The AI Finance Intelligence Platform

One honest AI brain for every financial decision.
It starts by proving trading agents actually work.

Anyone can build a trading bot. Almost no one tells you the truth about it. Tessen is the platform where you build a trading agent conversationally, then it gets honestly graded — out-of-sample, net of every fee, tested against real fills, checked for robustness. Not a backtest you can talk yourself into believing. A verdict — and the first proof point for the intelligence layer behind it.

The Bigger Picture

One honest-grading engine. Every financial decision, eventually.

Tessen starts with trading agents because proving an edge is the fastest, hardest test of honesty we could pick. The same build-then-honestly-grade engine is designed to extend to personal finance, business accounting, and institutional tools — but no division launches on hype. Each one waits for its own proof, same as this one did.

Investinglive today

Trading agents, market intelligence, and research — this is Tessen right now.

Personal Financethe vision

An AI CFO for your own money — goals, planning, and spend intelligence, not generic budgeting.

Business & Accountingthe vision

Books, treasury, and tax intelligence for crypto-native teams, built on the same honest-grading spine.

Enterprise & Datathe vision

Institutional research, risk, and compliance tools, plus the developer APIs behind all of it.

D

We graded our own strategy first. It got a D.

Before building Tessen, we ran our own live trading strategy through the same engine that will grade yours. Thin edge, survivable drawdown, passed every gate — an honest D, not an inflated A. If we're not willing to grade our own agent truthfully, why would you trust the grade on anyone else's? See the live verified report →

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.

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, 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
The Platform

The Studio and Dashboard are live in closed beta.

Build conversationally, get graded, paper-trade, connect your own exchange with a trade-only key, and watch it live — shipped and running for invited testers now. The marketplace stays gated until there's a trustworthy Grade to sort by: no exceptions, that's the point.

Live Trading DashboardLive in beta
BTC/USDT · 15m · chart placeholder (TradingView widget in the real build)
Grade-drift alert:live expectancy is -1.8bp vs the +3.1bp backtest promised — investigate before it compounds.
Live P&L (30d)
+$1,240
Exposure
1.4× equity
Margin used
18%
Max DD (live)
11%
Agent MarketplacePhase 3
B
RSI Reversion — Majors
142 days live · 38 buyers · avg realized +$412
C
Funding Carry — Perp Basis
89 days live · 21 buyers · avg realized +$118
F
Breakout ADX Trend
delisted — fails cost hurdle · flagged: live diverged from backtest

Sorted by Grade and live track record — never raw ROI. Every buyer sees other buyers' real realized P&L, not the seller's backtest.

Analytics HubPhase 3–4
Combined P&L by exchange
BloFin
+2140
Binance
+860
Hyperliquid
-310
Fee + funding drag (30d): -$186
One Platform, Three Engines

Everything the Grade unlocks.

🧠Tessen Aurix
live in beta

Trader memory & improvement. Post-mortems that explain every grade in plain language, a journal on every agent, and drift detection that tells you when live results stop keeping the backtest's promise.

🌐Tessen Lumen
live in beta

Market intelligence across 10 venues — positioning, funding, open interest, crowd divergence — with extremes flagged and every signal labeled by whether it survived robustness testing. No black boxes.

💰Tessen NEXA
proof-gated

The agent economy. Verified track-record passports, a marketplace where only gate-passing agents can list, and non-custodial copy trading. Deliberately locked until live winners exist — that's the point.

Closed beta is running. Get the next invite.

A small invited group is testing the Studio right now. Join the waitlist and invites go out in batches — no spam, no hype, just a code when a seat opens.