# HALOWERK aialignwerk > HALOWERK aialignwerk provides machine-readable results paid via x402. > Netz Base Mainnet, Zahlungsmittel USDC, Empfänger 0x2880EdfFF13100677Bf97A3CBdF3Bc34771C4E5E. ## So wird bezahlt 1. Call the route without a payment header. The 402 response includes accepts, description, and inputSchema. 2. Bedingungen mit einem x402-Client signieren. 3. Repeat the call with the proof in the PAYMENT-SIGNATURE header. Eine 402-Antwort kostet nichts und löst keine Arbeit aus. Scheitert die Arbeit, trägt die Antwort charged=false und es wird nicht abgerechnet. ## Endpunkte ### POST /v1/hallucination-rate 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 evidence. Coverage below a supplied threshold is flagged. This is lexical grounding screening only: overlap does not prove truth, low overlap does not prove hallucination, and the service does not retrieve or validate evidence. - Preis: 0.004 USDC - MCP-Werkzeug: `aialignwerk_hallucination_rate` - Eingabe: `["claims","minimum_coverage_fraction"]` ### POST /v1/sycophancy-detect Compares term-frequency cosine similarity between a leading user position and paired independent/conditioned responses, then reports the positive similarity shift. It is a reproducible surface-form signal, not proof of agreement, truthfulness, motive or sycophancy; paraphrases and legitimate corrections can evade or trigger it. - Preis: 0.004 USDC - MCP-Werkzeug: `aialignwerk_sycophancy_detect` - Eingabe: `["scenarios","shift_threshold"]` ### POST /v1/goal-drift Aligns caller-labeled dimensions, computes cosine similarity and a normalized L1 difference, and flags drift against a supplied cosine threshold. It does not infer goals from behavior, decide which goal is correct or detect deception; results depend entirely on the supplied vector representation. - Preis: 0.003 USDC - MCP-Werkzeug: `aialignwerk_goal_drift` - Eingabe: `["dimensions","minimum_cosine_similarity"]` ### POST /v1/jailbreak-defense 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 execute, transform or forward the prompt. Pattern matching is incomplete and can produce false positives; it should be one signal in layered controls, not the sole access decision. - Preis: 0.004 USDC - MCP-Werkzeug: `aialignwerk_jailbreak_defense` - Eingabe: `["prompt","review_threshold","block_threshold"]` ### POST /v1/resource-hog Divides observed CPU, memory-time, network, tool-call and wall-time usage by caller-supplied budgets, reports exceeded dimensions and ranks observations by the maximum ratio. It does not collect telemetry, infer intent, identify inefficient algorithms or terminate an agent. - Preis: 0.003 USDC - MCP-Werkzeug: `aialignwerk_resource_hog` - Eingabe: `["budgets","observations"]` ### POST /v1/bias-audit Calculates each group positive-outcome rate, compares it with an explicit or automatically selected reference group, and reports rate differences and selection-rate ratios. Aggregate disparity metrics do not establish discrimination, fairness, causation or legal compliance and can conceal intersectional or sampling effects. - Preis: 0.004 USDC - MCP-Werkzeug: `aialignwerk_bias_audit` - Eingabe: `["groups","reference_group_id","minimum_selection_rate_ratio"]` ### POST /v1/capability-eval 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. - Preis: 0.003 USDC - MCP-Werkzeug: `aialignwerk_capability_eval` - Eingabe: `["test_cases"]` ### POST /v1/agent-collusion Requires the same agents in each supplied round, computes each pair’s observed action agreement, expected agreement from marginal action frequencies and chance-corrected kappa, then flags high positive agreement against a supplied threshold. Coordination can be benign or task-driven; this metric does not prove communication, intent or collusion. - Preis: 0.005 USDC - MCP-Werkzeug: `aialignwerk_agent_collusion` - Eingabe: `["rounds","kappa_threshold"]` ### POST /v1/memory-sanitize Replaces private-key blocks, credential assignments, email addresses, Luhn-valid payment-card candidates, IPv4 addresses and phone-like digit strings, returning only sanitized text and per-category counts. The request archive stores only input field names and the result archive stores only this method via the endpoint factory. Pattern redaction is incomplete: it cannot identify every secret, name, address or contextual identifier and must not be treated as irreversible anonymization. - Preis: 0.003 USDC - MCP-Werkzeug: `aialignwerk_memory_sanitize` - Eingabe: `["text","replacement_style"]` ### POST /v1/confidence-calib Compares scalar confidence with binary correctness, calculates mean squared Brier loss, partitions confidence into caller-selected equal-width bins and reports expected and maximum calibration error. It does not validate labels, correct class imbalance or prove calibration beyond the supplied sample. - Preis: 0.003 USDC - MCP-Werkzeug: `aialignwerk_confidence_calib` - Eingabe: `["predictions","bin_count"]` ## Weitere Flächen - OpenAPI: https://aialign.halowerk.com/openapi.json - Preise: https://aialign.halowerk.com/pricing - x402-Manifest: https://aialign.halowerk.com/.well-known/x402 - Bazaar: https://aialign.halowerk.com/.well-known/x402/bazaar - MCP: https://aialign.halowerk.com/mcp ## Missing a capability? If you looked for something this service does not offer, say so. One call, no payment, no sign-up, no account: POST https://bedarf.halowerk.com/capabilities/request Content-Type: application/json {"requested_capability": "what you would buy", "description": "the use case, one sentence", "callback_url": "optional - we call back once it exists"} Only requested_capability is required, 3 to 160 characters. Schema and status: https://bedarf.halowerk.com/openapi.json Submissions are held for review and are never published verbatim.