Author
Sally-Ann DeLucia
Recent posts
-
Agent EvaluationHow to build a remote evaluator in Arize AX with Jev
Evaluate agent responses with Jev and Arize AX. Build a FastAPI remote evaluator, return labels and scores, and choose a threshold for your data. Sally-Ann DeLucia Jim Bennett September 24, 2026 12 min read -
Agent EngineeringThe future of AI operations teams
Your agents produce more traces and eval results than your team can read. SallyAnn DeLucia on how engineering teams are restructuring around managed agents, and which work stays… Jim Bennett Sally-Ann DeLucia September 16, 2026 8 min read -
Agent ObservabilityFrom Signal to PR: What if your agents got better every time they failed?
Signal, a managed agent built into Arize AX, continuously reviews production traces, surfaces ranked issues with evidence and proposed fixes, and — with Managed Agents — can carry… Chris Cooning Sally-Ann DeLucia Jason Lopatecki Aparna Dhinakaran July 29, 2026 5 min read -
Agent EngineeringHow we use Alyx to build Alyx: How to build an AI agent feedback loop
How Arize uses Alyx to debug Alyx: searching dense traces, aggregating failures, triaging dogfooding issues, and closing the AI engineering feedback loop. Chris Cooning Sally-Ann DeLucia Priyan Jindal Jack Zhou May 13, 2026 10 min read -
Agent EvaluationHow Arize tests AI agents with traces, evals, and CI/CD
Lessons from building and shipping Alyx, our AI agent Sally-Ann DeLucia Chris Cooning Priyan Jindal Jack Zhou May 5, 2026 9 min read -
Agent EngineeringManaging Memory in AI Agents: Beyond the Context Window
This is part two of our deep dive series on how we built Alyx 2.0, our AI engineering agent. Watch us discuss it above, or keep reading for… Chris Cooning Priyan Jindal Sally-Ann DeLucia Jack Zhou March 19, 2026 10 min read -
Agent EngineeringHow to Build Planning Into Your Agent (The Architecture That Actually Works)
2025 was supposed to be the year of agents. And for the most part, it wasn’t. The industry was full of hype, demos looked incredible, but when you… Chris Cooning Priyan Jindal Sally-Ann DeLucia Jack Zhou March 5, 2026 11 min read -
Agent EngineeringAlyx 2.0: The AI Agent That Actually Plans
Two years ago, we started building Alyx with GPT-3.5, a vision, and honestly, no clear path forward. Agents were a buzzword. The models were rough. Tool calling was… Sally-Ann DeLucia Jack Zhou Chris Cooning Aman Khan February 24, 2026 6 min read -
Agent EngineeringMeet Alyx: Arize’s Evolving AI Agent
We’re excited to introduce Alyx, the next evolution in Arize’s intelligent assistant. You might remember our first iteration — Copilot — launched last year as a set of… Sally-Ann DeLucia July 1, 2025 4 min read -
AI ObservabilityNew in Arize: Realtime Trace Ingestion, Prompt Playground Upgrades & More
In May, we expanded access to realtime trace ingestion across all Arize AX tiers, making it easier than ever to monitor LLM performance live. We also rolled out… Sally-Ann DeLucia June 4, 2025 2 min read
Don’t ship vibes.
Arize gives AI teams observability and evals to understand and improve agent performance.
