The switch stays human
Confirm gates, review loops, kill switches. Autonomy is granted, bounded — and revocable in one tap.
AI Futures is an independent product lab building instruments for the agentic age — systems that trade live markets, map living codebases and command fleets of autonomous agents, with human judgment wired into every loop.
01 — THE THESIS
Markets move in microseconds.
Agents ship code while you sleep.
Complexity compounds daily.
Whoever holds the controls, holds the future.
02 — THE INSTRUMENTS
Every system we ship obeys the same law — machine speed, human judgment, provable evidence. Choose your control surface.
INSTRUMENT 001 — LIVE MARKETS
A semi-automated trend engine for Micro Gold and Micro E-mini S&P futures. It reads regime, waits for price to reach value, then asks a human the only question that matters: confirm?
Trades only when the market agrees — trend, volatility and session filters gate every setup.
Entries at value, not at hope. Profile structure decides where the trigger is even allowed to fire.
Every order waits for your tap. Signals expire in 180 seconds; risk is re-checked at the moment you confirm.
Server-side stop and target brackets on every entry, auto-halts near the loss limit, force-flat at 16:08 ET, one kill switch.
INSTRUMENT 002 — SYSTEM CARTOGRAPHY
Point AIFlow at any repository. It reads the code and renders the machine inside — providers, models, agents, tools, pipelines — every claim pinned to file:line evidence. Scan → render. Nothing leaves your machine.
Dependency and syntax-tree analysis finds the AI layer in TypeScript, Python, Go and Rust — models, agents, tools, stores.
Every node carries file:line receipts. LLM synthesis is optional, guarded against hallucination, and can be switched off.
No upload, no external API. Share maps from your own server with secret redaction on everything that leaves the scanner.
One CLI. An interactive layered map with edge bundling — and architecture drift caught between any two scans.
INSTRUMENT 003 — AGENT OPERATIONS
A local-first control plane for durable multi-agent work. Route tasks to Codex, Claude or OpenClaw. Execute in isolated Git worktrees. Verify independently. Seal the evidence. You keep the last word.
Agents never touch your checkout. Every run gets a clean, disposable worktree with mutation guards.
An independent, no-shell verification step can veto an agent's claimed success before it ever reaches you.
Prompts, diffs, logs and screenshots become immutable SHA-256-addressed artifacts on an append-only timeline.
Outbound-only cloud federation with Ed25519-signed, workspace-bound envelopes — offers decline safely, never fail mid-run.
06 — THE ETHOS
Confirm gates, review loops, kill switches. Autonomy is granted, bounded — and revocable in one tap.
file:line receipts, SHA-256 artifacts, backtests before capital. If it can't be proved, it didn't happen.
Broker credentials, source code, daemon tokens — they live on your machine. The cloud gets dashboards, never keys.
Microsecond markets, always-on agents, zero-lag maps. We build for the speed the world actually runs at.
TRANSMISSION OPEN
Three instruments and counting — built in public, verified in private, shipped when the evidence says so.