Alternative · Analytics aggregator
Prediedge vs
SimpleFunctions.
Same upstream venues. Prediedge surfaces large-trade signals and whale activity on Polymarket and Kalshi — flow analytics and insider detection aimed at human traders watching market microstructure. SimpleFunctions ships the agent layer above those same markets: causal-tree thesis system with continuous auto-evaluation cycles, autonomous portfolio trading, calibrated world model across 48K+ contracts, computed indicators, and a 56-tool MCP server.
Verified 2026-04 · public sources only · live SF data from /calibration
Verdict
Pick the one that fits how
you actually work.
Choose SimpleFunctions if
You are building agents, autonomous trading systems, or research pipelines that need more than flow surveillance — calibrated probabilities with public Brier scores, causal-tree thesis modelling with continuous evaluation cycles, regime classification and computed indicators (implied yield, cliff risk, liquidity availability score) across the full 48K-contract universe, autonomous execution with a 7-gate risk cascade, and a 56-tool MCP server that integrates with Claude Code or Cursor in one line.
Choose Prediedge if
You specifically need large-trade and whale-flow surveillance — detecting outsized positions, insider-adjacent activity, and market microstructure signals on Polymarket and Kalshi. That is Prediedge's product focus, and their UI and signal pipeline are built around traders who use that flow data as a primary input.
Same upstream venues (Kalshi + Polymarket). Prediedge specialises in whale and large-trade flow analytics. SimpleFunctions ships the agent layer: world model, thesis system, indicators, autopilot, MCP.
At a glance
Three things that
actually differ.
Everything Prediedge gives you — real-time market data, signals, and cross-venue coverage on Kalshi and Polymarket — SimpleFunctions also gives you, on the same underlying feeds.
On top of that, SF ships a causal-tree thesis system, an autonomous Portfolio Autopilot (1M-context LLM, 7-gate risk cascade), computed indicators across 48K+ contracts, and 56 MCP tools no current PM data product exposes.
SF publishes live Brier scores for itself at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days. Most competitors claim accuracy; SF lets you verify its own.
Side by side
9 dimensions · verified 2026-04SimpleFunctionsKalshi + Polymarket normalised, 48K+ active contracts indexed at /api/public/markets.
PrediedgeKalshi + Polymarket real-time prices and analytics surfaced in dashboard.
SimpleFunctionsBid/ask ladder, spread, and slippage data at /api/public/market/{ticker}?depth=true.
PrediedgeMarket microstructure data surfaced as part of analytics view.
SimpleFunctionsNot a dedicated feature; orderbook depth and liquidity availability score (LAS) serve structural edge detection.
PrediedgeCore product feature: large-trade detection, whale-flow surveillance, and insider-adjacent activity signals.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, τ-days, and regime label — pre-computed across 48K+ contracts at /screen.
PrediedgeRaw price, volume, and flow data; derived signals are left to the user.
SimpleFunctionsLive Brier scores at /api/calibration — by venue, category, and price bucket; updated continuously.
PrediedgeNot published.
SimpleFunctionsPOST /api/thesis/create decomposes any sentence into a causal tree of testable sub-claims, propagates probabilities, auto-evaluates on each news cycle, and surfaces tradeable edges.
PrediedgeNot in scope.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM, 13 data sources, 7-gate risk cascade (kill switch, drawdown gate, regime check) before execution.
PrediedgeNot in scope.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp; works with Claude Code, Cursor, and any MCP client.
PrediedgeNo MCP server published.
SimpleFunctionsPublic REST + MCP + CLI require no auth for reads. Thesis and intent execution is free up to 15M tokens, then pay-per-token.
PrediedgePricing not publicly detailed in available sources.
Methodology
Verified 2026-04 from public sources only — Prediedge's documentation, public website, and publicly observable behaviour. We never claim non-public information about Prediedge's internals. SimpleFunctions claims on this page are computed live from /api/calibration, /api/public/cross-venue/pairs, and /api/public/markets — you can re-verify them yourself with curl.
Use cases
Same data, different
best fit per scenario.
Scenario 01
Building an AI agent that monitors prediction markets and executes trades based on a structured research thesis.
SimpleFunctions · best fit
SF's thesis system decomposes the hypothesis into a causal tree, runs evaluation cycles on every news update, and hands off to Portfolio Autopilot for gated execution. The 56-tool MCP server exposes the full pipeline to Claude Code or any MCP-compatible client.
Prediedge
Prediedge is analytics-oriented and does not expose an agent execution layer, thesis evaluation loop, or programmatic trading capability.
Scenario 02
A trader wants to detect large whale positions and insider-adjacent flow entering the market in real time.
SimpleFunctions
SF tracks prices and orderbook depth but does not specialise in whale-flow surveillance or large-trade detection as a first-class product feature.
Prediedge · best fit
This is Prediedge's core product. Their signal pipeline and UI are purpose-built around large-trade detection, whale tracking, and insider-adjacent activity — precisely the audience they serve.
Scenario 03
Decomposing a complex geopolitical or macroeconomic thesis into testable sub-claims and tracking confidence as new information arrives.
SimpleFunctions · best fit
SF's POST /api/thesis/create handles exactly this — causal-tree decomposition, probability propagation, continuous evaluation against news and market prices, and signal injection via /api/thesis/{id}/signal. Public theses are forkable.
Prediedge
Prediedge does not surface a thesis modelling or sub-claim evaluation capability.
Scenario 04
Cross-venue arbitrage detection using computed indicators and a live calibration baseline.
SimpleFunctions · best fit
SF's /api/public/cross-venue/pairs?preset=arb surfaces matched pairs across Kalshi and Polymarket. Computed indicators (implied yield, cliff risk index) and live Brier scores at /api/calibration give a calibrated baseline for evaluating edge quality.
Prediedge
Prediedge surfaces cross-venue market data but does not publish computed arbitrage pairs or a calibration accuracy baseline.
Live data
The SimpleFunctions claims on this page are not marketing copy. Brier scores, market counts, and cross-venue pair counts are computed live from /calibration, /screen, and /api/public/cross-venue/pairs. All public, all free, all CC-BY-4.0.
FAQ
What is the main difference between SimpleFunctions and Prediedge?+
Prediedge is an analytics product focused on whale tracking and large-trade detection on Polymarket and Kalshi — a signal layer for human traders watching market microstructure. SimpleFunctions is an agent execution layer built on the same venues: causal-tree thesis evaluation, autonomous trading via Portfolio Autopilot, computed indicators across 48K+ contracts, and a 56-tool MCP server. The two products target different workflows and audiences.
Does SimpleFunctions have whale tracking or large-trade detection?+
Not as a dedicated feature. SF tracks orderbook depth, spread, and slippage at /api/public/market/{ticker}?depth=true and pre-computes a liquidity availability score (LAS) across all active contracts. If whale-flow surveillance and large-trade detection are your primary signal source, Prediedge is purpose-built for that use case and SF is not.
How does the SimpleFunctions thesis system work?+
POST /api/thesis/create accepts a plain-language sentence and decomposes it into a causal tree of testable sub-claims. Each node receives a probability estimate. An evaluation heartbeat runs continuously: news scan, price refresh, milestone check, LLM evaluation, and confidence update. You can inject external signals at any node via /api/thesis/{id}/signal. The system scans Kalshi and Polymarket for contracts that correspond to each sub-claim and flags tradeable edges. No competitor exposes this pipeline.
What is Portfolio Autopilot and how does it manage risk?+
Portfolio Autopilot is SF's autonomous trading agent. It runs a 1M-context LLM across 13 data sources and passes every candidate trade through a 7-gate risk cascade — kill switch, position-size limits, drawdown gate, regime check, and additional controls — before any order is placed. The agent can monitor the full 48K-contract universe, evaluate ideas against the live thesis graph, and execute without a human in the loop on every trade, while hard-coded risk stops remain active throughout.
Can SimpleFunctions be used inside Claude Code or other AI tools?+
Yes. SF ships a 56-tool MCP server accessible in one line: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. This integrates with Claude Code, Cursor, and any MCP-compatible client. Once connected, the agent can query live markets, evaluate theses, pull cross-venue arbitrage pairs, and trigger trading actions — all from within the development environment.
Does SimpleFunctions publish its own prediction accuracy?+
Yes. /api/calibration returns SF's live Brier scores by venue, category, and price bucket, computed over the past 90 days. Current figures: Kalshi 0.20, Polymarket 0.12 on T-24h price. Brier score is a standard probabilistic accuracy metric — lower is better. SF audits its own accuracy publicly; most data and analytics products do not publish an equivalent baseline.
What computed indicators does SimpleFunctions provide, and how are they different from raw data?+
SF pre-computes six indicators across its 48K+ active contracts: IY (implied yield), CRI (cliff risk index), LAS (liquidity availability score), EE (event overround), τ-days (time to settlement), and regime label (adverse-selection classification). These are available at /screen and surfaced in the MCP server. Raw price and flow feeds require you to derive these signals yourself; SF ships them pre-computed and queryable across the full contract universe.
Start for free.
Public endpoints are free for normal usage and rate-limited for reliability. Authenticated endpoints are free up to 15M tokens, then pay per token. No credit card to start.