Alternative · AI agent
Jatevo vs
SimpleFunctions.
Jatevo's 6-agent pipeline produces deep-research reports on Polymarket — a finished product for human analysts who want structured findings without writing code. SimpleFunctions operates one layer below, and across a broader venue universe: a causal-tree thesis system with auto-evaluation heartbeats and signal injection, a Portfolio Autopilot running through a 7-gate risk cascade, computed indicators across 48K+ contracts on both Kalshi and Polymarket, and a 56-tool MCP server any AI agent can call directly.
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 programmatic access — calibrated probabilities with public Brier scores, causal-tree thesis modelling with auto-evaluation cycles, regime classification across 48K+ contracts on both Kalshi and Polymarket, computed indicators (implied yield, cliff risk, liquidity availability score), and a 56-tool MCP server that drops into Claude Code or Cursor in one line. That is the SimpleFunctions surface area.
Choose Jatevo if
You need a turn-key deep-research report on a specific Polymarket question — one where a 6-agent pipeline does the investigation and returns structured findings you can read and act on directly, without writing any API calls or building downstream infrastructure. Jatevo's product is built around that human-analyst research workflow.
Jatevo runs a 6-agent research pipeline on Polymarket for human analysts. SimpleFunctions is the agent API layer: world model, thesis system, indicators, autopilot, MCP, and dual-venue coverage.
At a glance
Three things that
actually differ.
Everything Jatevo gives you — AI-driven analysis of Polymarket prediction markets and structured multi-agent research findings — SimpleFunctions also gives you, via the thesis system, trade ideas, and world-snapshot endpoints.
On top of that, SF ships computed indicators across 48K+ contracts on both Kalshi and Polymarket, an autonomous trading agent with a 7-gate risk cascade, and 56 MCP tools that no current PM research product exposes.
SF also publishes live Brier scores at /api/calibration — Kalshi 0.20, Polymarket 0.12 on T-24h price, past 90 days — so you can audit the underlying probability model before trusting any research output.
Side by side
9 dimensions · verified 2026-04SimpleFunctionsKalshi + Polymarket normalised, 48K+ active contracts indexed across both venues.
JatevoPolymarket integration documented publicly; Kalshi coverage not mentioned in public materials.
SimpleFunctionsGET /api/public/market/{ticker}?depth=true returns bid/ask ladder, spread, and slippage estimates.
JatevoNot published in public documentation.
SimpleFunctionsImplied yield, cliff risk index, liquidity availability score, event overround, and τ-days pre-computed across 48K contracts at /screen.
JatevoNot published; pipeline output is narrative research, not computed market signals.
SimpleFunctionsPOST /api/thesis/create decomposes any sentence into a causal tree, maps nodes to tradeable contracts, and runs an auto-evaluation heartbeat on a schedule.
Jatevo6-agent pipeline runs a structured deep-research workflow on a Polymarket question and returns findings as a human-readable report.
SimpleFunctionsLive Brier scores at /api/calibration — by venue, category, and price bucket — updated continuously.
JatevoNot published.
SimpleFunctionsPortfolio Autopilot: 1M-context LLM, 13 data sources, 7-gate risk cascade before execution.
JatevoNot in scope; Jatevo produces research output, not trade execution.
SimpleFunctions56 tools via claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp — works with Claude Code, Cursor, any MCP client.
JatevoNo MCP server published.
SimpleFunctionsFull public REST API, 60-command CLI (npm i -g @spfunctions/cli), and MCP server — no auth required for reads.
JatevoNo public REST API or CLI documented; access appears to be through the Jatevo platform interface.
SimpleFunctionsPublic REST, MCP, and CLI reads require no auth. Authenticated thesis and intent execution is free up to 15M tokens, then pay-per-token.
JatevoNot publicly disclosed.
Methodology
Verified 2026-04 from public sources only — Jatevo's documentation, public website, and publicly observable behaviour. We never claim non-public information about Jatevo'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 needs to query prediction market data, run indicator screens, and execute trades programmatically.
SimpleFunctions · best fit
SF's REST API, 56-tool MCP server, and Portfolio Autopilot are purpose-built for this. The agent can call /api/public/markets for live prices, /screen for indicator signals, and delegate execution to the Autopilot's 7-gate risk cascade.
Jatevo
Jatevo does not publish a programmatic API, making it a poor fit for machine-to-machine integration or autonomous agent workflows.
Scenario 02
A human analyst needs a structured deep-research report on a specific Polymarket question without writing any code.
SimpleFunctions
SF's thesis system can decompose the question and surface related contracts, but the output is structured data for downstream consumption, not a finished human-readable research report.
Jatevo · best fit
Jatevo is designed exactly for this: submit a question, receive a multi-agent research report. If the deliverable is a readable document rather than API data, Jatevo's product fits the workflow directly.
Scenario 03
Decomposing a complex macroeconomic thesis into testable sub-claims and tracking live calibration against market prices on both Kalshi and Polymarket.
SimpleFunctions · best fit
POST /api/thesis/create builds a causal tree, maps each node to contracts on both venues, and runs a scheduled evaluation heartbeat — news scan, price refresh, LLM eval, confidence update. Signal injection via /api/thesis/{id}/signal keeps the tree current.
Jatevo
Jatevo's 6-agent pipeline is oriented toward producing research on individual Polymarket questions, not maintaining a persistent causal model with cross-venue propagation and continuous re-evaluation.
Scenario 04
Auditing the accuracy of a prediction market data provider before building a trading system on top of it.
SimpleFunctions · best fit
SF publishes live Brier scores at /api/calibration, broken down by venue, category, and price bucket. You can verify the numbers yourself with a curl call before committing to integration.
Jatevo
No calibration benchmark is published, so accuracy claims cannot be independently verified from public sources.
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 Jatevo?+
Jatevo is a deep-research platform: submit a question about a Polymarket event and a 6-agent pipeline returns a structured research report for a human reader. SimpleFunctions is an API, CLI, and MCP server — a machine-readable layer your agent or code calls directly. The two products serve different audiences: Jatevo targets human analysts who want a finished report; SimpleFunctions targets developers and AI agents that need raw data, computed indicators, autonomous trading infrastructure, and a causal thesis system with live evaluation.
How does SimpleFunctions' causal thesis system work?+
POST /api/thesis/create takes a plain-English hypothesis — for example, "a US recession begins before Q4 2026." The system decomposes it into a causal tree of testable sub-claims, locates tradeable contracts on Kalshi and Polymarket that map to each node, and propagates probability estimates up the tree. An evaluation heartbeat then runs on a schedule: news scan, price refresh, milestone check, LLM evaluation, confidence update. You can inject new signals via /api/thesis/{id}/signal at any time. Public theses are forkable by other users.
Does SimpleFunctions cover Kalshi as well as Polymarket?+
Yes. SimpleFunctions normalises prices across both Kalshi and Polymarket, covering 48K+ active contracts. Jatevo's documented integration is Polymarket-only. If your research or trading spans both venues — or if you need cross-venue arbitrage opportunities via /api/public/cross-venue/pairs — SF provides the broader coverage by default.
Can I use SimpleFunctions with Claude Code, Cursor, or other AI coding environments?+
Yes. SF ships a 56-tool MCP server. Add it with one command: claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp. Once connected, your AI coding environment can query markets, run thesis searches, pull computed indicators, and access the world snapshot without any additional configuration. Jatevo does not publish an MCP server.
What is Portfolio Autopilot and how does it manage risk?+
Portfolio Autopilot is SF's autonomous trading agent. It runs a 1M-context LLM over 13 data sources and passes every candidate trade through a 7-gate risk cascade — including a kill switch, position limits, drawdown gate, and regime check — before any order is placed. It is designed to operate without human approval on each individual trade, while remaining bounded by the risk gates. Jatevo produces research reports; it does not offer autonomous trade execution.
How does SimpleFunctions audit its own prediction accuracy, and does Jatevo do the same?+
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 the T-24h price, computed over the past 90 days. You can re-verify these yourself with a curl call at any time. Based on public documentation as of 2026-04, Jatevo does not publish a comparable calibration benchmark.
Does Jatevo have a public REST API I can integrate with programmatically?+
Based on Jatevo's public website and documentation as of 2026-04, no public REST API is documented. Jatevo appears to operate as a platform where you submit research queries through their interface and receive reports back, rather than exposing a programmatic integration layer. If you need machine-readable endpoints, SF's REST API, CLI, and MCP server are all documented and accessible without authentication for reads.
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.