-
Agent ObservabilityIs the cheap model good enough? How to test a new model in your agent
A paper called GVS5H claims a cheap model in a manager/worker loop closes the gap to frontier models. I tested that against Opus 5.5 in my own agent,… Jim Bennett November 5, 2026 21 min read -
Agent ObservabilityI put a ghost in Claude Code. Then I evaluated it.
I built a Halloween Claude Code mod that grades each turn as a treat or a trick and blocks dangerous commands, then traced and evaluated it with Arize… Jim Bennett October 27, 2026 17 min read -
Agent ObservabilityA web page talked our agent into leaking a stranger’s data. Here’s how we caught it.
A web page told our support agent to look up a different customer, and the agent complied on 28 of 100 runs. Here's how we found the leak… Nancy Chauhan October 26, 2026 15 min read -
Agent ObservabilityEU AI Act compliance for AI agents: a practical engineering guide
Learn how agent traces, human oversight, production evaluations, and log retention support EU AI Act compliance with a practical credit-assistant example. Jim Bennett October 13, 2026 15 min read -
Agent ObservabilityAlignment is a human-AI workflow: how Custom Views make agent review possible
Automated evals can score every agent session, but they do not automatically reflect what your team considers a good outcome. That takes human judgment. Dheeraj Bandaru October 9, 2026 7 min read -
Agent ObservabilityCost Agent: find where your LLM and agent spend goes with your traces
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. Fuad Ali October 8, 2026 3 min read -
Agent ObservabilityNVIDIA proposes an AI agent kill switch in silicon after a year of sandbox escapes
This year agents at OpenAI, Anthropic, and Google escaped environments meant to contain them. What decided severity was time-to-detect and time-to-kill, from 12 minutes to seven months. NVIDIA's… Jim Bennett September 30, 2026 13 min read -
Agent ObservabilityBuilding production-ready AI agents with Atlas Agent Engine and Arize AX
Agents built and deployed on MongoDB’s Atlas Agent Engine can export OpenTelemetry traces to Arize AX, where teams can inspect each run, evaluate both the outcome and execution… Richard Young Ryan Berg September 30, 2026 6 min read -
Agent ObservabilityArize AX in September 2026: first-class sessions, Agent-as-a-Judge, and vision evals
Sessions are now a first-class unit of work in Arize AX. Annotate a whole conversation, queue it for review, and ask Alyx to filter for it — plus… Fuad Ali September 22, 2026 5 min read -
Agent ObservabilityHow to find and debug agent failures your evals are missing
Evals measure failures you know how to name. Arize Signal continuously reviews production traces to find recurring trajectory failures you do not, then turns them into evidence for… Aaron Winston September 17, 2026 13 min read -
Agent ObservabilityHow Coinbase Wallet built an agent-first product development lifecycle
By redesigning planning, validation, and risk review around AI agents, Coinbase Wallet dramatically shortened the path from product idea to working software. Sara Verdi September 2, 2026 7 min read -
Agent ObservabilityAgent cost management is about more than the model
Every LLM call your application makes costs money, and agentic applications make a lot of LLM calls. Arize AX now ships a Cost Agent that reads traces, ranks… Laurie Voss September 1, 2026 8 min read -
Agent ObservabilityHow Signal found two hidden retry loops in our production agent Alyx
We ran Signal on Alyx, the AI engineering agent built into Arize AX. It surfaced a duplicate task-state loop and a 43-call dataset retry that appeared as valid… Nancy Chauhan August 27, 2026 8 min read -
Agent ObservabilityA skill is just an agent. So measure your changes.
A skill is just another AI agent: a prompt plus a harness that runs it. That means you can trace it, eval it, and prove a change made… Jim Bennett August 24, 2026 10 min read -
Agent ObservabilityHow Uber evaluates AI agents at production scale
A background comment about pizza exposed a failure that Uber’s offline evaluations had missed. The incident helped reveal what production AI agent evaluation actually requires: automatic tracing, living… Sara Verdi August 14, 2026 14 min read
Don’t ship vibes.
Arize gives AI teams observability and evals to understand and improve agent performance.