Results
Tech Stack
BOTTOM LINE
Your automation needs a second opinion before it acts.
We build n8n workflows, AI agents, and operational automations for teams that need their systems to make judgment calls — not just execute instructions. Deployed in 2–3 weeks.
Frequently Asked Questions
Does Claude execute trades on its own?
No — Claude only analyzes and recommends. The bot generates a trade signal from market conditions, then passes the full context — current price, volatility, position size, portfolio exposure — to Claude AI for a real-time risk assessment. Claude's recommendation and confidence score go to the trader on Telegram. Execution only happens through the trader's own confirmed Telegram account — no order is ever placed without a human tap.
How fast is the risk-check loop?
Under 3 seconds — 2.8 seconds on average across the first two months of live trading. That's how long it takes Claude to fetch context, run the risk assessment, and return a recommendation, all before the Telegram alert is even fully read. The trader's own approve/reject tap adds roughly 8 seconds on top, since the human step is deliberately in the loop.
Does this work on exchanges other than Deribit?
The current deployment is built for Deribit's options and perpetuals. The same architecture adapts to Binance, Bybit, or OKX — the signal logic and Claude integration are exchange-agnostic. The order execution module is swapped per exchange API during deployment, typically a 4–6 hour change.
What happens if the trader doesn't respond in time?
The trade is skipped automatically. Every Telegram approval request has a 30-second window — no response defaults to no trade, every time. Capital preservation takes priority over trade opportunity; the system is designed to fail safe, not fail open.
How do I audit AI decisions after the fact?
A PostgreSQL dashboard logs every signal, decision, and executed trade with timestamps, Claude's reasoning text, and P&L per position. A weekly Telegram digest summarises win rate, risk-adjusted return, and flagged edge cases. The owner can query historical decisions at any time to audit the AI's reasoning.
Related Resources
Skip the trial-and-error. We've already mapped what works.
Answer 5 questions about your current workflow — we identify which processes to automate and send you a specific deployment plan within 2 hours. No call required.
Get My Workflow Analysis →