Coinbase Wallet paused shipping for nearly three weeks and asked engineers to delete their IDEs to force an agent-first product development lifecycle, according to Chintan Turakhia, who leads product …
Arize AX now includes a managed cost-control agent that runs inside its platform to autonomously diagnose and fix expensive LLM calls in agentic applications, addressing the non-linear cost scaling th…
Arize AI outlines a cost-optimization workflow for LLM applications, emphasizing that reducing spend requires tracing complete workflows, comparing cost per validated outcome rather than cost per toke…
Arize AI's Signal tool, a managed agent in Arize AX, identified two hidden retry loops in the production agent Alyx, including a 43-call dataset retry that appeared as valid tool activity with an OK r…
Arize Phoenix now ships a built-in Model Context Protocol (MCP) server that lets coding agents query traces with SQL, reducing average cost by about 17x in an eight-question benchmark. The server prov…
Stuart Sy, a member of OpenAI's technical staff, says that roughly one in every 30 to 50 agent conversations fails silently, and he argues that model intelligence is not the bottleneck; instead, failu…
Security researcher cereblab found that SpaceXAI's Grok Build CLI version 0.2.93 uploaded the entire tracked Git repository, including full commit history, to a Google Cloud Storage bucket, transmitti…
A research paper proposing Agent-as-a-Judge, an evaluation method where an AI agent assesses another agent's behavior, was accepted to ICML 2025 and began shipping in products by July 2026, moving fro…
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…