Product

Build a trading agent conversationally.
Get told the truth about it.

Anyone can build a trading bot. Almost no one tells you the truth about whether it actually works. Tessen's engine grades every agent out-of-sample, net of every fee, tested for robustness — a real verdict, not a backtest you can talk yourself into believing.

The Grade

Five hard gates. Fail one, and it's an F — full stop.

An agent doesn't go live or get listed for sale unless it clears all five. No exceptions, not even for us — we graded our own strategy first and it got a D.

1

OOS Net Expectancy > 0

Chronological 60/40 split, after fees, funding, and slippage — not a curve-fit vanity backtest.

2

Clears the Cost Hurdle

Gross edge ≥ 1.5× round-trip cost. No strategies that only "work" by scalping inside the spread.

3

Robust, Not Lucky

Positive across ≥60% of assets, majority of regimes, majority of yearly windows — not one lucky run.

4

Survivable Drawdown

Max drawdown ≤ 35% at responsibly-sized position risk — Monte-Carlo tested, not eyeballed.

5

Not Overfit

Test-set expectancy ≥ 50% of train-set expectancy. If it falls apart out of sample, it fails.

Letter Scale
A85+
B70–84
C55–69
D40–54
F<40 / fails gate
How It Works

Idea to honest grade in minutes, not weeks.

01

Describe your idea

Plain English: "buy BTC when RSI drops below 28 on the 15-minute chart, take profit at 3%, stop at 1.5%." No code required.

02

It compiles to AgentSpec

One structured contract every builder — conversational, visual, or code — compiles to. The same spec runs in backtest, paper, and live.

03

The engine grades it

Out-of-sample, net-of-fees, fill-realistic, robustness-tested. A real letter grade — computed by the engine, never self-reported.

04

You see the truth, then decide

Edit a rule, watch the Grade update live. Ship to paper trading, connect your own exchange, or walk away knowing before risking real capital.

See It Work

Describe it on the left. The truth shows up on the right.

This is the Studio — a mock walkthrough, not live data. Every real agent goes through this exact screen before it ever touches a chart.

Agent Studio
buy BTC when RSI drops below 28 on the 15-minute chart, take profit at 3%, stop at 1.5%
Got it. I filled in a few defaults you didn't specify — 3× leverage cap, 5% max daily loss, BTC/USDT perp. Here's the spec. Want me to run it through the Grade?
sleeve: rsi_reversion
entry.long: rsi(14) < 28
exit: take_profit_pct: 3.0, stop_loss_pct: 1.5
risk: leverage_cap: 3, max_daily_loss_pct: 5
run it
Grade Reportrsi_reversion · BTC
C
62 / 100 — passes all 5 gates
Win rate 54% (context, not edge)
OOS Net Expectancy > 0+3.1bp per trade
Clears the Cost Hurdle1.8× round-trip cost
Robust, Not Luckypositive on 4/5 assets
Survivable Drawdown24% sized max DD
Not Overfittest = 58% of train exp.
Edge
Robustness
Risk
Execution
Live-readiness
Per-asset OOS expectancy
BTC
+3.4bp
ETH
+1.2bp
XRP
+2.1bp
DOGE
+0.6bp
SOL
-1.8bp
Deploy

Paper first. Then your own exchange, your own keys.

Non-custodial by design: agents trade on your connected exchange with a trade-only key. Keys with withdrawal permission are rejected outright — Tessen can never move your funds, and neither can anyone who compromises us. Three modes: dry-run (simulated), confirm (approve every trade in Telegram), or fully automatic live.

Live Trading DashboardLive in beta
BTC/USDT · 15m · chart placeholder
Grade-drift alert:live expectancy diverges from the backtest promise — investigate before it compounds.
Live P&L (30d)
+$1,240
Exposure
1.4× equity
Margin used
18%
Max DD (live)
11%

6 exchanges connected today: Binance, Bybit, OKX, Bitget, Coinbase, Hyperliquid.

Grade a strategy right now — free, no signup.