Verify a claim against 2-4 source URLs: cited passages, cross-source agreement, verdict: consistent | conflicting | insufficient_evidence. Evidence, not truth. Use when your agent needs to verify a claim against independent sources before acting on it. Give a claim plus 2-4 source URLs; each source is extracted (three-fetch cross-check, confidence-scored), the checkable figures are compared across sources, and you get the cited passages plus a verdict: consistent (sources report the claim's figures), conflicting (sources agree with each other on different figures), or insufficient_evidence. This sells evidence, not truth — the verdict describes source agreement and says so. One $0.03 call replaces three separate extractions plus your own comparison. Money Mind sells judges, not strategies. This company has no proven edge and does not sell signals, forecasts or data.

Triage up to 1,000 backtests in one call: the best-of-N multiple-testing selection correction over every return series — $0.01 per series, survivors ranked best-first. Use when your agent has a FARM of backtests, strategies, or research results — dozens to a thousand — and needs triage, not one-by-one verdicts. One call runs the selection correction over every series: each gets NO (killed), PROVISIONAL (survived this gate), or ERROR (malformed). Results ranked survivors-first by family-wise p. Priced at $0.01 per series submitted, stated in the 402 before you pay. This is triage: run judge-lite on the provisional survivors for the full three-gate verdict. Bad bodies are refused before payment, never charged. Money Mind sells judges, not strategies. This company has no proven edge and does not sell signals, forecasts or data.

Is this backtest, strategy or DeFi result real, or the luckiest of N tries — selection, Sharpe and clustering in one verdict, built for trading agents. Use when your agent has a backtest, a research result, or any return series that looks good — and needs to know whether it is real or the luckiest of N tries before spending money on it. One call runs the three cheapest high-signal gates: selection correction (family-wise p across your declared n_tested), deflated Sharpe, and date-clustered t. Verdict REAL means every gate passed; PROVISIONAL means the selection gates passed but no dates were given, so clustering is unchecked — never REAL; NO names the gate that killed it. Bad input is refused before payment, never charged. Money Mind sells judges, not strategies. This company has no proven edge and does not sell signals, forecasts or data.

Is this backtest winner real, or the luckiest of N tries — the selection correction in one $0.01 call. Use when your agent has a backtest winner, a research result, or any return series that looks good — and needs the cheapest possible check on whether it is real or the luckiest of N tries. One call runs the selection correction: the family-wise p of the series' own t across your declared n_tested. Verdict NO names selection as the killer; PROVISIONAL means it survived this one gate — the deflated Sharpe and date-clustered t did not run, so this is never REAL. For the full three-gate verdict use judge-lite. Bad input is refused before payment, never charged. Money Mind sells judges, not strategies. This company has no proven edge and does not sell signals, forecasts or data.

Fetch a web page three independent ways (rendered, static, second-render cross-check), confidence-scored, with a tamper-evident attestation. Refuses protected, login and CAPTCHA pages without charging. Use when your agent needs web content it cannot fetch itself — JavaScript-rendered pages, static pages, or paginated listings — and needs to show its principal the evidence. Every extraction runs three independent fetches (rendered, static, second-render cross-check), is confidence-scored, and is written to a public tamper-evident attestation chain. Protected, login, and CAPTCHA pages are explicitly refused and never charged. Money Mind sells judges, not strategies. This company has no proven edge and does not sell signals, forecasts or data.