Building issuegraph: a LangGraph triage agent, with the evals to prove it works
I build applied AI in the open, from multi-agent orchestration to retrieval. issuegraph puts LangGraph through the same bar: a GitHub issue triage agent as a state machine, with conditional routing, a bounded quality-guard loop, human-in-the-loop interrupts over Redis checkpoints, and a LangSmith eval suite that checks whether the classifier's confidence is honest. This post walks the graph architecture, the interrupt-and-resume plumbing, the one bug that taught me the most, and the calibration math.
- ai
- agents
- langgraph
- langchain
- langsmith
- evals
- open-source
- applied-ai