Agent observability

Concept

Collecting traces, metrics, evaluations and audit data of AI agents to see what they did, why, and at what cost.

Title graphic: Agent observability (Concept)

Type	Concept
Also known as	AI observability, Agenten-Observability

Sessions on this topic (6)

Your Copilot Studio Agent Works. Is It Ready for Production? · Mikko Koskinen · M365Con 2027
Master the 4 Levels of Agent Management to Unlock Enterprise-Grade Confidence in AI Agents · Griffin Lickfeldt · M365Con 2027
Your AI Agent Has a Production Problem. Architecture Patterns for Reliable Agents · Tiago Costa · M365Con 2027
Your Copilot Studio Agent Works. Is It Ready for Production? · Mikko Koskinen · M365Con 2027
Master the 4 Levels of Agent Management to Unlock Enterprise-Grade Confidence in AI Agents · Griffin Lickfeldt · M365Con 2027
Your AI Agent Has a Production Problem. Architecture Patterns for Reliable Agents · Tiago Costa · M365Con 2027

Glossary

Relationship map of Agent observability: linked topics

Related to

Microsoft Agent 365 · Product
AI governance · Concept
Audit logs · Concept
FinOps · Concept
Microsoft Foundry · Product
AI agent · Concept
Griffin Lickfeldt · Person
Mikko Koskinen · Person
Tiago Costa · Person

Community wiki

Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.

Experts and companies for this topic

Nobody has listed this topic yet. Add it to your profile.