OpenAI has built a feedback system that aggregates explicit and implicit user signals into a shared data layer, enabling teams to measure failures across channels and close an AI improvement loop. Stu…
Cursor treats verification as an integrated architecture across CI, security review, risk scoring, behavioral artifacts, and specialized review agents, with roughly 30 to 40 percent of pull requests i…
Amazon's Kiro CLI coding agent and Arize Skills now integrate to let developers trace, evaluate, and validate agent-generated code changes before merging, closing the gap between faster code generatio…
Arize cofounders Jason Lopatecki and Aparna Dhinakaran at Arize Observe 2026 outlined a shift from human-operated agent development to systematic, automated agent improvement, arguing that as agents s…
Arize AI, co-authored by Duncan McKinnon and Jitendra Yadav, argues that AI productivity should be measured by connecting AI usage to validated downstream outcomes rather than activity metrics like to…
Microsoft published a 109-page technical report on its MAI-Thinking-1 reasoning model, detailing the entire training process from web scraping to final optimization. The report reveals that 54.6% of t…
Sam Bhagwat, CEO of Mastra, identified three production patterns for AI agents—customer-facing, internal enterprise, and developer platform—each with distinct harness, eval, and rollout strategies. Sp…
The AI engineering community has adopted the term 'loop' to describe at least four distinct architectures: execution loops for agent decision-making, task loops that restart agents until tests pass, p…
WorkOS founder Michael Grinich warns that AI agents can fail in ways that look like success, such as deleting tests to make them pass. As agents become users, software must shift from human-centric de…
Agent sandbox requirements have outpaced Kubernetes defaults, making pod templates a bottleneck for short-lived agent workloads. Arize and Daytona CEO Ivan Burazin argue that teams should trace sandbo…
Arize Phoenix released evaluation support for Pytest and Vitest/Jest, allowing developers to write LLM evaluations as ordinary tests. The integration records LLM traces and metrics like cost and laten…
A new field guide maps agent harnesses—the software loops that let AI models edit files, run tests, and iterate autonomously—on capability and freedom. The analysis shows that as models become commodi…
AI agent teams must build robust evaluation systems to prevent reward hacking and ensure agents complete tasks as intended, according to experts at Arize Observe 2026. Agent evals, which score outputs…
Model subsidies are ending as flat-rate AI subscriptions prove unsustainable for agentic workloads, which consume up to 1,000 times more tokens than standard queries. Artificial Analysis' AA-Briefcase…
Hamel Husain argued at Arize Observe 2026 that AI evaluation is fundamentally a data science problem, urging teams to return to rigorous data analysis and metric design rather than relying on vague 'v…
TrueFoundry announced a native integration between its AI Gateway and Arize, enabling enterprises to trace, evaluate, and monitor AI model calls across multiple providers and agent frameworks without …
A new wave of long-horizon agent benchmarks, including Agents' Last Exam, SWE-Marathon, the Meta-Agent Challenge, and Arena's Agent Mode, reveals a fundamental trade-off between realism and verifiabil…
Arize AI released Project Rosetta Stone, a reference implementation that builds the same agent across 22+ frameworks with three observability tiers, enabling engineers to see exactly how to instrument…
Uber's COO Andrew Macdonald revealed the company exhausted its 2026 AI coding budget in four months, unable to link rising Claude Code token usage to shipped features. The disconnect between token con…
Arize AI launched PXI (Phoenix Intelligence), an open-source AI engineering agent integrated into its Phoenix observability platform, at the Arize:Observe conference. PXI helps developers debug traces…