Opinion vs
SimpleFunctions.

POST /api/thesis/create takes any natural-language sentence — for example, 'the Fed will cut rates before July' — and decomposes it into a directed causal tree of testable sub-claims. SF then scans Kalshi and Polymarket for contracts that price those sub-claims, propagates probabilities up the tree, and runs an evaluation heartbeat: news scan, price refresh, milestone check, LLM evaluation, and confidence update. You can inject external signals at any time via /api/thesis/{id}/signal. Public theses are forkable. No competitor offers a structured causal-tree system with live evaluation cycles.

Not yet. SF's cross-venue coverage today spans Kalshi and Polymarket, totalling 48K+ active contracts. Opinion's Open API is on SF's cross-venue roadmap, pending API stability verification and pair-matching coverage. If your workflow requires Opinion's on-chain venue specifically, Opinion's own API is the correct access point today. The competitor facts above reflect this honestly: SF does not ingest Opinion order flow at this time.

Portfolio Autopilot is SF's autonomous trading agent. It uses a 1M-context LLM across 13 data sources and passes every candidate trade through a 7-gate risk cascade before execution: kill switch, position limit check, drawdown gate, regime check, liquidity gate, conviction threshold, and a final LLM review. The thesis system feeds signals directly into the autopilot loop so that a thesis update can trigger a position review. This is a server-side agent, not a client-side script — it runs continuously and does not require user intervention per trade.

One line: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. After that, any Claude Code or Cursor session gains 56 tools covering market search, thesis creation, signal injection, orderbook depth, cross-venue pairs, computed indicators, trade ideas, and the world snapshot endpoint. No API key is required for read operations. Opinion has no published MCP server.

SF pre-computes six indicators across 48K+ active contracts: IY (implied yield — annualised return if the contract settles YES), CRI (cliff risk index — probability-weighted distance to a sharp price discontinuity), LAS (liquidity availability score — how much size the orderbook can absorb before slippage exceeds a threshold), EE (event overround — how much total probability across a market's outcomes exceeds 1.0), τ-days (time to settlement), and regime label (adverse-selection classification). All are available at /screen and via the MCP server. These are pre-computed — no client-side derivation required.

/api/calibration returns SF's own Brier scores broken down by venue, category, and price bucket, computed over the past 90 days using T-24h prices. Current figures: Kalshi 0.20, Polymarket 0.12. These are publicly auditable — anyone can replicate the calculation with a curl call. Opinion does not publish a comparable accuracy baseline. SF treats calibration as a product primitive, not an internal metric.

OPN is Opinion's utility token, launched in March 2026 with a 1-billion maximum supply. According to Opinion's public materials, OPN is used for trading fee discounts, access to premium AI insights on their platform, and as a platform reward mechanism. Their Open API (key + Bearer auth) is documented at docs.opinion.trade; the relationship between OPN token holdings and API tier access is not described in their public documentation as of the date of this review. SF has no token dependency — access is REST-based with no on-chain requirement.