Directory / aialign.halowerk.com
Computes weighted pass rates and weighted scores from caller-labeled test outcomes, with deterministic category summaries. It does not run tests, validate labels, measure untested capabilities or establish deployment safety; the result is only as representative as the supplied evaluation set.
# 1. Ask the endpoint what it costs (no payment, no wallet needed): curl -i -X GET 'https://aialign.halowerk.com/v1/capability-eval' # -> HTTP/1.1 402 Payment Required # the response carries the price, asset and pay-to address. # 2. Pay and retry with any x402 client: npx x402-fetch 'https://aialign.halowerk.com/v1/capability-eval'
Endpoint: https://aialign.halowerk.com/v1/capability-eval. Operated by aialign.halowerk.com, not by Animica. Price and availability were correct at the last probe on 2026-09-02 and are set by the operator, who may change them.
Requires the same agents in each supplied round, computes each pair’s observed action agreement, expected agreement from marginal action frequencies and chance-…
Calculates each group positive-outcome rate, compares it with an explicit or automatically selected reference group, and reports rate differences and selection-…
Compares scalar confidence with binary correctness, calculates mean squared Brier loss, partitions confidence into caller-selected equal-width bins and reports …
Aligns caller-labeled dimensions, computes cosine similarity and a normalized L1 difference, and flags drift against a supplied cosine threshold. It does not in…
Tokenizes each claim and its supplied evidence, removes a small declared English stop-word list, and reports the fraction of unique claim tokens present in evid…
Applies a small fixed set of defensive regular-expression categories and returns category names, a bounded risk score and a review recommendation. It does not e…
Replaces private-key blocks, credential assignments, email addresses, Luhn-valid payment-card candidates, IPv4 addresses and phone-like digit strings, returning…
Divides observed CPU, memory-time, network, tool-call and wall-time usage by caller-supplied budgets, reports exceeded dimensions and ranks observations by the …
Compares term-frequency cosine similarity between a leading user position and paired independent/conditioned responses, then reports the positive similarity shi…