{"slug": "show-hn-jylus-give-ai-systems-evidence-from-changing-data", "title": "Show HN:Jylus – give AI systems evidence from changing data.", "summary": "Jylus launched a Show HN developer API that ingests logs, OpenTelemetry, Docker events and telemetry and returns a proof-bound \"Context Pack\" with facts, timeline evidence, contradictions, freshness and proof IDs, reporting 75.130% Recall@10, 45.663% MRR@10 and 31.473% program accuracy with zero model calls on its TEMPO full live API cohort. The service offers a single-use trial that creates an isolated one-time tenant, compiles the result, blocks further access immediately and runs the tenant through a deletion lifecycle, with no account required. A sample /api/v1/analyze response shows edge-17 reporting 12.4 ms latency with an estimated token reduction of 76.33% (1,842 source tokens to 436 retained evidence tokens).", "body_md": "## Test better evidence.\n\nIngest evidence, generate a proof-bound Context Pack, then compare model input and answers on your workload.\n\nDeveloper workload access\n\nSend logs, OpenTelemetry, Docker events, telemetry or awkward JSON. Measure ingest, retrieval and proof-bound Context Packs with your own data.\n\nSend events, search retained history and test mixed structured, semantic and relationship queries.\n\nSingle-use trial\n\nNo account is required. Jylus creates an isolated one-time tenant, compiles the result, blocks further access immediately, and sends the tenant through the deletion lifecycle.\n\nThe response contains source-backed facts, proof IDs, conflicts, missing evidence and the deletion state.\n\nTest AI evidence\n\nUse your own current state, history and documents. Jylus returns a bounded Context Pack with facts, timeline evidence, contradictions, freshness and proof IDs.\n\n`/api/v1/analyze` with the question your model needs answered.\n75.130% Recall@10 · 45.663% MRR@10\n\n31.473% program accuracy · zero model calls\n\nTEMPO · FULL LIVE API COHORT\nThe complete test loop\n\nThe response keeps facts, temporal evidence, contradictions, missing evidence and proof IDs explicit. Efficiency values are measured from your own request.\n\n```\ncurl https://api.jylus.ai/api/v1/analyze \\\n  --request POST \\\n  --header \"Authorization: Bearer $JYLUS_READ_API_KEY\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n    \"source\": \"current\",\n    \"text\": \"What is the latest latency reported by edge-17?\",\n    \"vector\": {\n      \"text\": \"latest edge device response time\"\n    },\n    \"context\": {\n      \"mode\": \"decision\",\n      \"token_budget\": 2000,\n      \"max_facts\": 18,\n      \"max_timeline\": 12,\n      \"include_documents\": false\n    },\n    \"scan_limit\": 1000,\n    \"limit\": 24,\n    \"include_results\": false\n  }'\n{\n  \"success\": true,\n  \"complete\": true,\n  \"execution_mode\": \"native_current\",\n  \"context\": {\n    \"decision_context_id\": \"ctx_...\",\n    \"decision_readiness\": {\n      \"status\": \"ready\",\n      \"can_answer\": true\n    },\n    \"facts\": [\n      {\n        \"statement\": \"edge-17 reported 12.4 ms latency\",\n        \"proof_ids\": [\"evt_001\"]\n      }\n    ],\n    \"timeline\": [\n      { \"observed_at\": \"2026-08-21T08:00:00Z\", \"proof_ids\": [\"evt_001\"] }\n    ],\n    \"contradictions\": [],\n    \"missing_evidence\": [],\n    \"context_efficiency\": {\n      \"source_tokens_estimated\": 1842,\n      \"retained_evidence_tokens_estimated\": 436,\n      \"estimated_token_reduction_percent\": 76.33\n    },\n    \"proof\": { \"event_ids\": [\"evt_...\"], \"complete\": true }\n  }\n}\n```\n\nTest the data engine\n\n```\ncurl https://api.jylus.ai/api/v1/events \\\n  -H \"Authorization: Bearer $JYLUS_API_KEY\" \\\n  -H \"Idempotency-Key: try_evt_001\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"stream\": \"my-workload\",\n    \"events\": [{\n      \"id\": \"evt_001\",\n      \"type\": \"telemetry.sample\",\n      \"occurred_at\": \"2026-08-21T08:00:00Z\",\n      \"data\": { \"device\": \"edge-17\", \"latency_ms\": 12.4 }\n    }]\n  }'\n```\n\n", "url": "https://wpnews.pro/news/show-hn-jylus-give-ai-systems-evidence-from-changing-data", "canonical_source": "https://jylus.ai/try", "published_at": "2026-09-29 00:33:11+00:00", "updated_at": "2026-09-29 00:47:27.963248+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-tools", "developer-tools", "mlops", "ai-agents"], "entities": ["Jylus", "Show HN", "OpenTelemetry", "Docker", "TEMPO", "/api/v1/analyze", "/api/v1/events"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-jylus-give-ai-systems-evidence-from-changing-data", "markdown": "https://wpnews.pro/news/show-hn-jylus-give-ai-systems-evidence-from-changing-data.md", "text": "https://wpnews.pro/news/show-hn-jylus-give-ai-systems-evidence-from-changing-data.txt", "jsonld": "https://wpnews.pro/news/show-hn-jylus-give-ai-systems-evidence-from-changing-data.jsonld"}}