# Kelet: Building a durable workflow to diagnose AI agent quality failures

DevFeed: [Kelet: Building a durable workflow to diagnose AI agent quality failures](<https://devfeed.tech/articles/we-built-a-durable-agent-that-debugs-durable-agents-36096.md>)

Original publisher: [Read original article](<https://temporal.io/blog/we-built-a-durable-agent-debugs-durable-agents>)

Author: Almog Baku

Published: 2026-06-18T00:00:00Z

Content type: article

Language: en

Sources: [Temporal Blog](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-quality](<https://devfeed.tech/tags/ai-quality.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [community](<https://devfeed.tech/tags/community.md>), [don-t](<https://devfeed.tech/tags/don-t.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [traces](<https://devfeed.tech/tags/traces.md>)

## AI overview

This article explains how Kelet diagnoses recurring quality failures in production AI agents by processing sessions, accumulating hypotheses, and reasoning across many occurrences. It describes why durable workflows are needed instead of a single agent loop or LLM call.

## Source excerpt

Almog Baku, co-founder and CEO of Kelet AI built an AI that diagnoses failing AI agents in production. Here's how he did it and why it needed durable workflows.