PolymarketDash vs
SimpleFunctions.

POST /api/thesis/create accepts any natural-language sentence — e.g. 'Israel and Hamas reach a ceasefire before Q3' — and decomposes it into a causal tree of testable sub-claims. Each node gets a probability estimate. The system then scans Kalshi and Polymarket for contracts covering those sub-claims and scores each for tradeable edge. An evaluation heartbeat (news scan, price refresh, milestone check, LLM eval, confidence update) runs automatically. Inject new signals at any time via /api/thesis/{id}/signal.

Both. SF normalises and indexes 48K+ active contracts across Kalshi and Polymarket under a unified API. Cross-venue matched pairs are available at /api/public/cross-venue/pairs. All indicators — implied yield, cliff risk, liquidity score — are computed across both venues. PolymarketDash covers Polymarket only, per its publicly described scope.

Portfolio Autopilot is SF's autonomous trading agent. It uses a 1M-context LLM, draws on 13 data sources, and runs a 7-gate risk cascade before placing any position: kill switch, position limits, drawdown gate, regime check, and additional safeguards. It is not a rule-based bot — it reasons over the full world model each cycle. Autopilot is distinct from the thesis system; theses feed edge signals to it, but it can also operate independently of any open thesis.

Yes. SF ships a 56-tool MCP server. Add it with one command: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. From that point your AI assistant can call world snapshots, scan markets, retrieve calibration data, query cross-venue pairs, and interact with the thesis system — all without leaving your editor or chat session. The server is compatible with Claude Code, Cursor, and any client that speaks the Model Context Protocol.

GET /api/calibration returns SF's live Brier scores, broken down by venue (Kalshi and Polymarket), category, and price bucket, over a rolling 90-day window. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h prices. These numbers update automatically and you can re-verify them with a curl command. SF audits its own prediction accuracy publicly; most competitors describe accuracy in marketing copy without a verifiable endpoint.

PolymarketDash is built around trader-level analytics and smart-money tracking on Polymarket. Its stated focus is wallet attribution and position monitoring — identifying which accounts are moving markets and tracking informed flow in real time. SF models market signals at the contract and portfolio level but does not provide wallet-level trader attribution or per-account position history. If your research depends on following specific traders inside Polymarket, PolymarketDash is the more focused tool.

SF pre-computes six indicators across 48K+ active contracts: IY (implied yield on binary contracts), CRI (cliff risk index, measuring late-contract non-linearity), LAS (liquidity availability score), EE (event overround, summing all legs), τ-days (time to settlement), and a regime label classifying each contract's adverse-selection profile. All are available at /screen for browsing or queryable via the API and MCP tools — pre-computed, no need to derive them from raw price and volume feeds.