{"company":{"id":"arize","name":"Arize AI","homepage":"https://arize.com/"},"generated_at":"2026-10-19T11:58:24.008Z","sources":[{"id":"arize:feed","label":"Arize AI blog","kind":"Announcement","url":"https://arize.com/blog/feed/","last_checked":"2026-10-19T04:55:43.888Z","last_success":"2026-10-19T04:55:43.888Z","error":null,"state":"ok"}],"social":[],"daily":[{"day":"2026-10-19","company":"arize","material":false,"item_ids":[],"latest_change_at":0,"text":"No material verified update from Arize AI's official sources on 2026-10-19 (UTC). Covers Arize AI's official Arize AI blog. It does not cover social posts or independent reporting.","links":[],"generated_at":"2026-10-19T11:58:24.008Z"},{"day":"2026-10-18","company":"arize","material":false,"item_ids":[],"latest_change_at":0,"text":"No material verified update from Arize AI's official sources on 2026-10-18 (UTC). Covers Arize AI's official Arize AI blog. It does not cover social posts or independent reporting.","links":[],"generated_at":"2026-10-19T11:58:24.008Z"},{"day":"2026-10-17","company":"arize","material":false,"item_ids":[],"latest_change_at":0,"text":"No material verified update from Arize AI's official sources on 2026-10-17 (UTC). Covers Arize AI's official Arize AI blog. It does not cover social posts or independent reporting.","links":[],"generated_at":"2026-10-19T11:58:24.008Z"},{"day":"2026-10-16","company":"arize","material":false,"item_ids":[],"latest_change_at":0,"text":"No material verified update from Arize AI's official sources on 2026-10-16 (UTC). Covers Arize AI's official Arize AI blog. It does not cover social posts or independent reporting.","links":[],"generated_at":"2026-10-19T11:58:24.008Z"},{"day":"2026-10-15","company":"arize","material":true,"item_ids":["track:6be4ee7701ba338543b55893"],"latest_change_at":1792075978000,"text":"Arize AI published 1 official update on 2026-10-15 (UTC): AI agent permissions: Why agents don’t know what you’re allowed to do (Arize AI blog). Covers Arize AI's official Arize AI blog. It does not cover social posts or independent reporting.","links":[{"title":"AI agent permissions: Why agents don’t know what you’re allowed to do","url":"https://arize.com/blog/ai-agent-permissions/","source":"Arize AI blog"}],"generated_at":"2026-10-19T11:58:24.008Z"},{"day":"2026-10-14","company":"arize","material":false,"item_ids":[],"latest_change_at":0,"text":"No material verified update from Arize AI's official sources on 2026-10-14 (UTC). Covers Arize AI's official Arize AI blog. It does not cover social posts or independent reporting.","links":[],"generated_at":"2026-10-19T11:58:24.008Z"},{"day":"2026-10-13","company":"arize","material":true,"item_ids":["track:cd5932a181918da3e539537a","track:33de1ec43ea8c6fb25bfc1c8"],"latest_change_at":1791907215000,"text":"Arize AI published 2 official updates on 2026-10-13 (UTC): EU AI Act compliance for AI agents: a practical engineering guide (Arize AI blog); Does being rude to AI work? What 6 models revealed (Arize AI blog). Covers Arize AI's official Arize AI blog. It does not cover social posts or independent reporting.","links":[{"title":"EU AI Act compliance for AI agents: a practical engineering guide","url":"https://arize.com/blog/eu-ai-act-compliance-ai-agents/","source":"Arize AI blog"},{"title":"Does being rude to AI work? What 6 models revealed","url":"https://arize.com/blog/does-being-rude-to-ai-work/","source":"Arize AI blog"}],"generated_at":"2026-10-19T11:58:24.008Z"}],"items":[{"id":"track:6be4ee7701ba338543b55893","title":"AI agent permissions: Why agents don’t know what you’re allowed to do","url":"https://arize.com/blog/ai-agent-permissions/","summary":"AI agent permissions determine what an agent is allowed to do on someone’s behalf. As agents get more powerful, we’re running into a basic problem: a model can’t reliably verify those permissions just because someone claims to have them in…","source":"Arize AI blog","category":"announcement","published_at":"2026-10-15T14:52:58.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:cd5932a181918da3e539537a","title":"EU AI Act compliance for AI agents: a practical engineering guide","url":"https://arize.com/blog/eu-ai-act-compliance-ai-agents/","summary":"Learn how agent traces, human oversight, production evaluations, and log retention support EU AI Act compliance with a practical credit-assistant example. The post EU AI Act compliance for AI agents: a practical engineering guide appeared first on Arize AI .","source":"Arize AI blog","category":"announcement","published_at":"2026-10-13T16:00:15.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:33de1ec43ea8c6fb25bfc1c8","title":"Does being rude to AI work? What 6 models revealed","url":"https://arize.com/blog/does-being-rude-to-ai-work/","summary":"Does being rude to AI improve answers or lower costs? We tested six models to separate prompt tone from brevity instructions and examine what changes. The post Does being rude to AI work? What 6 models revealed appeared first on…","source":"Arize AI blog","category":"announcement","published_at":"2026-10-13T14:30:49.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:e7fff4fbc015e6112f6820c0","title":"Together AI integration: Evaluate open models and optimize evaluation costs in Arize AX","url":"https://arize.com/blog/together-ai-integration-arize-ax/","summary":"Evaluate open models with Together AI in Arize AX. Compare model performance, run LLM-as-a-Judge evaluations, and explore lower-cost alternatives. The post Together AI integration: Evaluate open models and optimize evaluation costs in Arize AX appeared first on Arize AI .","source":"Arize AI blog","category":"announcement","published_at":"2026-10-12T18:27:10.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:9d761febe47ad9aadf70dddf","title":"How to test agent tool descriptions with Harbor and Phoenix","url":"https://arize.com/blog/how-to-test-agent-tool-descriptions-with-harbor-and-phoenix/","summary":"Build a reproducible benchmark, compare tool use across agents, and test whether a description change reduces unnecessary work while preserving outcomes. The post How to test agent tool descriptions with Harbor and Phoenix appeared first on Arize AI .","source":"Arize AI blog","category":"announcement","published_at":"2026-10-12T14:30:47.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:384bbf0973cc17f0c2056813","title":"Alignment is a human-AI workflow: how Custom Views make agent review possible","url":"https://arize.com/blog/alignment-is-a-human-ai-workflow-custom-views/","summary":"Automated evals can score every agent session, but they do not automatically reflect what your team considers a good outcome. That takes human judgment. The post Alignment is a human-AI workflow: how Custom Views make agent review possible appeared first…","source":"Arize AI blog","category":"announcement","published_at":"2026-10-09T18:25:34.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:c7824dacc82bb0ae0baaedcb","title":"Cost Agent: find where your LLM and agent spend goes with your traces","url":"https://arize.com/blog/arize-ax-cost-agent/","summary":"AI costs don’t always scale predictably with traffic. A retry loop, oversized context window, or unnecessarily expensive model can make a small number of traces disproportionately expensive. The post Cost Agent: find where your LLM and agent spend goes with…","source":"Arize AI blog","category":"announcement","published_at":"2026-10-08T15:50:29.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:8616800b82a76d949758d5f7","title":"Decision model benchmark: Jev, Kev, Liquid d1, and more","url":"https://arize.com/blog/decision-model-benchmark/","summary":"On 15 September, TypeSafe released Jev, and within a few weeks about 10 companies had shipped something that works the same way. OpenAI, Liquid, Cloudflare, AWS and PostHog all launched one, and an open clone called Kev showed up on…","source":"Arize AI blog","category":"announcement","published_at":"2026-10-07T16:37:26.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:759332500b9bafc3e5585962","title":"What agent traces can tell you without an LLM judge","url":"https://arize.com/blog/agent-traces-without-llm-judge/","summary":"Some agent failures are already in the trace. tracelint proves them on Phoenix OpenInference spans and fails CI, without an LLM judge. The post What agent traces can tell you without an LLM judge appeared first on Arize AI .","source":"Arize AI blog","category":"announcement","published_at":"2026-10-06T14:00:07.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null},{"id":"track:7ec82e8942229282909cf1e0","title":"How we benchmark AI agents and tools with Harbor and Arize Phoenix","url":"https://arize.com/blog/ai-agent-benchmarking-harbor-arize-phoenix/","summary":"See how Arize uses Harbor and Phoenix to benchmark AI agents, MCP servers, skills, and CLIs in reproducible sandboxes, then inspect traces and annotations. The post How we benchmark AI agents and tools with Harbor and Arize Phoenix appeared first…","source":"Arize AI blog","category":"announcement","published_at":"2026-10-05T14:19:10.000Z","first_seen_at":"2026-10-16T19:35:52.805Z","same_as":null}],"guth_coverage":[],"limits":"Official sources listed in \"sources\" only. Social posts and independent reporting are not covered."}