Opening move: audit the books before the story
The Michael Burry Agent's default posture isn't "why does the market love this?" It's: is there a line in the 10-K or 10-Q quietly contradicting the story? Revenue is growing — are receivables growing faster? Earnings look great — is the cash keeping up? Are stock comp, depreciation, and capitalized costs quietly pushing real expenses into the future?
Its job isn't to shout long or short for you. It puts a company back inside the constraints of accounting, cycles, and valuation. The narrative can be beautiful and management can be very good on a call, but the numbers always leave fingerprints somewhere. This agent dusts for them.
What it trusts first
This agent's sources have a strict pecking order. The freshest data in the database comes first — the latest posts, Trading Post entries, reports, prices, and filings. Where new content conflicts with older writing, the new content wins, labeled as the latest stance as of its date.
- Fresh data first — never numbers from memory Current prices, moves, market caps, rates, and filing figures all get looked up. Historical levels in old articles are anchors for their publication date, not answers for today.
- Primary sources over secondhand summaries It searches the long-form Cassandra Unchained essays first, then Short Thoughts, Trading Post, and X posts. Framework documents supply method and voice — they don't substitute for fresh data.
- Web search is a data layer, not an opinion layer News, announcements, analyst reports, and company talking points are raw material only. It extracts the data points first, runs them through the forensic-accounting and cycle frameworks, and never dresses a judgment up as "according to recent reports."
- If it hasn't done the work, it says so If the corpus doesn't cover a name, it will say "I haven't taken this one's 10-K apart," then offer a framework-based read — rather than pretending a published conclusion exists.
Where the forensic accountant looks
What sets it off isn't grand narratives — it's the accounting lines that wreck a narrative the moment they slip out of place. Accounts receivable (AR), days sales outstanding (DSO), stock-based compensation (SBC), depreciation, inventory, deferred revenue, capitalized costs, construction in progress (CIP), off-balance-sheet purchase obligations, backstops, and residual value guarantees (RVGs) — all places where the story and reality can come to blows.
Say revenue growth looks great but DSO is stretching even faster. It won't declare "strong growth" — it will first ask whether that's channel stuffing, fading pricing power, or revenue getting pulled forward. When management says demand is "still strong," it takes the word "still" apart. Still? The more subtle cousin to If.
Valuation isn't a number — it's a set of implied conditions
On valuation, it translates the market price into implied assumptions: fifteen-year intrinsic value (IV15), the AI capital-cycle tracker (AICT), where price sits relative to IV15, the direction of earnings, the speed of cash conversion, and what the current narrative requires the company to keep pulling off, quarter after quarter.
When it cites valuation figures from past articles, it attaches the article date and reminds you those numbers belong to that moment's data — rerun them with current filings and prices. It won't hand you a lone "price target" dressed up as precision. It cares how much growth, how much margin, and how much return on capex that price is demanding — and whether those conditions have started to slip.
The capital cycle: which link is the fire at?
For AI data centers, semiconductors, and the power chain, it locates the capital cycle first: build-out, peak, or the bullwhip already swinging back. Hyperscaler capex, order books, delivery schedules, supply expansion, financing conditions, and customer concentration together decide whether the fire is burning in chips, racks, networking, power, land — or back onto the balance sheet.
That's the core question it asks of Nvidia, Palantir, SOXX, or the data-center transmission chain: the narrative says demand is infinite, but the books tell you who fronts the cash, who books revenue first, who carries the depreciation, and who actually collects at the end. History rhymes.
What its output looks like
A complete answer compresses into four blocks rather than sprawling into an industry survey. The point is to hand you a research conclusion you can verify, falsify, and wait on.
-
01
The forensic accounting verdict
First, what's off in the books — or where nothing looks obviously wrong yet. The checklist: days sales outstanding, cash flow, stock-based compensation, depreciation, inventory, deferred items, and capitalized costs.
-
02
Capital cycle vs. the narrative
Next, is it in build-out, at the peak, or rolling over — and has the market's story already outrun what the balance sheet, cash conversion, and industry supply-demand can support?
-
03
The transmission chain
Then trace the risk or opportunity through customers, suppliers, financing, inventory, capacity, and pricing, to locate which link benefits first, strains first, or cracks first.
-
04
The fat pitch
Finally, the Fat Pitch Zone: what triggers the thesis, what falsifies it, and which variables to watch next. And when there's no fat pitch, it says exactly that — no fat pitch here.
Try asking
These questions put it straight into working mode. Don't ask a vague "are you bullish?" — make it audit the books, place the cycle, and find the trigger.
Who it's for
It's not here to validate your feelings, and it won't send retail investors into impulsive shorts. It's for people who already have a name, a supply-chain question, or a long-short thesis — and want the numbers to cross-examine the story.
- US equity researchers who need to take apart 10-Ks, 10-Qs, cash flow, and receivables quality
- Investors testing whether the bull story is already more than priced in
- Supply-chain watchers tracking AI compute, data centers, chips, and power bottlenecks
- Anyone who wants a short thesis broken into triggers, falsification conditions, and variables to watch
Boundaries: no fat pitch, no swing
The Michael Burry Agent doesn't promise returns, doesn't call exact prices or timing, and won't tell everyday investors to lever up or short on impulse. Shorting isn't the answer for most people. Much of the time, the right move is simply trimming, standing aside, or waiting for the fat pitch to show up.
When put protection is already expensive, it won't mechanically tell you to buy puts. If you want to keep the upside, it treats low-cost, far-dated out-of-the-money calls as an alternative that deserves its own analysis. With no clean trigger, it says "no fat pitch here" — and tells you which signal to keep waiting for.
Do I need to short? I do. Does anybody else? That is up to them. This is my thinking, I may be wrong, not investment advice, and your positions are your own.
Michael Burry
Hey, I'm Michael Burry — you call me the Big Short, but most of the time I'm actually long. Other people read narratives; I read 10-Ks. This agent is my brain: give me a ticker, and I take apart the books, place it in the cycle, and call the fat pitch.
This agent offers an analytical perspective only. Content is for reference and is not investment advice.
