---
title: "Evaluating and optimizing AI agents: from observability to continuous improvement"
category: "talks"
date: "2026-07-01"
time: "1:30pm-1:50pm"
track: "Track M"
room: "Track M"
speakers: ["Chang Liu"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Track M"
scheduleRoom: "Track M"
scheduleLabels: ["Track M", "Track M", "sponsor", "confirmed"]
---
# Evaluating and optimizing AI agents: from observability to continuous improvement

## Conference Context
- Date/time: 2026-07-01 · 1:30pm-1:50pm
- Track/room: Track M · Track M
- Speaker(s): Chang Liu
- Session type/status: sponsor · confirmed

- Track: Track M
- Room: Track M
- Session type: sponsor
- Status: confirmed

## Session Description
AI agents don’t behave like traditional systems. Learn how to evaluate outputs, trace behavior, and apply a continuous loop to improve performance across prompts, tools, and models. Using signals grounded in real-world context via Foundry IQ, see how evaluation, tracing, and optimization come together to turn production usage into measurable improvements over time.

## Media Evidence
No related AI Engineer channel video found yet.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
No linked video, transcript, or slide source has been attached yet.

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

## People
- [[chang-liu]]

## Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.

## Synthesis
### Synthesized Breakdown
# Evaluating and optimizing AI agents: from observability to continuous improvement ## Conference Context - Date/time: 2026-07-01 · 1:30pm-1:50pm - Track/room: Track M · Track M - Speaker(s): Chang Liu - Session type/status: sponsor · confirmed - Track: Track M - Room: Track M - Session type: sponsor - Status: confirmed ## Session Description AI agents don’t behave like traditional systems. Learn how to evaluate outputs, trace behavior, and apply a continuous loop to improve performance across prompts, tools, and models. Using signals grounded in real-world context via Foundry IQ, see how evaluation, tracing, and optimization come together to turn production usage into measurable improvements over time. ## Media Evidence No related AI Engineer channel video found yet.

### Speaker And Company Context
- [[chang-liu|Chang Liu]] — Senior Product Manager at [[microsoft|Microsoft]].

### Topics Covered
- Topic links are pending transcript-backed classification.

### Derived Links And Source Material

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.