At Arize:Observe 2026, Uber senior AI product manager Aayush Agrawal said the hardest part of AI agent evaluation is not tooling but designing defaults, ownership models, and feedback loops that make …
Arize AI, the AI observability platform co-founded by Jason Lopatecki and Aparna Dhinakaran, announced a definitive agreement to be acquired by Dynatrace, a software intelligence company, to accelerat…
Arize head of developer relations Laurie Voss said that AI agent reliability depends on both guardrails and evals, which solve different engineering problems, after a live demo where a voice agent spo…
CVS Health teams moved a four-week feature from idea to production in roughly a day and a half and completed a legacy rewrite in one month after estimating six to nine months, according to Matt Turner…
CrewAI launched Crew Studio, an Automated Agent Builder with native Arize AX tracing and evaluation integration, enabling teams to send traces from the first run without custom instrumentation. The in…
Arize AI and Atlan report that enterprises running over 100 million AI evaluations monthly still face agent failures because model choice alone cannot ensure reliability, with context and harness engi…
Arize AX, the AI observability platform from Arize AI, now natively supports OpenTelemetry GenAI semantic conventions, enabling teams to send gen_ai.* telemetry directly over OTLP without custom proce…
Arize AI's analysis warns that the EU AI Act's transition period under Article 111 may not cover significantly modified AI agents, urging product and engineering teams to operationalize Responsible AI…
Anthropic reported that a Fable 5 orchestrator directing Sonnet 5 workers retained 96% of an all-Fable team's score on BrowseComp at 46% of the cost, signaling a shift in multi-agent economics. The or…
AI agent observability requires a reasoning layer that reconstructs intent and causality, not just traces, according to Nate Slater, Startup SA Leader at AWS, speaking at Arize Observe 2026. Slater sa…
Arize AI has launched Signal, a managed agent built into Arize AX that automatically reviews production traces on a recurring schedule, identifies recurring failure patterns, and turns them into prior…
Hamel Husain, a prominent AI engineer, argues that most AI evaluations fail because teams treat weak outputs as model failures when the real problem is product design, not the model itself. In the sec…
Arize AI launched Signal, a managed agent built into its Arize AX platform that continuously reviews production traces, identifies recurring failure patterns, groups them into ranked issues with root-…
An agent skill reduced average latency by 56%, token usage by 27%, and estimated cost by 44%, but also decreased answer completeness. The regression was detected only after tracing both versions in Ar…
Anthropic technical staff member Marius Buleandra reported that a newer AI model appeared to beat its predecessor by nine points on an AI data analyst eval, but the improvement vanished after he fixed…
Anthropic technical staff member Marius Buleandra warns that AI agent evaluations can produce misleading results, citing a case where a newer model appeared to beat its predecessor by nine points on a…
Booking.com relies on Arize AI for observability across its ecosystem of traditional ML models and generative AI agents, including trip planning assistants, ranking systems, and fraud detection models…
A good AI agent skill is a compact package of procedural expertise that fixes a repeatable failure, loads only when relevant, and earns its place against a matched evaluation, according to three recen…
Arize and Fireworks tested 10 AI models on 40 real agent tasks across 2,400 runs, finding that the open-source model gpt-oss-120b had the lowest cost per successful task at $0.054 despite a 33% pass r…
A new guide breaks down evaluation alignment between human experts and LLM judges into three measurable questions: human reliability on the rubric, LLM-human agreement relative to human-human agreemen…