Now in beta — Kalshi & Alpaca live, paper-first

AI-powered trading.
Desk-grade discipline.

An AI agent researches, sizes, and drafts every trade on your own Kalshi and Alpaca accounts. You approve each order, and the risk limits you set are enforced at the moment of placement.

Paper-firstYou approve every orderRisk limits enforced at placementNot a black box

Free while in beta. No credit card required.

Two styles front the desk

The beta ships the two methods we can stand behind end-to-end. The other four shipped styles return as each earns its keep.

Launch style

Event-Driven

Trade around known catalysts — Fed decisions, CPI prints, hearings — researched before they're priced in. Kalshi-first, where your view on an event trades directly.

Launch style

Relative Value

The quant flagship: market- and sector-neutral long/short baskets on Alpaca, and consistency scans across related Kalshi markets. Paid for being right on relationships, not market direction.

RoadmapTail RiskMomentumMean ReversionMacro Thematic

Runs today for existing sleeves; new sleeves return after the beta.

Not a chatbot. A trading desk.

Professional desks separate research, execution, and risk oversight. Now you get that structure too — free while in beta.

Research

Triangulated web + X/Twitter scanning surfaces catalysts before they're priced in. Never trade on a single source.

Discipline

Kelly-criterion sizing, a mandatory thesis, and a written exit plan on every trade. No FOMO, no YOLO.

Risk officer

Set exposure and daily-loss limits once, plus a same-instrument concentration warning — checked against your whole book at placement. The global kill switch halts app-driven opens and closes; resting-order cancellation and venue reads continue, and urgent exits happen directly at the venue.

Memory

Every order, thesis, and result persists across sessions — an auditable track record the agent carries into every conversation.

The quant engine

Institutional portfolio construction, retail account.

Most "AI trading" tools just pick tickers. Quantreno's finance engine builds market- and sector-neutral baskets, measures beta and R² against the market, and tilts toward a momentum + reversal signal — the construction a hedge-fund desk runs, automated on your account.

  • Target near-zero market and sector exposure, so you're paid mainly for being right on the names — not market direction.
  • A per-name signal tilts the basket toward what it expects to outperform, keeping it neutral.
  • Beta, R², and net exposure on every proposal — you see the risk before you approve.
proposed basket
you> Build a market-neutral AI-chip spread, $10k
Chip-vs-chip spreadnet β-$ ≈ 0
LONGMUsig +1.5$3,000
LONGAMDsig +0.6$2,000
SHORTNVDAsig −0.9$3,000
SHORTTSMsig −0.6$2,000
Gross $10,000 · long $5,000 / short $5,000 · net $0. Both sides are semis and the solver targets matched market & sector exposure — so the bet is mainly MU/AMD vs NVDA/TSM on a +1.9σ signal spread, hedged name-vs-name rather than with an inverse ETF. Approve to trade.

From idea to executed trade, in one chat

The full workflow — discovery, research, sizing, execution, and monitoring — in a single conversation.

01

Connect your venues

Link Kalshi and Alpaca — paper or live — in seconds. Credentials are encrypted at rest and never stored in plaintext.

02

Tell the agent an idea

Say "hedge my tech exposure" or "bet on a March rate cut with $200." The agent shapes it into one of the desk's two launch styles, researches, and sizes the trade.

03

Review and execute

Every proposal shows the edge, sizing, net beta, and risk. You confirm — the app executes exactly what you reviewed. Nothing trades without your approval.

Built so you stay in control

It's your money and your own venue accounts. The architecture treats that as the constraint that matters most.

The AI can't touch your orders

On every venue the agent proposes and reads — only the app can place, only the exact trade you approved on the review sheet, and only after it clears your risk limits and a global kill switch.

Every leg checked before anything places

A hedged basket is validated leg by leg at review — if any leg can't place, nothing is sent. Cross-symbol orders aren't atomic once submission starts, so if a leg is rejected mid-basket, placement stops and everything already filled is journaled and shown — never hidden.

Everything on the record

Every venue instruction is journaled verbatim — request and response — and closes are verified against actual fills, not order acceptance.

Powered by

KalshiAlpacaVercel AI SDKClaude · GPT · GeminiTavily SearchX API

Free while in beta

Quantreno is in early access. Everything described on this page is live and included — no billing yet, no card required.

Early access

Beta access

$0while in beta

The full desk, on your own connected venue accounts. You approve every order before anything is placed.

Join the beta
  • Full AI trading agent — research, sizing, execution proposals
  • Kalshi trading + Alpaca long/short equity baskets (paper or live), approval-gated
  • Market- & sector-neutral construction with a momentum + reversal signal
  • Per-sleeve P&L, exposure, and performance tracking
  • Live positions and P&L across Kalshi and Alpaca on one desk
  • Enforced exposure + daily-loss limits, a same-instrument warning, and a global placement halt

Fair-use limit of 50 chat messages per rolling 24 hours per registered account during beta. Paid plans come later — beta users will be notified before anything changes.

Stop trading on gut feel.
Start trading with a desk.

Your AI quant is ready. Connect a venue and run your first sleeve in minutes.