Your AI is confidently wrong about markets.
Slatemark grounds your AI in primary sources, then closes the loop by learning how you trade: every quote and filing arrives with a source and a timestamp, and your journal and the rules you sized each trade against stay with you, so a later session knows your patterns. Discipline, not edge: trade less, size better, know your own stats. Built first for swing traders; macro, options, and long-term work run on the same footing.
- Read-only by design. Every tool pulls data; none write to your broker.
- Not investment advice. Slatemark is not a registered investment adviser; the methodology and rule parameters described below are user-configurable starting points, not recommendations tailored to your circumstances.
Strategy Scorecard
A read of your own closed trades, scored by the tags you give them. Each row is a setup; Slatemark reports its win rate with a Wilson confidence band, dollar expectancy, total P&L, and how long you hold, computed from broker-reconciled fills or the realized P&L you record on a manual close.
- From your real fills, or your own hand. Link your broker and Slatemark pulls your trade history, matches it into round-trip trades, and scores each setup automatically. No broker? Close a trade in your journal, record the realized P&L you made, and it scores too.
- Journal in conversation, score automatically. Write the idea to your journal through your AI client; once the matching fills land, Slatemark links the trade you described to the trade you made and scores it for you.
- Filter by date range and account. Slice a single account or a single quarter without losing the rest of your record.
- Honest about small samples. A setup with only a handful of trades withholds its numbers until the sample is big enough to mean something, and every win rate carries its confidence band.
- Free on every plan. Your scorecard is computed on your own trades, free. Pro adds the broker link that reconciles your fills and fills the card automatically, so it populates without you logging a trade by hand.
The Strategy Scorecard describes your own past trades. It is not a recommendation, a signal, or a performance claim, and past performance doesn't guarantee future results.
Grounded in primary sources
Every quote, filing, and macro print comes back with the source it came from and the moment it was read, so your AI quotes the number on the table instead of recalling one from training data.
Cited, not recalled
Ask for a price, an indicator, an insider sale, or a CPI print and the answer carries the primary source behind it, like a live quote at $1,043.20broker · 0.3s or Relative Strength Index — a momentum oscillator (0–100) that flags overbought (>70) and oversold (<30) conditions.(14) at 71.8broker bars. Each response records when it was fetched and links the filing, release, or feed it came from, so a stale figure is obvious and every claim is one step from its origin. The same discipline runs across market data, SEC filings, and macro releases alike: your AI quotes what Slatemark just read, not what it half-remembers.
It learns how you trade
This is where the loop closes. Framework rules shape the trade going in; your own record grades it coming out. Your theses and the rules you sized them against stay in one place, so a later session can show you what's actually working in how you trade, and what isn't. The point is process, not a signal: trade less, size better, know your own stats.
Journal & pattern audit Free
Plan a trade with thesis, levels, rule references, and catalysts; close it with structured exit prices. Then audit yourself: see where your own win-rate and R-multiple skew across position class, lifecycle, day-of-week of entry, catalyst presence, and stop discipline. Account-profile framing keeps multi-account users in the right risk-capacity bucket.
Framework rules Free
Decision discipline lives in versioned, editable rules: concentration caps, position lifecycles, hedge management, sizing from risk, tax discipline. Tune any rule to how you trade with per-user overrides; every journal entry pins the exact rule versions it was sized against, and a later session flags the drift when a rule changes after the fact, so you never act on a stale framework without seeing it.
Everything, from one place
The grounding holds because the coverage is wide: market and options, SEC filings, FRED macro, the FOMC calendar, Treasury, energy, CFTC and FINRA positioning, news, and earnings, all on the same cited footing. Whatever the question touches, there's a primary source for it.
Live quotes, OHLCV & option chains Pro
Real-time quotes, intraday bars (extended hours included), and full option chains with greeks and Implied Volatility — the option market's forward-looking estimate of how much a stock will move, derived from option prices. Higher IV = more expensive options. via your linked broker. Without a broker linked, the same tools fall back to 15-minute delayed market data automatically, free. Greek-less on Free, but enough to keep an AI conversation moving while you decide whether to link.
Quant analytics & TA-Lib indicators Free
Sharpe / Sortino / Calmar, beta vs. any benchmark, realized vol regimes, anchored Volume-Weighted Average Price — the average price an instrument has traded at over a session, weighted by volume. A common intraday benchmark., Donchian channels, Average True Range — a volatility measure that captures the typical daily price swing of an instrument over a lookback window. Often used to size stops. stops, pair spreads with half-life, support / resistance, mean-reversion score. Composable over any candle series, plus the full TA-Lib indicator set.
SEC filings, insider trades & 13F Free
Primary-source EDGAR: 10-K / 10-Q / 8-K (and 20-F / 6-K for foreign issuers), Form 4 insider transactions, 13F institutional holdings, and structured company financials. Cited with the actual filing URL, not a summary.
Macro releases & FOMC calendar Free
FRED economic releases (CPI, PPI, NFP, PCE, GDP, JOLTS) with upcoming-print dates, the scraped FOMC meeting calendar with SEP flags and press-conference URLs, and Treasury auction results with bid-to-cover and primary-dealer takedown. Know what's pricing in before you trade through it.
News, earnings & positioning Pro
Massive News with per-ticker sentiment and the Finnhub earnings calendar with analyst rating distribution come with Pro. The public-data positioning around them stays free: CFTC Commitments-of-Traders across commodities and financial futures, FINRA short interest plus Reg SHO daily short volume, and EIA weekly petroleum / gas / power data.
How it's built
Read-only against your broker, isolated per user, and open to the AI client you already use.
Read-only by policy
Slatemark never sends an order, sets an alert, or writes to your broker. Every tool pulls data; your fills and positions stay where they live. No write surface means no blast radius. The journal is the only write path, and the target is your own data.
Per-user broker link, encrypted at rest Pro
Broker tokens are minted per account, encrypted at rest with a key unique to this environment, and isolated to your own account. No shared key, no cross-tenant leakage, no token in a config file on someone else's laptop. More brokers on the roadmap.
Bring your own AI client Free
One MCP endpoint, 7 clients out of the box: Claude Desktop, Claude.ai, Claude Code, Codex, Gemini CLI, Cursor, OpenCode. ChatGPT and Gemini coming soon. Mint per-client credentials from the dashboard once; revoke any of them in one click without touching the others.
Six moves to start with
Slatemark is easiest to try as a named workflow, not a blank chat. These are the repeatable moves the Claude plugin packages as slash commands, and the same prompts work in any connected AI client.
Pre-trade brief
Before you enter. Trend, levels, ATR, catalysts, options IV, macro backdrop, and where the thesis breaks before capital moves.
Position review
For a position you hold. Re-underwrite the thesis at today's price against your journal, current market data, and framework rules.
Earnings setup
Before a print. Frame earnings as a volatility event first: implied move, straddle, IV percentile, and reaction history.
Regime check
Before single-name conviction. Read the curve, dollar, credit, financial conditions, and vol so the single-name view starts with the tape around it.
Catalyst map
For event-dense names. Put earnings, guidance, macro releases, and market-implied moves on one timeline before sizing the trade.
Post-mortem
After a close. Separate what happened from why, then journal the lesson and tag the setup so it lands in later review.