Arize's Aparna Dhinakaran on the AI engineer's new job: running factories of agents
AI Engineer · youtube · 2026-10-26
Aparna Dhinakaran of Arize AI redefines what an AI engineer does as the field shifts from writing features to running agent factories. The core job is building the loop:
- Using evals to review non-deterministic work, making telemetry something agents consume and act on.
- A walkthrough of Arize's always-on agent Signal: reads traces, remembers past issues, and opens PRs — covering triggers, sandboxes, and durable state.
- Discussion of what triggers an always-on agent, run-time context/sandbox/proxy architecture, what persists vs. gets torn down, durable agent design, model/harness agnosticism, and evaluating the evaluators.
- Advice to trace everything including coding agents, and close the gap between labs and businesses.
More from coding & agent
- How to get more ambitious with evals as models approach superhuman intelligence — shyamalanadkat · 2026-10-26
- GenAICode: open-source toolkit puts one API over Claude Code, Codex, Copilot, Cursor and Gemini CLI — Codeblix_Ltd · 2026-10-26
- Claude rebuilds a Gaussian-splatted garden scene in Blender with Geometry Nodes — CSProfKGD · 2026-10-26
- Vocs: fully local macOS dictation with whisper.cpp streaming, short chunks decoded 8x faster — zenitsu--DS · 2026-10-26
- Most MCP servers skip two of four tool safety hints, breaking confirmation heuristics — abhiramreddykalluru · 2026-10-26
- 50 agent runs, zero doc reads: five models pass tests but skip the documentation — ducha_aiki · 2026-10-26