Every decision recorded. Every alternative replayable. Every record verifiable against Bitcoin. Every release watched for drift.
For automated traders who need to know — and prove — what their strategy did, what would have happened under different rules, and how live releases performed.
Titan is one instrument. It performs four operations on every automated trading decision your strategy makes.
Every signal evaluation is timestamped, hashed, and stored with full input and output state. 26 gates produce verdicts you can inspect line by line. Pre-trade enforcement is optional; recording is not.
Change a setting and replay it against the signals that actually crossed your pipeline. Cohort replay and single-decision counterfactuals share one evidence chain.
Daily aggregate roots are anchored to Bitcoin. Any party can verify a recorded decision against Bitcoin Core or any public block explorer, without trusting Titan.
Once a candidate goes live, Release Watch tracks whether the conditions Deploy Gate flagged actually materialize. Drift detection alerts when live behavior diverges from the release baseline.
Titan is not a trading bot. It doesn't generate signals, hold funds, or store broker credentials.
Each decision records gate verdicts, evidence, timing, config hash, evaluation hash, and decision signature. The same record carries the state source Titan observed, the broker intent it would have issued, and the anchor status of the audit chain leaf — so the decision can be audited later, replayed under different rules, or verified against Bitcoin.
Deploy Gate replays a candidate config against the signals that actually crossed your pipeline. CI/CD for trading rules — change a setting, replay your real signals, see what would change before going live.
Standard replay evaluates signals independently. Cascade replay is sequential: each forwarded signal changes portfolio state, and the next signal evaluates against that new state. Both replay real signals with real broker state — not backtesting, not synthetic data. You see what the candidate policy would have decided on every signal that actually crossed the pipeline, with the actual state evidence Titan recorded at the time.
Counterfactual replay applies the same machinery to a single past decision. Re-evaluate one historical trade under hypothetical config overrides, without writing anything. The evidence chain that runs against a cohort runs against a single decision.
Titan publishes Bitcoin-anchored commitments to canonical audit state at known times. Downstream users can verify recorded decisions trustlessly with Bitcoin Core, or with weaker trust assumptions via any public Bitcoin block explorer.
Every decision row produces a leaf hash, written in the same database transaction as the decision itself. Leaves aggregate daily into per-account roots. Account roots aggregate into a single daily aggregate root. The aggregate root is committed to Bitcoin via OpenTimestamps and lands in a Bitcoin block within hours.
Once anchored, no party — including Titan — can modify a recorded decision without breaking a Bitcoin block's hash. The chain proves what was recorded, not whether the input was sound. Input integrity is handled separately by Titan's state provenance and deterministic re-evaluation layers; Bitcoin handles post-hoc immutability.
| Rung | What you trust | Setup |
|---|---|---|
| 1 | OpenTimestamps calendars | None — verify against the proof file directly |
| 2 | A public Bitcoin block explorer (mempool.space, blockstream.info) | None — open a URL |
| 3 | Local Bitcoin Core node | ~10 GB pruned, one-time sync |
The audit chain itself is identical at every rung. The verifier decides how skeptical to be about which third parties stay in the loop.
Every trace in the operator console shows its anchor status and links to a downloadable .ots proof. Verifying a single decision against Bitcoin is a one-command walkthrough — the same command an external auditor would run.
A candidate's job isn't done when it goes live. Release Watch monitors every release against the conditions Deploy Gate flagged at promotion, and raises an alert when live behavior matches the predicted concern.
When a candidate is released, Release Watch attaches to the release record. It evaluates the live decision stream against the warnings the Deploy Gate run produced — for example, "predicted 3 additional Position Limit blocks per week." If live behavior matches the prediction, Release Watch raises an alert with the matched evidence linked back to the original Deploy Gate run.
Every Release Watch evaluation is recorded. The release timeline becomes an auditable record of what was predicted versus what actually happened.
Live behavior is compared against the release baseline continuously. Push alerts fire when verdict rates, latency profiles, or block reasons shift outside expected ranges. A flagged drift can route back into the candidate lifecycle — a Deploy Gate re-evaluation or a config rollback.
Trace → Candidate → Deploy Gate → Release → Release Watch.
Every link is recorded, every transition is verifiable, and the chain holds whether you're auditing yesterday's trade or last quarter's release.
Works with TradingView, Python bots, any REST client. Broker support starts with Alpaca.
Upload your Alpaca trade history. No account needed.
Your data is analyzed in real time and never stored.