{"api_version":2,"receipt_profile":"zambo-hosted-receipt/1","schema_url":"https://zambo.dev/aer-1/hosted-profile.schema.json","id":"4deb882f-82be-49b7-bf44-3576c54aab45","source_url":"https://zambo.dev/api/receipt/4deb882f-82be-49b7-bf44-3576c54aab45","receipt":{"id":"4deb882f-82be-49b7-bf44-3576c54aab45","created_at":"2026-10-19T03:01:28.933Z","receipt_schema_version":"0.4","job_summary":"MCP tool execution: write","tools":["write"],"steps":[{"tool":"write","status":"success","started_at":"2026-10-19T03:01:27.403Z","completed_at":"2026-10-19T03:01:28.933Z"}],"output_hash":"sha256:55b0e532d7550743ec81a152a1fce66b78b747a0c716d86c881d41d50090c575","hash_algorithm":"sha256","canonical_bytes":"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","canonical_bytes_withheld_for_privacy":false,"canonical_byte_length":5325,"verification_status":"verified","session_trail":[],"result_preview":"AI reliability isn’t a nice‑to‑have feature; it’s the backbone of every production line that trusts machine learning to deliver results. When a model fails, the cost spikes—downtime, lost revenue, and eroded trust. That’s why enterprises that deploy AI at scale treat reliability like a critical infrastructure asset, not an optional upgrade.\n\nFirst, consider the stakes. In finance, a misclassified risk score can trigger a cascade of regulatory fines. In healthcare, an inaccurate diagnostic model can endanger lives. In manufacturing, a faulty predictive maintenance algorithm can halt an entire assembly line. The margin for error shrinks as the domain demands higher precision. Reliability, therefore, becomes the linchpin that guarantees consistent performance under real‑world conditions.\n\n**Why traditional testing falls short.** Conventional unit tests capture code logic but miss the stochastic nature of data. Unit tests assume inputs stay within a narrow envelope, yet production data is a wild card—seasonal shifts, new customer segments, sensor drift. Even a perfectly engineered algorithm can misbehave when the data distribution drifts. Relying solely on pre‑deployment validation leads to brittle systems that crumble once the first anomaly hits.\n\n**Continuous monitoring is the antidote.** Deploying an AI model with real‑time dashboards that flag deviations in input statistics, prediction confidence, or outcome metrics creates a living safety net. When a sudden spike in error rates appears, the system can trigger a rollback or an automated retraining cycle. This approach transforms reliability from a static guarantee into a dynamic, self‑correcting process.\n\n**Data lineage and governance matter.** Every feature fed into a model must be traceable from raw source to final prediction. When a data source changes, the impact on downstream performance should be instantly visible. Auditable pipelines empower teams to pinpoint root causes quickly, reducing mean time to recovery. Moreover, robust governance ensures that data quality standards are enforced before the data even reaches the model, preventing contamination that could erode reliability.\n\n**Model versioning and reproducibility.** In production, you’re rarely running a single version of a model. You cycle through experiments, fine‑tuning, and A/B tests. If an older version underperforms, you need a clear path to rollback. Version control for models, combined with reproducible training environments, guarantees that a regression can be identified and reversed without compromising the entire system. It also provides the evidence needed for compliance audits, a critical factor for regulated industries.\n\n**Stress testing under realistic workloads.** Simulating peak traffic, edge cases, and hardware failures reveals hidden bottlenecks. Stress tests expose latency spikes, memory leaks, and concurrency issues that only manifest under load. By incorporating these tests into the CI/CD pipeline, you catch reliability problems before they reach customers. The results are predictable latency, graceful degradation, and confidence that the system can handle the worst case.\n\n**Human‑in‑the‑loop (HITL) safeguards.** Even the most robust AI can misinterpret context. Embedding human oversight in critical decision paths ensures that anomalies trigger a review rather than an automatic action. HITL acts as a safety net, catching edge‑case errors that automated systems overlook. Over time, the feedback loop from human reviews feeds back into the model, tightening its reliability.\n\n**Metrics that matter.** Accuracy, precision, recall, and F1 score are valuable, but they don’t capture the full reliability picture. Turnkey metrics such as uptime, mean time between failures, and recovery time offer a clearer view of operational health. Coupling these with a confidence‑based alerting system creates a comprehensive reliability dashboard that stakeholders can trust.\n\n**Investing in reliability pays dividends.** Companies that prioritize AI reliability enjoy higher adoption rates, fewer support tickets, and stronger brand reputation. They avoid costly downtime and regulatory penalties. Moreover, a reliable AI foundation unlocks new opportunities—real‑time personalization, autonomous operations, and predictive analytics—without the fear of catastrophic failure.\n\nIn sum, AI reliability is the bedrock of production-grade machine learning. It demands continuous monitoring, rigorous data governance, version control, stress testing, and human oversight. By treating reliability as an integral part of the development lifecycle, organizations transform AI from a speculative novelty into a dependable, scalable asset that drives business value at every turn.","result_preview_integrity":"display_only_not_committed","result_preview_truncated":false,"input_hash":"sha256:ae637fd19228b3963883ab6ab98fadbed9aa7d91df4947ad08906b8de9ff2847","input_hash_layout":"zambo-json-sorted-keys-utf8-v1","free_used":0,"free_remaining":0,"free_limit":0,"signal_handle":null,"tool":{"name":"write","version":"4.0.0","scope":"public"},"caller":{"type":"anonymous","id":"sha256:831c0b63a8e508a6e53738c083ac40181438af8f6d1b1be7ea56ff0cfa7668a9","basis":"ip_ua_30d","rotates_at":"2026-11-03T00:00:00.000Z"},"side_effects":{"declared":["none"],"schema_version":"zambo-side-effects/1","declaration_hash":"sha256:45aad38f3aa982b9aafe92ecb416ebe98791eddbaf8ab6df0bd08605b7c1bfee"},"evidence_sha256":null,"evidence_url":null,"evidence_byte_length":null,"evidence_content_type":null,"evidence_source_url":null,"evidence_status":"no_upstream_bytes_captured","external_evidence":[],"provenance":null,"provenance_class":"EXECUTED BY ZAMBO","metadata_hash":"sha256:837ac2cf840f37290d69e9bd061b8916f2c4e826b035a98caf8b09b2dbf3423e","anchor":{"event_id":"13383d1b9fbde0ce1affb2e70e0f6833ca04e812410c139de08206b731977663","pubkey":"e13475107d30c918ec664adf2ab1141024a22fb35190f82c9e933704fa49af41","relays":["wss://relay.damus.io","wss://nos.lol","wss://relay.primal.net"],"status":"partial","published_at":"2026-10-19T03:01:29.504Z","schema_version":"zambo-receipt-anchor/1","envelope":{"anchored_at":"2026-10-19T03:01:28.933Z","evidence_url":null,"receipt_uuid":"4deb882f-82be-49b7-bf44-3576c54aab45","output_sha256":"sha256:55b0e532d7550743ec81a152a1fce66b78b747a0c716d86c881d41d50090c575","schema_version":"zambo-receipt-anchor/1","evidence_sha256":null,"evidence_byte_length":null},"envelope_bytes":"{\"anchored_at\":\"2026-10-19T03:01:28.933Z\",\"evidence_byte_length\":null,\"evidence_sha256\":null,\"evidence_url\":null,\"output_sha256\":\"sha256:55b0e532d7550743ec81a152a1fce66b78b747a0c716d86c881d41d50090c575\",\"receipt_uuid\":\"4deb882f-82be-49b7-bf44-3576c54aab45\",\"schema_version\":\"zambo-receipt-anchor/1\"}"},"receipt_profile":"zambo-hosted-receipt/1","schema_url":"https://zambo.dev/aer-1/hosted-profile.schema.json","api_version":1,"verification_scope":"separate_sha256_commitment_and_provenance_binding_checks","checks":{"commitment_matches":{"label":"SHA-256 commitment","passed":true,"status":"pass","detail":"The exact decoded canonical bytes match the stored SHA-256 output hash."},"canonical_payload_matches":{"label":"Canonical payload reconstruction","passed":true,"status":"pass","detail":"The stored output and known call context reconstruct the exact canonical bytes."},"provenance_binding":{"label":"Provenance claim binding","status":"pass","passed":true,"detail":"The metadata claim is consistent with the verified receipt bytes; issuer is not authenticated."},"metadata_binding":{"label":"AER-1 metadata hash","status":"pass","passed":true,"detail":"metadata_hash matches the canonical metadata block."},"signature":{"label":"Ed25519 signature (not checked)","passed":false,"status":"not_checked","detail":"No Ed25519 signature or pinned signing key was checked."},"chain":{"label":"Receipt chain (not checked)","passed":false,"status":"not_checked","detail":"No append-only receipt-chain proof was checked."},"issued_by_zambo_dev":{"label":"Issuer authentication","passed":false,"status":"not_checked","detail":"A zambo.dev receipt URL does not authenticate the issuer; no pinned signature or trusted issuer key was checked."},"immutable_log_timestamp":{"label":"Stored timestamp","passed":true,"timestamp":"2026-10-19T03:01:28.933Z","detail":"The receipt store reports 2026-10-19T03:01:28.933Z; immutability is not checked here."},"receipt_schema_version":"0.4","signature_valid":{"label":"Ed25519 signature (not checked)","passed":false,"status":"not_checked","detail":"Compatibility field only. No Ed25519 signature was checked; use API v2 checks.commitment_matches for the SHA-256 commitment."},"chain_valid":{"label":"Receipt chain (not checked)","passed":false,"status":"not_checked","detail":"This endpoint does not verify an append-only chain."}},"execution_context":{"environment":"zambo.dev hosted MCP"}},"verification_status":"verified","checks":{"commitment_matches":{"status":"pass","passed":true,"expected_hash":"sha256:55b0e532d7550743ec81a152a1fce66b78b747a0c716d86c881d41d50090c575","computed_hash":"sha256:55b0e532d7550743ec81a152a1fce66b78b747a0c716d86c881d41d50090c575","detail":"SHA-256 of the exact decoded canonical bytes matches output_hash."},"canonical_payload_matches":{"label":"Canonical payload reconstruction","passed":true,"status":"pass","detail":"The stored output and known call context reconstruct the exact canonical bytes."},"provenance_binding":{"label":"Provenance claim binding","status":"pass","passed":true,"detail":"The metadata claim is consistent with the verified receipt bytes; issuer is not authenticated."},"metadata_binding":{"label":"AER-1 metadata hash","status":"pass","passed":true,"detail":"metadata_hash matches the canonical metadata block."},"issuer_authentication":{"label":"Issuer authentication","passed":false,"status":"not_checked","detail":"A zambo.dev receipt URL does not authenticate the issuer; no pinned signature or trusted issuer key was checked."},"signature":{"status":"not_checked","detail":"No Ed25519 signature or pinned signing key is supplied."},"schema":{"status":"not_checked","detail":"Schema conformance is left to the client using the linked hosted-profile schema."},"chain":{"status":"not_checked","detail":"This endpoint does not verify an append-only receipt chain."}}}