--- title: "How Kelet AI built a durable agent that debugs durable agents." url: https://daily.dev/posts/how-kelet-ai-built-a-durable-agent-that-debugs-durable-agents--ft13scevm source_url: https://temporal.io/blog/we-built-a-durable-agent-debugs-durable-agents type: article source: "Temporal" published: 2026-08-06T10:37:25.983Z updated: 2026-08-06T10:39:52.456Z tags: ["llm", "ai-agents", "observability"] reading_time: 7 upvotes: 1 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How Kelet AI built a durable agent that debugs durable agents. **[Temporal](https://daily.dev/sources/temporal)** · 7 min read · 1 upvotes · 0 comments ## Summary Kelet AI built a production system that continuously diagnoses quality failures in AI agents by analyzing patterns across thousands of sessions — not individual traces. The core insight is that AI failures are fuzzy clusters that only emerge across many sessions, requiring multi-stage pipeline infrastructure rather than a simple agent loop. Built on Temporal, the system uses a four-level Workflow hierarchy: Session Workflows with debounce windows, parallel Signal Workflows for enrichment, an Agent Aggregation Workflow for cross-session hypothesis collection, and an Investigate Issue Workflow for root-cause clustering and prompt patch generation. Key Temporal primitives used include long-running state, durable execution, event-driven Signals, wait_condition, and continue_as_new. The system monitors itself in production via a Temporal plugin that propagates session context across Workers and Activities using OTel headers, with an infinite-loop guard to prevent self-monitoring from re-ingesting its own diagnostic sessions. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Sherlocks AI uses Temporal to orchestrate AI agents for incident resolution](https://daily.dev/posts/how-sherlocks-ai-uses-temporal-to-orchestrate-ai-agents-for-incident-resolution-phsthx9x8) · Temporal · 1 upvotes · 0 comments - [Building Reliable Production AI with Durable Workflows](https://daily.dev/posts/building-reliable-production-ai-with-durable-workflows-8k7gdooen) · Salesforce Engineering · 2 upvotes · 1 comments - [The hero’s journey to AI durability with Temporal](https://daily.dev/posts/the-hero-s-journey-to-ai-durability-with-temporal-dpw0q6hol) · Temporal · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#observability](https://daily.dev/tags/observability) [View this post on daily.dev](https://daily.dev/posts/how-kelet-ai-built-a-durable-agent-that-debugs-durable-agents--ft13scevm)