Paper trading. No real money is invested and nobody earned these results. Every figure here is hypothetical. The full disclosures →
HYPOTHETICAL PERFORMANCE These are paper-trading portfolios. No client money is invested, no orders are routed to any venue, and no result shown here was achieved with real capital. Hypothetical results have inherent limitations and do not reflect the effect of real order flow on price.
AI Portfolios
The public record of AI-managed portfolios.

P14 · Retired

Bottleneck Hunters

by AI Portfolios

No recorded value yet. This book is not at zero — it has not been marked.
All time
—
Holdings
0
Risk level
high
Read this with the numbers

The instrument selection in this portfolio is made by a large language model working a published thesis. Position sizes, stop levels and every risk limit are computed by deterministic code the model cannot see or influence.

The thesis' "obscurity" requirement is enforced as a MARKET-CAP CEILING of $150 billion — the mechanical part of the rule. The platform's licensed universe is currently the S&P 500 / 400 / 600 + Nasdaq-100 compilation (~1,550 names, session 14) — the mid- and small-cap hunting ground is real, from SSGA's free daily holdings files.

This portfolio is labelled EXPERIMENTAL from inception: it tests whether AI deep research can express this thesis at all, and it may fail. The label predates any result.

Research runs once weekly (Tuesday); risk management (stops, forced exits, NAV marks) runs every session. Days without a decision are chart points, not missing runs. One disclosed exception: the portfolio's FIRST research cycle runs at deployment whatever the weekday — a new book must not sit empty for up to a week — and the exception self-disables after that first run, detected from the audit chain itself.

The model identity and prompt version are published; any change is a MODEL_CHANGE event in the audit chain.

About

Markets are quick to price the companies everyone can see and slow to price the ones nobody looks at. A bottleneck is worth more than its size suggests because the cost of NOT buying its product is a stopped production line, a failed certification or a redesigned system — so the customer pays, year after year. The research burden is proving the chokepoint is real: every proposal must name what is controlled, who cannot function without it, and why switching away is prohibitively expensive. A thesis that cannot fill in those three blanks is not a bottleneck, it is a stock somebody likes.

Follow Bottleneck Hunters

This is the simple view. Nothing has been removed — the decision records, the refused proposals, the AI's own words, the cost model, the published limits and the hash chain are all in Advanced, which is the switch in the header. How to verify any of it →

Showing every layer. Pick Simple or Advanced in the header to choose one — nothing is removed either way, and the full record is always in this page.

Home / portfolios / P14

Bottleneck Hunters

P14retiredhigh riskrulebook v1.4.0rank and explain
RetiredRETIRED

This book is closed. Its record stays published in full; retirement is a state transition recorded as an event, not a deletion.

This portfolio is retired. It is preserved unedited, it appears in every aggregate statistic on this site, and it was never deleted. It never traded: it was withdrawn before launch, so it has no results to report and contributes nothing numerically. It is published because a reader who cannot see what was withdrawn cannot judge what remains. Retired without ever opening a position. The mandate's selection criterion is qualitative — it requires evidence of supplier concentration, certification barriers, patent position, customer dependency and switching cost — and the platform's fact pack contains none of it. Asked to decide, the model correctly declined rather than assert a thesis from training data, which its own hard constraints forbid as a source of fact. The book was not failing; it was being asked to prove something the platform cannot show it.

Own companies that control something an industry cannot easily function without: sole or limited-source suppliers, extreme switching costs, tiny components inside huge end-markets, specialised machinery, certification barriers, patents and geographic monopolies — with a strong preference for names most retail investors have never heard of. The ideal holding is a small supplier of a boring product that is absolutely critical, with the pricing power that position implies.

Bottleneck Hunters's decisions, live →The public decision feed posts every decision when it's made — before settlement, refusals included. On Telegram, free.
Cadence — when it last decided, and when it next will
Next decision due
2026-09-29 22:00Z
Decision slots
1 · 1 non-deciding
SlotLast dueAnsweredStatus
weekly deep research
0 18 * * TUE · America/New_York
—neverunchecked
This slot marks and reports; it never calls the model, so it leaves no decision record to check it against.
monthly review
0 12 1 * * · America/New_York
—n/adoes not decide
This slot marks and reports; it never calls the model, so it leaves no decision record to check it against.

Catch-up policy. A decision instant that passes unanswered is run on the next pass, once, and the record stamps both instants — when it was due and when it actually ran. Past the catch-up window the gap stays open and is published as missed rather than backfilled.

Track record

No track record exists.

This portfolio was retired before its first decision cycle and is preserved in this state permanently.

Starting capital
$100,000own work — never restated
Benchmarks
SPY · URTH, RSP
Mandate hash
22fffbf98de2597685059170264dbe38448a7f9f2f23bf82b3e3768ae1bad216

What the AI is allowed to do

This portfolio's AI ranks candidates and explains its reasoning. It proposes direction and conviction only. Every price, quantity, weight and risk limit is computed by deterministic code the model cannot see or influence.

It may propose

BUY · ADD · TRIM · SELL · HOLD · TIGHTEN_STOP · FLAG_THESIS_BREAK

At most 4 proposals per run, each carrying a direction, a conviction from 1 to 5, a rationale, and references to the facts it used.

It cannot
  • set a price
  • set a quantity or share count
  • set a weight or position size
  • set or move a risk limit
  • execute anything

Model tier deep · prompt version P14-v1. Any change to the decider or the prompt is recorded as a MODEL_CHANGE event in the audit chain — without it the record would be a chimera of two systems presented as one.

Enforced limits

Every limit below names the code path that enforces it. This is not decoration: a limit that is published but never fires is worse than no limit, because a reader has no way to tell the difference. A test walks every mandate, drives the engine into the state each declared control claims to protect against, and fails the build if nothing stops it.

exposure
LimitValueEnforced by
Maximum gross exposure100.0%gate 2 — size_order
Maximum single sector40.0%gate 2 — size_order
permissions
LimitValueEnforced by
Shortingprohibitedgate 1 — proposal validation
Derivativesprohibitedgate 1 — proposal validation
Marginprohibitedgate 1 — proposal validation
Leverageprohibitedgate 1 — proposal validation
sizing
LimitValueEnforced by
Maximum positions12gate 3 — BREACH_MAX_POSITIONS (portfolio limit check)
Minimum new position2.0%gate 2 — size_order
Maximum order as % of ADV0.5%gate 2 — size_order
loss limits
LimitValueEnforced by
Monthly loss limit15.0%gate 3 — HALT_MONTHLY_LOSS_LIMIT
Single-day loss alert6.0%gate 3 — alert
data integrity
LimitValueEnforced by
Stale-data halt48 hoursgate 3 — HALT_STALE_DATA
drawdown ladder
LimitValueEnforced by
At −12.0% drawdownalert, publish_commentarygate 3 — drawdown ladder
At −20.0% drawdownalert, pause_new_positions_days:10, mandatory_deep_reviewgate 3 — drawdown ladder
At −30.0% drawdownalert, pause_new_positions_days:30, publish_commentarygate 3 — drawdown ladder
At −45.0% drawdownsuspend_portfolio, graveyard_reviewgate 3 — drawdown ladder
turnover
LimitValueEnforced by
Max trades per month8entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit)
Min holding period days10entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit)
circuit breakers
LimitValueEnforced by
Halt trading if price gap unexplained pct25gate 3 — circuit breaker
Halt trading if factpack hash mismatchtruegate 3 — circuit breaker

Disclosures specific to this portfolio

These render on the page itself rather than in a footer, because without them the numbers actively mislead.

  • The instrument selection in this portfolio is made by a large language model working a published thesis. Position sizes, stop levels and every risk limit are computed by deterministic code the model cannot see or influence.
  • The thesis' "obscurity" requirement is enforced as a MARKET-CAP CEILING of $150 billion — the mechanical part of the rule. The platform's licensed universe is currently the S&P 500 / 400 / 600 + Nasdaq-100 compilation (~1,550 names, session 14) — the mid- and small-cap hunting ground is real, from SSGA's free daily holdings files.
  • This portfolio is labelled EXPERIMENTAL from inception: it tests whether AI deep research can express this thesis at all, and it may fail. The label predates any result.
  • Research runs once weekly (Tuesday); risk management (stops, forced exits, NAV marks) runs every session. Days without a decision are chart points, not missing runs. One disclosed exception: the portfolio's FIRST research cycle runs at deployment whatever the weekday — a new book must not sit empty for up to a week — and the exception self-disables after that first run, detected from the audit chain itself.
  • The model identity and prompt version are published; any change is a MODEL_CHANGE event in the audit chain.

Execution

Cost profile
zero_commission_us
Fill convention
vwap_window
Decision → order latency
60s
VWAP window
15 minutes

Fills are struck on a VWAP window that begins strictly after the decision timestamp plus a latency delay. No fill can use information from the bar in which the decision was made, so look-ahead is arithmetically impossible rather than merely avoided.

Philosophy

Markets are quick to price the companies everyone can see and slow to price the ones nobody looks at. A bottleneck is worth more than its size suggests because the cost of NOT buying its product is a stopped production line, a failed certification or a redesigned system — so the customer pays, year after year. The research burden is proving the chokepoint is real: every proposal must name what is controlled, who cannot function without it, and why switching away is prohibitively expensive. A thesis that cannot fill in those three blanks is not a bottleneck, it is a stock somebody likes.

Review schedule

JobCronTimezoneMakes a decision
weekly deep research0 18 * * TUEAmerica/New_Yorkyes
monthly review0 12 1 * *America/New_Yorkno

Published on a fixed, regular schedule. Never event-triggered — no "market is crashing, sell now" alerts, deliberately. This table is the promise; the cadence panel at the top of the page is whether it was kept, instant by instant.

Machine-readable mandate: config/portfolios/P14_bottleneck_hunters.yaml · human rulebook: docs/portfolios/P14_bottleneck_hunters.md · effective from 2026-08-10 (wall clock) · payload 540d30e63326…

Every trade, as it happens
What each portfolio bought, what it sold and what it lost. Free, on Telegram.
Join →
Or follow @AIPortfolios186 on X, where the same trades are posted.
Live public decision feed.Every decision, fill and refusal, as it is published — including the ones that lose money. Delivered on Telegram, free.Get the feed →or subscribe by RSS/Atom

The same decisions are posted on X as @AIPortfolios186.

Data provided for free by IEX. By accessing or using IEX Historical Data, you agree to the IEX Historical Data Terms of Use. · Powered by CoinGecko · Logos provided by Logo.dev · Company logos identify holdings only and imply no endorsement.