---
schema: 1
type: video
title: 'LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize'
description: >-
  Your agent called tool B before tool A, and B has a dependency on A. You did
  not catch it because nothing in your code audits agents. The telemetry does.
  Dat from Arize AI walks through what observability actually means when the
  system you are debugging is nondeterministic and the execution path changes
  with every run. The talk covers the five flavors of eval signal (LLM as judge,
  human feedback, golden datasets, deterministic checks, business metrics), what
  scope to run them at (single span, multispan, trajectory, session), and where
  this is heading. Arize Phoenix is open source, runs as a single container, no
  Kubernetes required. The enterprise product adds an AI layer called Alex that
  scans traces, surfaces high latency and errors, and creates evals
  automatically. The stated goal: automate you out of the observability loop
  entirely. Speaker info: - https://www.linkedin.com/in/datdarylngo/ -
  https://x.com/dat_attacked --- Watch along with the corrected transcript,
  summary, timestamps and resources on this talk's official AIE page:
  https://ai.engineer/talks/JsCCrBF7F1g-llm-observability-evaluation-experimentation-platform-dat-ngo-arize-ai
  Join our upcoming AI Engineer conferences (see https://ai.engineer landing
  page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs
  and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference
  returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS
  2026 in Sydney ---
canonical: 'https://liquidgold.cc/watch/JsCCrBF7F1g'
markdown: 'https://liquidgold.cc/watch/JsCCrBF7F1g.md'
llms: 'https://liquidgold.cc/watch/JsCCrBF7F1g/llms.txt'
parent: 'https://liquidgold.cc/channel/aidotengineer.md'
channel: aidotengineer
updated: '2026-10-24T09:39:52.006Z'
language: null
children: []
videoId: JsCCrBF7F1g
durationSeconds: 992
publishedAt: '2026-06-07T18:00:06.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 115
    endSeconds: 247
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=115'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 115
    endSeconds: 247
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=115'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 258
    endSeconds: 337
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=258'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 258
    endSeconds: 337
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=258'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 337
    endSeconds: 349
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=337'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 349
    endSeconds: 485
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=349'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 349
    endSeconds: 485
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=349'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 349
    endSeconds: 485
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=349'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 349
    endSeconds: 485
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=349'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 495
    endSeconds: 593
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=495'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 495
    endSeconds: 593
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=495'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 604
    endSeconds: 693
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=604'
    heldReason: rights
  - ordinal: 12
    text: null
    startSeconds: 604
    endSeconds: 693
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=604'
    heldReason: rights
  - ordinal: 13
    text: null
    startSeconds: 705
    endSeconds: 793
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=705'
    heldReason: rights
  - ordinal: 14
    text: null
    startSeconds: 705
    endSeconds: 793
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=705'
    heldReason: rights
  - ordinal: 15
    text: null
    startSeconds: 705
    endSeconds: 793
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=705'
    heldReason: rights
  - ordinal: 16
    text: null
    startSeconds: 804
    endSeconds: 893
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=804'
    heldReason: rights
  - ordinal: 17
    text: null
    startSeconds: 904
    endSeconds: 992
    watch: 'https://liquidgold.cc/watch/JsCCrBF7F1g?t=904'
    heldReason: rights
---


# LLM Observability, Evaluation, Experimentation Platform — Dat Ngo, Arize

Your agent called tool B before tool A, and B has a dependency on A. You did not catch it because nothing in your code audits agents. The telemetry does. Dat from Arize AI walks through what observability actually means when the system you are debugging is nondeterministic and the execution path changes with every run. The talk covers the five flavors of eval signal (LLM as judge, human feedback, golden datasets, deterministic checks, business metrics), what scope to run them at (single span, multispan, trajectory, session), and where this is heading. Arize Phoenix is open source, runs as a single container, no Kubernetes required. The enterprise product adds an AI layer called Alex that scans traces, surfaces high latency and errors, and creates evals automatically. The stated goal: automate you out of the observability loop entirely. Speaker info: - https://www.linkedin.com/in/datdarylngo/ - https://x.com/dat_attacked --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/JsCCrBF7F1g-llm-observability-evaluation-experimentation-platform-dat-ngo-arize-ai Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney ---

Canonical: https://liquidgold.cc/watch/JsCCrBF7F1g · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.
