Alternative · AI agent
Pricediction vs
SimpleFunctions.
Same upstream venues. Pricediction packages Kalshi and Polymarket into a web-first AI research and trading workflow — automated analysis, point-and-click execution for human operators. SimpleFunctions ships the agent layer above it: causal-tree thesis system with continuous evaluation cycles, autonomous Portfolio Autopilot (1M-context LLM, 7-gate risk cascade), computed indicators across 48K+ active contracts, live calibration data, 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 a browser interface — calibrated probabilities with public Brier scores, causal-tree thesis modelling that decomposes any sentence into testable sub-claims and auto-evaluates them on a continuous cycle, regime classification and computed indicators (implied yield, cliff risk, liquidity availability score) across the full 48K-contract universe, and a 56-tool MCP server that integrates with Claude Code, Cursor, or any MCP client in one command.
Choose Pricediction if
Pricediction is built as a web-first AI research and trading workflow — if your workflow is browser-based, with a human reviewing automated analysis before placing orders directly on Kalshi or Polymarket through a point-and-click interface, that is the experience Pricediction has designed its product around.
Same upstream venues (Kalshi + Polymarket). Pricediction offers a web-based research and trading workflow. SimpleFunctions ships the agent layer: thesis system, autopilot, indicators, MCP.
At a glance
Three things that
actually differ.
Everything Pricediction gives you — automated analysis, cross-venue coverage on Kalshi and Polymarket, and direct trading — SimpleFunctions also gives you, on the same underlying feeds.
On top of that, SF ships a causal-tree thesis system, an autonomous trading agent (Portfolio Autopilot, 1M-context LLM, 7-gate risk cascade), and 56 MCP tools that no current PM data product exposes.
SF publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days — a public accuracy audit most competitors skip entirely.
Side by side
9 dimensions · verified 2026-04SimpleFunctionsKalshi + Polymarket normalised, 48K+ active contracts indexed at /api/public/markets.
PricedictionKalshi and Polymarket — automated analysis and direct trading on both.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns bid/ask ladder, spread, and slippage estimate.
PricedictionOrderbook access not documented publicly.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, τ-days, and regime label — pre-computed across 48K contracts at /screen.
PricedictionAI-powered analysis on individual markets; derived indicator set not publicly documented.
SimpleFunctionsPOST /api/thesis/create decomposes any sentence into a causal tree, propagates probabilities, scans both venues for tradeable edges, and runs continuous auto-evaluation cycles.
PricedictionNot in scope.
SimpleFunctionsPortfolio Autopilot — 1M-context LLM, 13 data sources, 7-gate risk cascade before any execution; fully programmatic.
PricedictionDirect order execution on Kalshi and Polymarket from the web interface, with a human operator in the loop.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp; works with Claude Code, Cursor, any MCP client.
PricedictionNo MCP server published.
SimpleFunctionsLive Brier scores at /api/calibration — by venue, category, price bucket; Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days.
PricedictionNot published.
SimpleFunctionsAPI-first: REST endpoints, 60-command CLI, and MCP server — designed for programmatic and agent-driven consumption.
PricedictionWeb-based research and trading workflow — designed for human-in-the-loop usage.
SimpleFunctionsPublic REST + MCP + CLI reads require no auth. Thesis and intent execution: free up to 15M tokens, then pay-per-token.
PricedictionPricing not publicly documented in reviewed sources.
Methodology
Verified 2026-04 from public sources only — Pricediction's documentation, public website, and publicly observable behaviour. We never claim non-public information about Pricediction'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 continuously monitors, evaluates, and trades prediction markets without a human in the loop.
SimpleFunctions · best fit
SF's Portfolio Autopilot was designed for this: a 1M-context LLM evaluates 13 data sources and passes through a 7-gate risk cascade before any order. The MCP server exposes all tools to any agent runtime, and the thesis system auto-evaluates positions on an ongoing cycle.
Pricediction
Pricediction is built around human-in-the-loop web execution; its direct trading interface expects a user to review and confirm positions, making fully autonomous operation outside its stated product scope.
Scenario 02
Researching and manually executing trades on Kalshi and Polymarket through a browser-based interface.
SimpleFunctions
SF is API-first and CLI-first; it has a /screen indicator page but no purpose-built point-and-click trade execution workflow for human operators. Integration requires the REST API or CLI.
Pricediction · best fit
Pricediction is the right product for this. Its core design combines AI-assisted market research with a direct trading interface on both Kalshi and Polymarket, purpose-built for human-in-the-loop review and execution.
Scenario 03
Decomposing a complex macro thesis — 'EU energy supply disruption will force ECB to hold rates' — into individually tradeable prediction market contracts.
SimpleFunctions · best fit
POST /api/thesis/create handles exactly this: the thesis is parsed into a causal tree, each sub-claim is matched against active Kalshi and Polymarket contracts, and an evaluation heartbeat keeps confidence scores current as news and prices shift.
Pricediction
Pricediction's automated analysis can surface relevant markets, but structured causal-tree decomposition with auto-evaluation is not a documented feature.
Scenario 04
Integrating live prediction market signals into an LLM agent workflow via a standardised tool protocol.
SimpleFunctions · best fit
SF's 56-tool MCP server connects to Claude Code, Cursor, or any MCP-compliant runtime in one command. The agent can query contracts, evaluate theses, check calibration, and scan for arbitrage pairs without leaving its tool environment.
Pricediction
Pricediction does not publish an MCP server; integration into an LLM tool environment would require a custom wrapper around its web interface.
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 SimpleFunctions' thesis system and how does it differ from Pricediction's automated analysis?+
SimpleFunctions' thesis system starts from a plain-language hypothesis. POST /api/thesis/create decomposes it into a causal tree of testable sub-claims, assigns each a probability, scans Kalshi and Polymarket for contracts that represent tradeable edges, and runs a continuous evaluation heartbeat: news scan, price refresh, milestone check, LLM re-evaluation, confidence update. Signals can be injected at any time via /api/thesis/{id}/signal. Pricediction's automated analysis surfaces relevant markets but does not expose structured causal decomposition or auto-evaluation cycles as a documented feature.
How does SimpleFunctions' Portfolio Autopilot work?+
Portfolio Autopilot is an autonomous trading agent, not a web interface. A 1M-context LLM evaluates 13 data sources — price feeds, orderbook depth, thesis signals, calibration baselines, regime labels, and more — and passes every proposed action through a 7-gate risk cascade: kill switch, position limits, drawdown gate, regime check, and additional safeguards before any order is placed. The result is a system that can operate without human sign-off on each trade, unlike a browser-based direct trading interface where a human reviews and confirms each action.
Does SimpleFunctions have a web interface for research and trading like Pricediction?+
SF is API-first: REST endpoints, a 60-command CLI, and a 56-tool MCP server. A /screen page exposes pre-computed indicators across all active contracts as a browsable table, but there is no purpose-built point-and-click trade execution workflow for human operators. If your primary use case is browser-based research and manual order placement rather than agent or programmatic integration, Pricediction's web interface is the product designed for that workflow.
What computed indicators does SimpleFunctions provide beyond raw prices?+
SF pre-computes six indicators across all 48K+ active Kalshi and Polymarket contracts: IY (implied yield, annualised return if YES), CRI (cliff risk index, residual risk near expiry), LAS (liquidity availability score, deployable capital before significant slippage), EE (event overround, total market vig), τ-days (time to settlement), and regime label (adverse-selection classification). All six are available at /screen and via the MCP server. Pricediction's derived indicator set is not publicly documented.
How does SimpleFunctions measure and publish its own accuracy?+
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. The endpoint is live and re-verifiable with a single curl call at any time. Most prediction market data products claim accuracy in general terms but do not expose a structured, queryable calibration baseline. Pricediction does not publish equivalent accuracy metrics in its reviewed public documentation.
What is the MCP server and how do I connect it to Claude Code or Cursor?+
SimpleFunctions ships a 56-tool MCP server at https://simplefunctions.dev/api/mcp/mcp. Add it in one line: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. Once connected, any MCP client — Claude Code, Cursor, or any compliant runtime — can call all 56 tools directly: market lookup, thesis creation, autopilot instructions, calibration checks, cross-venue arbitrage scan, and more. No API key is required for read operations. Pricediction does not publish an MCP server.
Can I use SimpleFunctions and Pricediction together?+
Yes. The two products occupy different surfaces. Pricediction is a web research and trading workflow. SimpleFunctions is an API, CLI, and MCP server. If you use Pricediction for point-and-click research and manual execution, you can simultaneously use SF's MCP server inside Claude Code to drive agent workflows, or use SF's thesis system to evaluate the same markets programmatically. The underlying venues — Kalshi and Polymarket — are the same, so signals from one context carry into the other.
What cross-venue arbitrage detection does SimpleFunctions offer?+
SF normalises Kalshi and Polymarket contracts into matched pairs so that equivalent contracts are directly comparable across venues. Arbitrage opportunities are available at /api/public/cross-venue/pairs?preset=arb. Orderbook depth for slippage estimation is at GET /api/public/market/{ticker}?depth=true. Trade ideas with conviction scores and catalysts are at /api/public/ideas. These endpoints are publicly accessible without authentication and are re-verifiable in real time.
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.