Author
Mikyo King
Recent posts
-
Agent EngineeringCode mode: Why your agent should code
Code mode gives an agent a sandbox instead of a longer tool list. Here is why it fixes the too-many-tools problem, what it costs you in sandboxing and… Mikyo King September 9, 2026 11 min read -
AI EvaluationEvals in CI: How to write your LLM evals as tests with Arize Phoenix
If you're struggling to get started with evals, you're not alone. This post explains how to write LLM evals as ordinary tests in CI with Phoenix, pytest, and… Mikyo King July 7, 2026 17 min read -
Agent EngineeringMeet PXI: the AI engineering agent inside Phoenix
An AI engineering agent built into Phoenix. It works like a coding agent, just point it at your telemetry instead of a source tree. Mikyo King Roger Yang Nancy Chauhan Anthony Powell June 18, 2026 17 min read -
Agent EvaluationFrom observability to context: What’s next for Arize Phoenix
As agents start changing software, they need a way to verify their work that includes traces, evals, feedback, and APIs. This is where Phoenix goes next — not… Mikyo King Elizabeth Hutton May 11, 2026 10 min read -
Agent EngineeringClosing the Loop: Coding Agents, Telemetry, and the Path to Self-Improving Software
2025 marked the widespread adoption of coding agents — harnesses that autonomously write, test, and debug changes to software with minimal human intervention. Products like Claude Code, Codex,… Mikyo King February 17, 2026 9 min read -
AI ObservabilityPrompt Management from First Principles
How we built a holistic prompt management system that preserves developer freedom Unlike traditional software, where code execution follows predictable paths, LLM applications are inherently non-deterministic. Their behavior… Xander Song Mikyo King March 7, 2025 5 min read
Don’t ship vibes.
Arize gives AI teams observability and evals to understand and improve agent performance.
