Skip to main content
Docs/Get started/Overview

SigmaVue overview

The operator's manual. SigmaVue is twelve specialist AI agents managing your prop firm accounts under your rules — while you're at your day job, your kids' game, or asleep. This page is the single source of truth for how the agent floor works, end to end, in plain English.

v3.0.4Updated 2 hours agoMaintained by Claude Code & DallionAll systems operational
Quick installOne command. Configures the MCP server, drops the Claude Code skill into ~/.claude/skills/, and prompts for your token.
Shell
curl -fsSL https://install.sigmavue.io | sh
Claude Code -- Codex -- CursorPer-account scopedMac -- Linux -- WSLManual install
Claude Code skill
Canned prompts, morning briefings, journal workflows
Download skill

#How it works

You connect your prop firm accounts (Apex, TopStep, TPT, Leeloo — 18+ firms supported), set your daily base hit and risk profile, and the agents take over. Sigma orchestrates, Carter scans, Annalisa reads news, Bill sizes for the base hit, Wags vetoes anything that breaks compliance, Wendy & Devin execute.

No charts to watch. No webhooks to wire up. No VPS to pay for. Everything runs on the SigmaVue platform — you watch the floor, or close the tab.

First-time operators start here
If this is your first time, jump to the 5-minute setup below. You can be live on a paper account before you finish your coffee.

#5-minute setup

Three clicks, three minutes each. We OAuth into your prop firm — we never see your password — and route automatically to Tradovate, ProjectX, or TradeLocker based on your firm and account state.

1
Connect your prop firm account
Click Connect account in the dashboard, pick your firm, and OAuth in. We auto-detect demo vs. live and route accordingly. Apex / TopStep / TPT / Leeloo / MyFundedFutures / Bulenox / TradeDay all supported in one click.
2
Set your daily base hit
Pick a number you'd be happy to hit each day. SigmaVue splits it 40/35/25 across three Russian Doll layers — most cashes early, the rest runs to full TP. Wags pauses the day when the inner layer locks.
3
Pick your risk profile & go live
Conservative -- Balanced -- Aggressive. Wags enforces it on every trade, every account, every firm — always. Override any time. Circuit breakers always on.

#Example: a single trade lifecycle

Here's the audit trail of one ES.M26 long signal — start to fill — that ran on April 22, 2026 at 10:42:18 ET. End-to-end took 3 seconds.

JSON -- audit log entry
{
  "trade_id": "ES_M26_1745324538",
  "symbol": "ES.M26",
  "entered_at": "2026-04-22T14:42:21Z",
  "chain": [
    { "t": "10:42:18", "agent": "Carter",
      "action": "signal_long",
      "reasoning": "VWAP stretch 1.7s + Maff trend day 0.71 + Bill headroom OK" },
    { "t": "10:42:19", "agent": "Bill",
      "action": "sized", "qty": 2,
      "reasoning": "Inner base hit at +6 ticks, 2 ct = $25/tick" },
    { "t": "10:42:20", "agent": "Wags",
      "action": "compliance_pass",
      "reasoning": "Apex rules clear, within session, EIA in 90min noted" },
    { "t": "10:42:21", "agent": "Wendy",
      "action": "order_filled",
      "limit": 5871.75, "tp": 5876.25, "sl": 5869.75,
      "layers": "russian_doll" }
  ],
  "layers": {
    "inner":  { "qty": 0.40, "target": "base_hit" },
    "middle": { "qty": 0.35, "target": "tp_70pct" },
    "outer":  { "qty": 0.25, "target": "runner" }
  }
}

Every field above is exposed in the audit log export and on the Sigma Decisions screen inside the app. chain is immutable and timestamped at agent decision-time, not server-receive-time, so post-trade analysis stays honest.

#The Russian Doll exit

Most retail trades give up >60% of MFE on the round trip. The Russian Doll splits each position into three layers so the inner layer locks fast, and the outer layer runs only when the trend confirms.

LayerSizeTargetHit rate (2y backtest)
Inner40%Base hit (~6 ticks ES)81%
Middle35%70% of TP49%
Outer25%Runner / structural target28%
Aggressive profile only on funded accounts
Wags will refuse to apply the Aggressive profile on a Combine / Eval account regardless of your settings. The trailing-DD math on most prop firms makes Aggressive sizing a first-week-blowup risk on those phases. Pass the Eval first, then opt in.

#The 13 agents

Thirteen specialists, one orchestra. Each agent owns a single decision surface — they argue, defer, and pass the trade through a hand-off chain that's logged in real time. Below: who they are, what they own, and what triggers them. No prompts, no internal scoring math — that's the moat. But every operator should know the names on the floor.

Σ
Sigma
Head agent -- orchestrator

Routes every signal through the council, weighs disagreement, and decides which agent has the floor on a given trade. Sigma never trades alone -- but no trade leaves the building without Sigma’s stamp.

Always-onCouncil referee
C
Carter Hayes
Strategy tactician

Generates the long/short signals. Reads structure, momentum, and stretch. Argues hardest in the council when conviction is high -- and stays quiet when it isn’t. Most floor time of any agent.

Signal-originTape-sensitive
A
Annalisa
News & sentiment

Reads the wire -- econ data, FOMC, earnings, geopolitics, and prop-firm-relevant macro events. Vetoes Carter when an EIA print is 3 minutes out. Keeps the journal grounded in real-world context.

Pre-event awarenessMacro filter
B
Ben Kim
Signal quality filter

The skeptic. Every Carter signal passes through Ben for quality scoring before it’s sized. If the regime, conviction, or context doesn’t pass Ben’s bar, the signal dies quietly -- no broker call.

Quality gateFilter-only
L
Lion
HITL approver -- the human bridge

When you want Sigma to ask first, Lion is the one who asks. Configurable: full auto, ask-on-large, ask-on-novel, or ask-on-everything. Pushes to your phone, waits as long as your config allows, then defers to Wags’ standing rules.

OptionalMobile push
$
Dollar Bill
Risk manager -- sizing

Translates a signal into how many contracts. Sized for the inner Russian Doll layer at base hit, never above account headroom, never above the daily loss limit, never above your active risk profile.

Per-trade sizingHeadroom check
W
Wags
Compliance officer

The veto. Knows every prop firm’s rules -- daily loss, drawdown trail, news lockouts, position scaling, weekend exposure, EOD flatten -- and refuses any trade that breaks them. Wags is the most-blocked, most-loved agent on the floor.

Always-veto-ablePer-firm rules
W
Wendy
Synthesis -- council scribe

Compresses the council’s debate into a single decision packet. Ties Carter’s signal, Ben’s filter, Annalisa’s macro, Bill’s size, and Wags’ compliance into one row in the audit log -- with the reasoning of each.

Audit-row authorReasoning trail
D
Devin Matrix
Execution router

Picks the broker. Splits the order across funded accounts when you have multiple. Handles Tradovate / ProjectX / TradeLocker routing automatically based on firm and account state. Retries on transient failures, never on rejected.

Multi-accountBroker-aware
A
Axe
Portfolio & PnL tracker

Watches every open position across every funded account in real time. Computes layer-by-layer realized vs. unrealized, fund-level base-hit progress, and triggers Wags’ “pause the day” when the inner layer locks across all accounts.

Real-time PnLDay-pause trigger
J
Jack Mercer
Order-flow reader

Reads the tape -- order flow and time-and-sales. Spots institutional activity, absorption, and tape-speed anomalies, then confirms or rejects what Carter and Ben hand up. The agent that knows whether the move has real money behind it.

Tape readerFlow confirmation
R
Reggie
Regime detection

Classifies the market regime -- trending, ranging, volatile, quiet -- from volatility clustering, structure, and volume profile. Every downstream agent adapts its parameters to Reggie's read before the first signal fires.

First on the floorRegime context
T
Taylor Mason
The Arena -- bull vs bear

She runs The Arena -- the bull-vs-bear debate. Taylor argues both sides of every setup, stress-tests the thesis, and surfaces the strongest case for and against before Wendy's synthesis decides. The debate transcript is the most watchable artifact on the floor.

Bull vs bearThesis stress-test
D
Donna
Support & onboarding

The friendly one. Walks new operators through setup, answers in-app questions, surfaces relevant docs in chat. If something feels broken, talk to Donna first -- she handles the triage and pulls in a human if needed.

In-app chatOnboarding guide
The full agent floor is visible inside the app
Click any agent on the Office screen to open their drawer — current activity, recent decisions, and a 7-day floor-time ledger. We expose role and behavior; we never expose the prompt, the scoring math, or the inter-agent message schema. The agents are the moat.

#Supported prop firms

18 firms supported in v3. Wags ships with a per-firm rule profile — daily loss, trailing drawdown, news lockouts, position scaling, EOD flatten, weekend exposure — and updates automatically when a firm changes its eval or live rules. If your firm isn't here, ask in the in-app community and we'll evaluate.

A
Apex Trader Funding
Eval -- Live -- 4-step
T
TopStep
Combine -- Funded
P
Take Profit Trader
Eval -- Live -- 1-step
L
Leeloo Trading
Eval -- Live
M
MyFundedFutures
Eval -- Live -- Direct
B
Bulenox
Eval -- Live
T
TradeDay
Eval -- Funded
E
Earn2Trade
Combine -- Funded
T
TradeifyNEW
Eval -- Live -- Direct
F
FundedNext Futures
Eval -- Live
P
The Trading Pit
Eval -- Live
L
Lucid Trading
Eval -- Live
T
TickTickTrader
Eval -- Live -- 1-step
G
Goat Funded Trader
Eval -- Live
C
City Traders Imperium
Futures -- Eval
E
Elite Trader Funding
Eval -- Live
A
Aqua Funded
Eval -- Live
U
UProfit Trading
Eval -- Live
Eval-vs-Live behavior
Every firm has different rules between Eval (Combine, evaluation, challenge phases) and Live (funded). Wags applies the correct ruleset automatically based on the account state your prop firm reports — you don't manage this. Aggressive risk profile is locked out on Eval phases regardless of your settings.

#MCP serverOperator+

The headline integration. Connect SigmaVue to Claude Code, Codex, Cursor, or any MCP-aware client and ask questions about your floor in plain English. The MCP server is hosted at mcp.sigmavue.io and authenticates with a per-account token — you don't run anything locally.

Three lines of config in your ~/.claude/settings.json and you're live:

JSON -- ~/.claude/settings.json
{
  "mcpServers": {
    "sigmavue": {
      "url": "https://mcp.sigmavue.io",
      "headers": { "Authorization": "Bearer $SIGMAVUE_TOKEN" }
    }
  }
}

Then in Claude Code, just talk to your floor:

Shell -- Claude Code
# Read your floor
claude "show me yesterday's vetoes and what they cost"
claude "summarize Carter's win rate this week vs last week"
claude "which prop firm rules am I closest to violating right now?"

# Trader+ tier — write actions (governed)
claude "pause trading on apex-1247 for the rest of the day"
claude "set my risk profile to conservative until further notice"

Tool catalog

ToolTierDescription
sigmavue.audit.listOperatorLast N decisions across accounts. Filter by agent, by firm, by outcome.
sigmavue.audit.getOperatorFull hand-off chain for a single trade ID.
sigmavue.positions.listOperatorOpen positions, by account, with layer-by-layer realized vs. unrealized.
sigmavue.pnl.summaryOperatorAggregated PnL by account, day, week, month.
sigmavue.config.getOperatorRisk profile, base hit, account list, agent toggles. Read-only.
sigmavue.alerts.subscribeOperatorServer-sent stream of fills, vetoes, and base-hit lock events.
sigmavue.config.set_risk_profileTrader+Switch between Conservative / Balanced / Aggressive.
sigmavue.trading.pauseTrader+Pause one or all accounts.
sigmavue.trading.resumeTrader+Resume from pause. Wags re-validates first.
What MCP cannot do
No raw order placement. No strategy editing. No agent prompt access. No orchestration internals. The MCP surface is governed verbs only — read everything, write only what's safe to express in named English. The agents stay the moat.

#Claude Code skillFree download

One-click install for Claude Code users. Adds canned prompts, common workflows (“morning briefing”, “post-market journal”, “rule-violation check”), and shorthand commands. Works on top of the MCP server above.

1
Download the skill
Grab sigmavue.skill.md and drop it into ~/.claude/skills/. Or run the one-line install in your terminal.
Shell -- one-line install
curl -fsSL https://docs.sigmavue.io/sigmavue.skill.md \
  -o ~/.claude/skills/sigmavue.skill.md
2
Set your token (one-time)
Generate a token in Settings → Integrations → Claude Code and export it: export SIGMAVUE_TOKEN="sk_...". Tokens are scoped to a single account by default.
3
Talk to your floor
Open Claude Code and ask anything: “morning briefing”, “who got vetoed today”, “prep my journal entry”. The skill translates your phrasing into MCP tool calls.
Codex, Cursor, and other MCP clients
The skill format is Claude Code-specific, but the underlying MCP server works with any MCP-aware client. Codex and Cursor users: configure the same mcp.sigmavue.io URL in their respective settings — the tool catalog is identical across clients.

#Audit log -- CSV export

Every decision is exportable to CSV directly from the dashboard — no API needed. Settings → Audit → Export. Filter by date range, agent, firm, or outcome. The CSV is immutable: timestamp at agent decision-time, full reasoning chain, layer attribution, and final fill.

For accountants and prop-firm audits
CSV exports include a SHA-256 of the chain so you can prove tamper-resistance to a prop firm or auditor. Most firms have never seen retail-level audit trails this clean. Use that.

#Daily Base Hit

The single number you set on day one — and the number every agent on the floor optimizes for. Pick a dollar amount you'd be happy to take home each day. SigmaVue splits it 40 / 35 / 25 across three Russian Doll layers: most cashes early at the inner layer, the middle layer banks at 70% of TP, the outer layer runs.

Per-account targets compound at the fund level. $150 x 4 funded accounts = $600/day fund-level base hit. Wags watches the cumulative number across accounts and pauses the day automatically once the inner layer locks across all of them — no over-trading, no give-back.

Pick the number you can stop at
The base hit is a stopping rule, not a profit target. If $150 is a great day for you, pick $150. The system's edge is consistency — over a year, locking the base hit on 80% of trading days beats swinging for a 5x target on 30% of them.

#Risk profiles

Three named profiles — Conservative -- Balanced -- Aggressive — set how much of your account headroom Bill is allowed to use per trade. No custom sliders. Profiles are intentionally coarse so the floor never accidentally drifts to a config you didn't think through.

ProfilePer-trade DDDay capBest for
Conservative1.5%3.5%Combine / Eval phases -- drawdown-strict prop firms
Balanced2.5%5.0%Funded accounts -- default for most operators
Aggressive4.0%7.0%Funded accounts only -- high-conviction operators

Wags rejects Aggressive on Eval-phase accounts regardless of your settings — the trailing-DD math on most prop firms makes Aggressive sizing a first-week-blowup risk during evaluation. Pass the Eval first, opt in second.

#Compliance veto

Wags is the agent who says no. Every signal — every signal — passes through Wags before it reaches the broker. Wags' rule engine is loaded with a per-firm profile: daily loss limit, trailing drawdown, news lockouts, position scaling, weekend exposure, EOD flatten. If any rule would be broken, Wags vetoes.

Common veto reasons (and what they mean):

  • news_lockoutHigh-impact econ data is within the firm's lockout window. Resumes automatically.
  • dd_proximityAccount is within 30% of trailing drawdown. Bill could size for it; Wags refuses.
  • weekend_exposureWeekend hold not permitted by the firm. Trade flattens at EOD Friday.
  • position_scalingFirm prohibits scaling beyond initial size. Council wanted to add; Wags blocked.
  • session_windowOutside the firm's allowed trading session for that contract.
Wags cannot be overridden from the dashboard
By design. The veto is the moat that keeps the floor compliant across 18 prop firms. If you genuinely believe Wags is wrong, escalate via the in-app community and we'll review the rule profile. The audit log records every veto with full reasoning — we don't lose those.

#Emergency halt

Top-right of the dashboard, always one click away. The big red button. Halt does three things in this order:

  • Cancels all working orders across every connected account.
  • Flattens all open positions at market — Russian Doll layered exits are skipped.
  • Pauses every agent from generating new signals until you manually resume.

Resume is manual and per-agent — when you click resume, Wags re-validates rules and Bill re-checks headroom before any new entry. The full halt + resume sequence is logged with timestamps and operator confirmation.

#Your first week

The honest playbook for the first 7 days on the floor. Don't override the agents. Don't over-trade. Don't sit and watch every tick. Three rules.

1
Day 1-2 -- paper account
Connect a demo account first. Set a low base hit ($50). Watch the floor trade for two sessions. Read the audit log. No live capital yet. The goal is to see what Carter signals, what Wags vetoes, and how the journal writes — not to make money.
2
Day 3-5 -- one funded account, Conservative
Connect one funded account, set Conservative profile, base hit at $100. Let it run. Don't override. Read the EOD journal each evening — that's where you'll see whether the floor is reading the market the same way you would.
3
Day 6-7 -- review, then scale
By day 6 you should have ~30 trades in the audit log. Look at: how often Wags vetoed, how often Carter was wrong, where the inner layer locked. If the floor traded sane, raise base hit to your real number, switch to Balanced, and connect more accounts. If something feels off, ask in the in-app community first.
First-week support
Donna (the in-app agent) handles the most-asked first-week questions. For everything else, ask in the in-app community — the operators there remember exactly what week 1 felt like.

#System status

Real-time status of every component the agents depend on. Public status is at status.sigmavue.io.

Agent floor
12 / 12 online
Operational
Databento market data
CME futures -- ES NQ YM GC
Operational
Tradovate broker route
Apex / TopStep / TPT
Operational
ProjectX broker route
Bulenox / Tradeify
Operational
TradeLocker broker route
Leeloo / Aqua Funded
Operational
MCP server
mcp.sigmavue.io
Operational
Audit log + journal write
Postgres -- replication healthy
Operational
In-app livestream
Multi-platform simulcast
Degraded

#Glossary

The vocabulary the floor uses, in plain English. If a term in the dashboard isn't here, ask in the in-app community and we'll add it.

Base hit
The dollar amount you set as your daily target. Splits 40/35/25 across the Russian Doll layers.
Russian Doll
Three-layer exit pattern: inner cashes at base hit, middle takes 70% of TP, outer runs as the runner.
Council
The set of agents involved in a single trade decision. Sigma referees, Carter signals, Ben filters, Annalisa contexts, Bill sizes, Wags vetoes, Wendy synthesizes, Devin executes.
Veto
A compliance refusal from Wags. Always logged with reasoning. Cannot be overridden from the dashboard.
Inner / Middle / Outer
The three Russian Doll layers — 40% / 35% / 25% of position size respectively.
Day-pause
Wags pauses new entries when the inner layer locks across all funded accounts. Triggered by Axe.
Fund-level base hit
Sum of per-account base hits across all funded accounts. The number Axe optimizes against.
Audit chain
The hand-off log of every agent’s decision on a trade. Immutable, timestamped, exportable to CSV.
MFE
Maximum favorable excursion — how far a trade ran in your direction before you closed it. Russian Doll exists to capture more of this.
Headroom
Distance to the next firm-imposed limit (daily loss, trailing DD, weekly cap). Bill checks headroom before sizing.
Eval / Combine / Live
Account phases. Eval is the evaluation/challenge phase; Live is the funded phase. Wags loads different rules per phase.
Convergence
When two or more agents independently reach the same conclusion at high confidence. Surfaces in the audit log as a "council convergence" tag.

#Changelog

Public release notes. Internal pre-release builds are not listed. Every release lands first on staging for 48 hours before promotion.

v3.0.4
Current release
  • MCP server (Operator+): connect SigmaVue to Claude Code, Codex, or Cursor. 9-tool catalog covering audit, positions, P&L, config, alerts.
  • Claude Code skill: free download with canned workflows (morning briefing, post-market journal, rule-violation check).
  • Tradeify added as supported prop firm. Bringing total to 18.
v3.0.3
9 days ago
  • Russian Doll inner-layer hit rate improved 78% to 81% after Bill’s sizing recalibration.
  • Wags rule-profile auto-update for Apex’s new EOD requirement (April 4 firm announcement).
  • Auto-journal now uses operator’s own voice profile when configured.
v3.0.0
3 weeks ago
  • Strategy catalog deleted. The agents pick now. Operators set base hit + risk profile.
  • Office screen redesigned as the trading floor. Agent grid + orchestrator chip strip.
  • 10 fresh PRDs replacing the previous 47. Methodology refresh.
v2.4.1
2 months ago
  • Founding 100 program launch. 23 / 98 spots remaining at $497/mo locked-for-life ($897/mo self-serve after).
  • Community feed and live stream moved into the app. No more separate trading rooms required.

#What to read next