rate cycle, credit conditions, and the shape of the yield curve. A prompt that forces the AI to classify the current regime — and assign a historical analog — gives you a structured baseline instead of an opinion.

The output from this prompt should not be a narrative paragraph. Structure your request so the AI returns a regime label, the three most relevant historical parallels, and a directional bias for IWM under each analog. That output becomes the first cell in your trade thesis.

You are a macro analyst specializing in small-cap equities.
Current inputs: [2-year yield], [10-year yield], [HYG price or HY spread], [USD Index level], [IWM 50-day vs 200-day MA relationship].
Classify the current macro regime for Russell 2000 / IWM using these categories: Risk-On Expansion, Late-Cycle Rotation, Credit Stress, Rate-Driven Compression, or Recovery Phase.
Provide three historical analogs from 2000-present.
For each analog, state IWM's forward 30-day and 90-day return and the primary catalyst.
Conclude with a directional bias (bullish / bearish / neutral) and the single highest-conviction risk to that bias.

Prompt 2: Regional Bank Sub-Sector Pressure Test

Regional banks are the load-bearing wall inside IWM. When KRE — the regional bank ETF — diverges from IWM’s broader direction, you have an actionable signal. A rising IWM with a falling KRE is a distribution warning. A falling IWM with a stabilizing KRE is often a false breakdown. The AI prompt below forces a systematic comparison rather than a visual eyeball.

Feed this prompt weekly. The output should flag whether the bank sub-sector is confirming or contradicting IWM’s current trend. That confirmation or divergence becomes a primary filter for sizing any IWM position.

Compare the price performance of KRE (regional banks ETF) versus IWM over the past 10, 20, and 60 trading days.
Calculate the rolling correlation between KRE and IWM over the same windows.
Identify any periods of significant divergence (correlation below 0.6 or relative performance gap exceeding 5%).
For each divergence period, determine whether IWM subsequently reverted toward KRE or KRE reverted toward IWM.
Based on current data, state whether the bank sub-sector is a bullish confirmation, a bearish warning, or a neutral factor for IWM directional positioning.
Output in table format.

Prompt 3: Options Flow Interpretation

IWM’s options market is one of the most informative in the ETF universe. Put/call ratios, skew, and unusual sweep activity all contain positioning intelligence that price action alone does not reveal. The challenge is filtering signal from noise — institutional hedges look identical to directional bets in raw flow data.

This prompt is designed to help you interpret a specific flow event rather than summarize general options theory. Paste in the actual flow data — strike, expiry, premium, bid/ask side — and instruct the AI to classify it within the context of IWM’s current technical structure.

I will provide an unusual options flow print on IWM. Classify it as: institutional hedge, directional speculative bet, covered call program, or spread leg.
Flow data: [strike], [expiry], [premium paid], [bid or ask side], [open interest before print], [current IWM price and trend].
Explain the most probable intent behind this flow given current IWM IV rank and the macro regime.
State the price level at which this position becomes profitable and the level at which it signals a regime change.
Provide one confirming indicator I should monitor to validate the classification.

Prompt 4: Small-Cap Earnings Revision Cycle Analysis

Earnings revisions for small caps move differently than large caps. Analyst coverage is thinner, guidance is less precise, and revisions tend to cluster — when one small-cap industrial misses, the entire sub-sector gets revised down within two weeks. Tracking this revision cycle is an early warning system for IWM drawdowns.

Use this prompt during earnings season to build a forward-looking picture of where IWM component earnings estimates are trending. A net negative revision environment that is accelerating is one of the most reliable precursors to a sustained IWM downtrend.

• Pull the earnings revision ratio (upgrades vs. downgrades) for IWM’s top 5 sub-sectors by weight
• Compare current revision trend to the same week in the prior two earnings cycles
• Flag any sub-sector where downgrades exceed upgrades by more than 2:1
• Identify whether the revision pressure is concentrated in rate-sensitive names or in cyclicals
• Output a net revision score: positive, negative, or deteriorating neutral

Building a Pre-Trade Checklist Around These Prompts

Individual prompts generate data points. A sequenced workflow generates a trade thesis. The four prompts above are designed to be run in order: macro regime first, then bank sub-sector confirmation, then options flow, then earnings revisions. Each output either strengthens or contradicts the directional bias established in the previous step.

If three of four outputs align — say, a Risk-On Expansion regime, KRE confirming IWM’s uptrend, neutral-to-bullish options flow, and net positive earnings revisions — that is a high-conviction setup. If outputs conflict, that is a signal to reduce size or wait for resolution, not to force a trade.

Save each prompt output with a date stamp. Over time, you build a proprietary dataset of how your AI-assisted framework performed across different IWM environments. That feedback loop is what separates systematic use of AI from ad hoc querying.