The BotSquad trade experiment
What the team decided, why it decided, and what happens next. Follow the paper portfolio and open the evidence behind each decision.
Loading verified archive records… Current run state is not yet verified.
Latest operational update
Finite paper schedule active through 2026-10-27. Bounded company research and scheduled decision follow-up are enabled. Decisions and returns are not guaranteed.
Latest published decision
HOLD pending company evidence; do not force a trade to chase aspirational 30%.
Atlas proposed HOLD. Maya approved it.
Independent review approves the exact October 23 HOLD proposal, not a trade. The universe screen favors MSFT over 60 sessions and WMT over 20, but MSFT fell over five; full histories disclose unknown historical availability and unqualified adjustments. No issuer fundamentals, valuation or dated catalyst supports a risk-adjusted purchase. Reassess with dated issuer evidence and admissible observations; preserve all limits.
$100,000.00 cash · 0 holdings
Next scheduled review: . This is a published schedule, not a guarantee of completion.
Dated issuer evidence plus admissible observations establish a defensible capped investment case; revisit at next eligible session.
Experiment status
BotSquad Investment
Observed market data · modeled paper results · no real trades
Exact run: 0f6ea49caee91243f2f028a8ddde55abaa68faaaa2de453c ↗Official run: 0f6ea49caee91243f2f028a8ddde55abaa68faaaa2de453c. The selected run is never silently replaced.
2026-10-14 · inv-real-close-recovery-v1
Under this amendment, a new decision, independent review and order lock must precede the closing price reference. The missed morning OPEN remains missed; no trade is backdated. The original configuration and earlier records remain unchanged.
Owner amendment inv-real-close-recovery-v1: 2026-10-14 new decisions, reviews and orders must precede 2026-10-14T19:30:00.000Z; modeled fills use that session's regular CLOSE plus existing adverse slippage, observed later. Original morning opening was missed. Benchmark is cash then SPY at the same close. Historical usage gap and all consumed attempts remain retained. No real trades.
01 / Trade experiment
Participating workers from the published roster. No activity is inferred from availability alone.
Portfolio researcher
Develop research and alternatives, synthesize conclusions and submit scoped paper decisions.
Unknown
Independent reviewer
Independently challenge the exact thesis and paper proposal, evidence, downside and invalidation conditions.
Unknown02 / Trade experiment
Follow the research, the objections and what the team concluded. System records remain distinct from employee contributions.
03 / Trade experiment
Read the portfolio alongside the work that produced it. Financial values come from typed snapshots, never from discussion text.
Amendment: 0344c0273d7722816861d6439501ec8b7677e7eab91b6a8d. The initial cash-to-benchmark allocation is retained here; subsequent valuations apply the original benchmark rules.
129.925815 units · cash remaining $0.00 · raw closing reference $769.67.
Market reference 2026-10-14 20:00:00.000 UTC · available Unknown · retrieved 2026-10-14 20:07:35.933 UTC · allocation recorded 2026-10-14 20:20:03.643 UTC.
yahoo / yfinance · 2026-10-14 · regular close.
Portfolio and benchmark returns use the same configured starting capital. Excess return is measured in percentage points.
Latest loaded portfolio return 0.00%; benchmark -1.26%. 2 missing portfolio values and 0 sequence gaps remain disconnected.
━ Portfolio · circles┄ Benchmark · dashed
Latest loaded portfolio drawdown 0.00%; derived benchmark drawdown Unavailable. 2 missing portfolio values and 0 sequence gaps remain disconnected.
━ Portfolio · circles┄ Benchmark · dashed
| Session / version | Equity (USD) | Portfolio | Benchmark | Drawdown | Benchmark drawdown (derived) | Quality |
|---|---|---|---|---|---|---|
| 2026-10-14 · v1 | Unavailable | Unavailable | Unavailable | Unavailable | Unavailable | partial
Benchmark: Unavailable exact benchmark closing mark |
| 2026-10-14 · v1 | $100,000.00 | 0.00% | 0.00% | 0.00% | Unavailable | complete
|
| 2026-10-15 · v1 | $100,000.00 | 0.00% | +0.28% | 0.00% | Unavailable | complete
|
| 2026-10-16 · v1 | Unavailable | Unavailable | Unavailable | Unavailable | Unavailable | partial
Benchmark: Unavailable exact benchmark closing mark |
| 2026-10-19 · v1 | $100,000.00 | 0.00% | -0.40% | 0.00% | Unavailable | complete
|
| 2026-10-20 · v1 | $100,000.00 | 0.00% | -0.05% | 0.00% | Unavailable | complete
|
| 2026-10-23 · v1 | $100,000.00 | 0.00% | -1.26% | 0.00% | Unavailable | complete
|
| Category | Value | Weight |
|---|---|---|
| Cash | $100,000.00 | 100.00% |
| Category | Value | Weight |
|---|---|---|
| Cash | $100,000.00 | 100.00% |
No holdings available in this view. Unknown holdings are not a zero balance.
| Instrument | Quantity | Book cost | Mark | Value | Weight | Unrealized | Sector | Mark time / quality |
|---|
04 / Trade experiment
A recommendation, an accepted order and a completed simulated fill are different records. A decision to wait belongs here too.
HOLD cash rather than buy a concentrated stock on limited price-only evidence. Facts: The last valuation shows $100,000 cash and no paper holdings.; The retained gateway excerpt has three completed daily rows through October 15 for most instruments; XOM research input was rejected.; SPY is a separate benchmark, not a portfolio holding. Assumptions: Preserving cash is preferable to a concentrated position without demonstrated advantage for this session.; Historical bars are research context, not executable quotes. Horizon: October 16, 2026 paper session; reassess at the next authorized decision. Position-change reason: No position change: the retained packet does not establish a stock-specific edge, while prior cash-drag concern remains. Research limitation: XOM daily price data failed OHLC validation and was unavailable for this decision. No replacement price was fabricated; orders for that instrument were disabled for this cycle.
Evidence, dissent & outcome →Hold cash in the paper portfolio rather than adding unsupported or blocked risk. Facts: The last reported portfolio valuation is cash-only with no positions.; The benchmark is SPY, but the last valuation lacks a usable SPY mark.; The gateway provides completed daily bars through October 16, not an executable quote. Assumptions: The reported cash-only book is current; no intraday execution price is inferred from completed daily bars. Horizon: One session, with reassessment at the next authorized review. Position-change reason: No change from prior cash HOLD: a fresh three-day gateway excerpt has not established a supported edge, while a private-state risk block remains.
Evidence, dissent & outcome →Retain cash for this session pending a documented, risk-aware investment case. Facts: October 19 portfolio valuation was $100,000 entirely cash; benchmark valuation was $99,601.13.; AMZN's October 19 verified close was $262.45; chart history is non-executable research. Assumptions: Recent price action alone is insufficient to establish a forward investment edge. Horizon: October 20 through December 31, 2026; reassess next approved session. Position-change reason: New 120-day chart history and complete October 19 valuation improve context, but do not resolve issuer-evidence gaps.
05 / Trade experiment
Published reports keep permanent exact-version links. Every registered deliverable has a visible publication state, including material that cannot be shown.
No public deliverables are registered.
Publicly designated summaries of genuine employee investment decisions and independent reviews. Private transcripts and raw evidence are withheld.
06 / Trade experiment
Read-only records of simulated financial actions, rejected requests and corrections. No public trading controls.
A typed ledger effect; no discretionary order is implied.
Cash impact: $100,000.00
07 / Trade experiment
Persistent employees, bounded assignments and inspectable evidence. A review can change the next decision without rewriting the old one.
Workers gather permitted evidence and publish a report with its limitations.
Discussion makes alternatives, objections and unresolved questions visible.
A proposal binds exact evidence. Independent review precedes any accepted order.
Trusted accounting records simulated effects. Later reviews examine what happened.
The selected run’s original configuration and any published, session-specific amendment govern its method. Capital, universe, fees, slippage and limits remain in the frozen configuration. Missing or blocked observations stay explicit. Published results do not prove reasoning quality or predict future performance.
Methodology, data quality & interventions →08 / Trade experiment
The planned service will connect a question to one relevant actual employee and the exact evidence under discussion.
For this amendment, the benchmark stays in cash until the same session’s qualified close, then allocates to SPY. The allocation evidence is retained with subsequent valuations. Later benchmark rules remain those of the original configuration.
The earlier employee-usage accounting gap is retained. Missing usage and cost are not reconstructed or reported as zero.
An amendment authorizes a method; it does not establish that an order filled or that a valuation is complete. Read each decision’s rationale and review, the exact fill evidence, and valuation limitations.
A personal noncommercial paper-investment experiment using real market observations and genuine AI employees.
Study evidence-driven decisions, independent challenge and transparent long-term accounting; no guaranteed return.
Universe: AAPL, MSFT, GOOGL, AMZN, JPM, JNJ, XOM, WMT.
Opening reference: Same-session raw daily chart OPEN, captured after that session closes and used only for precommitted modeled paper orders; not a tradable quote.
Yahoo Finance via pinned yfinance direct daily chart adapter. Yahoo permission is owner-reported. · 0s configured delay.
Decisions precede the target session. Its completed daily bar is retrieved after close; the OPEN is a modeled paper-execution reference. Market reference, evidence retrieval and accounting times are separate.
HOLD pending company evidence; do not force a trade to chase aspirational 30%. Facts: Portfolio remains $100,000 cash with no holdings at last October 20 valuation.; MSFT's 60-session as-delivered close gain is 33.4255%; its five-session change is -3.4035%.; WMT's 20-session as-delivered close gain is 12.5755%; SPY's is -0.4197%. Assumptions: No issuer fundamentals or catalyst may be inferred from price history.; No next-open price or fill is known. Horizon: October 23 session through December 31, 2026 evaluation end. Position-change reason: Current complete universe screen changes the shortlist from earlier AMZN interest to MSFT and WMT, but not the cash decision.
Evidence, dissent & outcome →