T BOT puts institutional-grade, AI-run investing within reach of anyone — regardless of economic standing or geography. A risk-first system that trades only where the evidence says it has an edge: every lane pays its own fees and AI spend, the books are rebuilt nightly from the exchange, and it reports only the numbers it measures, not invents.
The Problem
Algorithmic advantage has always lived on institutional balance sheets. Manual trading loses to speed. Static bots lose to regime change. Neither learns. T BOT is different.
Institutions execute in microseconds; retail reacts in minutes. The edge gap is structural, not skill-based.
Most retail bots run fixed parameters. Markets shift, win rates erode, operators panic-adjust on feeling, not data.
Managed funds charge management fees regardless of performance. You pay whether you win or lose.
Why we're building this
The "outgunned" gap is widest where it's least talked about — across borders. A trader in Nairobi has the same instincts as one in New York, but not the same access to capital, tools, or markets. T BOT exists to close that gap: institutional-grade, self-calibrating automation in an app simple enough that economic standing and geography stop deciding who gets to grow their money.
Runs from anywhere, on the user's own broker — no privileged address, no local desk, no gatekeeper.
The same disciplined engine works whether you start with $100 or $100k — no minimums that quietly exclude.
A profit-only fee means we earn only when our subscribers do — built for the underserved, not off them.
Founded by a Kenyan builder — so the kid in Nairobi with a phone has the same shot as the fund in Manhattan.
The Solution
Every surface is isolated — its own capital, env file, state machine and kill switch — and every lane pays its own exchange fees and AI spend. When the bill exceeds the return, the lane is retired and stays on the dashboard with its record. A Claude prediction lane was retired the same way on 2026-09-24.
Short-dated event contracts: one rules-based live strategy, replayed on settled markets before it went live, behind a 14-layer guard chain. The books are rebuilt nightly from the exchange's own records and must close to its cash within $5.
Of 398 logged FX trades only 41 were real fills, at a profit factor of 0.97. Carry was real but not worth running; momentum was negative in every variant. Killing a surface on evidence is part of the product.
Fed funds, CPI, GDP. Rebuilt from the exchange's own records: 26 real-money markets, 4 won. The model was never validated. Retired 2026-09-24.
Re-tested on 20 years of daily prices: the long-only 200-day trend rule trails buy-and-hold by 2.5 to 4.3 points a year on SPY, QQQ, IWM, DIA and XLK. Retired 2026-09-24 without risking capital.
Re-tested on 5 years: after a 0.80% round trip, the trend-filtered dip-buy has no coin with a confidence interval above zero; 6 of 9 are negative. Retired 2026-09-24 without risking capital.
Designed to sweep 25% of trading profit into a buy-and-hold 70% index / 30% quality portfolio. Never funded: it waits on a trading surface that earns more than it costs.
How it works
Every surface runs the same five-stage pipeline with no manual intervention. Each stage has an escape hatch, and every order passes the 14-layer guard chain.
Identify opportunities by volume, anomaly, and momentum composite
Observations, forecasts and the order book, read per market
Edge + confidence + Kelly sizing through upstream guards
Signed order placement, file-lock dedup, fail-closed safety, real fill
Settlement, P&L, Brier calibration; books rebuilt from the exchange
# Calibration engine # a live knob moves only after a replay # against settled markets ST_ENTRY_THRESHOLD=… ← replayed, then capped ST_CITY_FORCE_SKIP=… ← tripwire-managed # Shape engines A–H cover every # calibration type: weight / cap / # threshold / set / boolean / # time-window / blocklist / ratio CALIBRATION_APPLY=operator-gated SAFE_RESTART_GATE=unit tests pass
Discipline
The calibration engine is built: 23 strategy dimensions, 8 shape engines, every change logged. Since the 2026-09-03 rebuild it runs with the operator in the loop: a live knob moves only after a counterfactual replay against settled markets, and a new edge starts at capped size with a dated verdict.
Transparency
Most trading products are black boxes. T BOT measures itself in public: every figure in our documents and dashboards is regenerated from live trade logs — not typed by hand, not invented.
Allocations, the revenue cone, and the realized ledger auto-inject daily from the live snapshot. The doc can't drift from reality.
Each calibration change and trade carries its reasoning to an audit ledger — queryable, reversible, never silent.
We label every number: measured (from logs) or modeled (explicit, stated assumptions). Nothing is presented as real that isn't.
Business Model
One model, one sentence: subscribers pay a commission only on the profit they actually withdraw. If the bot doesn't make money, neither do we.
We earn nothing until you're above your previous withdrawal peak. Losses carry forward.
Commission crystallizes at withdrawal, not mark-to-market. Paper gains never trigger a fee.
Early subscribers pay nothing for the first 90 days.
No subscriptions, management fees, or seat counts. Pure profit-share.
Projections
We separate what we measure from what we model, and we never blur the two. The engine's edge is measured live; the business is modeled openly, with every assumption on the table.
| Subscribers | @ 8% return | @ 15% return | @ 25% return |
|---|---|---|---|
| 10 | $360 | $675 | $1,125 |
| 50 | $1,800 | $3,375 | $5,625 |
| 250 | $9,000 | $16,875 | $28,125 |
| 1,000 | $36,000 | $67,500 | $112,500 |
MODELED · annual commission = subscribers × $10,000 avg capital × net return × 30% withdrawal × 15% fee. The only input meant to be grounded in measurement is net return — and today the measured record is negative (−$767 lifetime across every surface, rebuilt from the exchange; the live ST strategy is the lane being proven now). So the return columns are planning scenarios, not validated baselines: the model shows the structure — revenue is linear in every input, with zero owed when the bot loses. Returns are the gate, and they're earned, not assumed. Offering to subscribers is RIA/custody-regulated; live deployment carries the compliance wrapper.
Security
Two external security audits completed; every critical and high finding closed. Defense-in-depth across independent layers.
Authenticated Origin Pulls — only Cloudflare reaches the origin; direct IP hits fail the handshake.
Secrets in an isolated vault, rotated vault→CLI→env. Never appear in shell, chat, or logs.
HMAC-SHA256 signed at generation, verified at execution. File-perm 600. Injection vector closed.
Ambiguous mode flags default to DRY_RUN. The safe state is the default state.
Per-surface NAV/balance breakers with hysteresis, plus a cross-surface risk governor (halt + throttle).
GitHub Actions → droplet via SSH; pre-restart check aborts if any env file is missing.
Audit record: two external security audits completed. All critical and high findings closed; remaining items are deliberate, scheduled hardening — not structural risk.
Traction
One surface trades real money today; four others and a Claude prediction lane ran and were retired when the evidence said so. Every figure below comes from the exchange's own records, not backtests — at honest, early-stage scale.
Roadmap
The system is built and live. The path to scale is funded data, a proven live return, and multi-subscriber infrastructure — not new code.
Isolated surfaces, auto-deploy, PM2 cluster, Cloudflare security stack, Bitwarden vault, native mobile app, circuit breakers.
Autonomous nightly calibration, cross-surface risk governor, self-maintaining docs, audit ledger, two security audits closed.
Prove the live ST strategy net-positive after fees on the live book, with weekly audited reviews. The return is the gate.
Scale the proven surface, launch the 90-day beta cohort under the 15% HWM model, ship per-subscriber state isolation.
Full subscriber dashboard, compliance wrapper (RIA/custody), and a signal API for third-party consumers.
Founder
"The infrastructure, the AI stack, the security model, the business model — every line is mine. I'm not building a demo. This is live money, live data, and a system that recalibrates itself every night and reports only what it can measure."
The Ask
Capital scales the surface that proves itself, funds capped live tests of new edges, premium data, and multi-subscriber infrastructure. The system is already running — we're raising to prove the live return, not to assume it.
Scale the live ST bankroll to a return-relevant size once the pool clears its verdict, and fund capped live tests of new edges.
Premium market-data feeds, lower-latency execution, redundant failover.
Multi-user dashboard, per-subscriber capital isolation, the compliance wrapper, and the HWM commission engine.