Inside Edge vs
SimpleFunctions.

Based on its public website, Inside Edge scans Polymarket for mispriced contracts and surfaces each opportunity alongside an explicit edge percentage. The product appears aimed at traders who want quantified inefficiency signals on a single venue without building their own pricing models. This characterisation is drawn entirely from their public website and tagline; we do not have access to their internal methodology, data pipeline, or execution layer.

The core difference is scope and product layer. Inside Edge surfaces Polymarket inefficiencies with edge percentages — a focused, single-venue signal product. SimpleFunctions covers both Kalshi and Polymarket, pre-computes a full indicator suite across 48K+ contracts, and ships a full agent layer: causal-tree thesis system with continuous auto-evaluation, autonomous Portfolio Autopilot with a 7-gate risk cascade, 56 MCP tools, and live Brier-score calibration data. They are purpose-built for different audiences.

POST /api/thesis/create accepts any natural-language claim and decomposes it into a causal tree of testable sub-claims, each mapped to matching Kalshi and Polymarket contracts. Probabilities propagate through the tree. A continuous evaluation heartbeat then runs — news scan, price refresh, milestone check, LLM evaluation, confidence update — keeping each node current. Signals can be injected at any node via /api/thesis/{id}/signal. Public theses are forkable. No current prediction-market data product exposes a comparable structured reasoning capability.

Yes, via Portfolio Autopilot. The system uses a 1M-context LLM with 13 data sources and requires all seven gates in its risk cascade to clear before execution: kill switch, position limits, drawdown gate, regime check, and additional safeguards. The design is conservative by default — the agent refuses execution when risk conditions are ambiguous. This is distinct from a simple rule-based executor; the LLM evaluates the full market context before committing to any position.

Yes. SF ships a 56-tool MCP server. Adding it takes one command: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. Once connected, an AI agent can search markets, retrieve orderbook depth, inspect cross-venue arbitrage pairs, query computed indicators, create and fork theses, and invoke Portfolio Autopilot controls — all from within its native tool interface, without writing custom API integration code. It works with Claude Code, Cursor, and any MCP-compatible client.

Yes. SimpleFunctions normalises data from both Kalshi and Polymarket, indexing 48K+ active contracts into a single API surface. Cross-venue matched pairs — contracts on the same underlying event listed at both venues — are available at /api/public/cross-venue/pairs?preset=arb, with spread data and potential arbitrage signals. Inside Edge, based on its public website, is scoped to Polymarket only. Traders who need cross-venue coverage or Kalshi-specific data will not find it there.

SF publishes live Brier scores at /api/calibration, broken down by venue, category, and price bucket. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h price, computed over the past 90 days. You can re-verify by hitting the endpoint directly with curl — the data is live, not a static assertion. Most prediction-market data products do not publish calibration data at this granularity; SF treats it as a public audit, not a marketing claim.

SimpleFunctions exposes a fully documented REST API (openapi.json at simplefunctions.dev), a CLI (npm i -g @spfunctions/cli, 60+ commands, MIT licensed), and a 56-tool MCP server. All read endpoints require no authentication. The same data available on SF's web interface — cross-venue prices, orderbook depth, computed indicators, trade ideas, arbitrage pairs — is queryable programmatically. Inside Edge does not currently publish a documented public API based on its public website.