# Session Traces and Cost Controls Help Diagnose AI Agent Failures

DevFeed: [Session Traces and Cost Controls Help Diagnose AI Agent Failures](<https://devfeed.tech/articles/session-traces-and-cost-controls-help-diagnose-ai-agent-failures-8456.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/09/observability-ai-agents/>)

Author: Mark Silvester

Published: 2026-09-11T08:14:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [debugging](<https://devfeed.tech/topics/debugging.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [cost](<https://devfeed.tech/tags/cost.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [devops](<https://devfeed.tech/tags/devops.md>), [llm](<https://devfeed.tech/tags/llm.md>), [loops](<https://devfeed.tech/tags/loops.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [news](<https://devfeed.tech/tags/news.md>), [observability](<https://devfeed.tech/tags/observability.md>), [observability-ai-agents](<https://devfeed.tech/tags/observability-ai-agents.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [traces](<https://devfeed.tech/tags/traces.md>)

## AI overview

The article describes using nested session traces, execution metrics, and cost limits to investigate and contain AI agent failures such as repeated tool calls and runaway spending.

## Source excerpt

Session traces and cost controls are emerging as key observability techniques for diagnosing AI agent failures, helping teams spot tool-call loops and runaway spend while preserving enough execution context for post-incident debugging. By Mark Silvester