LangGraph's Routing Is LLM-Guessing. I Wrote 50 Lines of Code to Make It Deterministic.

A developer created a deterministic routing system for LangGraph agents, replacing LLM-based routing with a 50-line rule-matching module. The solution uses a YAML-defined route table with keywords and regex patterns, ensuring the same input always maps to the same domain. A feedback cache automatically promotes frequently corrected routes to permanent rules, eliminating prompt engineering and guesswork.

Every time your LangGraph agent sees "check nginx logs", it might call a different tool. That's not an exaggeration. LangGraph's routing is driven by an LLM prompt — and prompts aren't reproducible. Same input, different day, different LLM mood, different tool selected. I spent months debugging this. Every wrong route meant tweaking a prompt, hoping the next call would be better. It never was. So I wrote something different. LangGraph is great at orchestrating multi-step agent workflows. But the first step — "what tool should I use?" — is a black box. You define a prompt, the LLM decides. If it chooses wrong, you can't debug it. You can only guess: was the prompt not specific enough? Too specific? Wrong example? This is the routing problem : given user input, which domain or tool should handle it? LangGraph leaves this to the LLM. I think it shouldn't. python from decide router import RouteTable rt = RouteTable "routes.yaml" rule, = rt.match "check nginx error logs" rule.domain → "monitoring" — always, every time No LLM call. No prompt. Just a YAML file and 50 lines of matching logic. The YAML defines domains with keywords and regex patterns: domains: monitoring: priority: 100 keywords: log, error, nginx, monitor, health, status patterns: " check|look . log|status|error " coding: priority: 100 keywords: code, script, deploy, write human: priority: 100 keywords: delete production, restart cluster require confirm: true Plug it into LangGraph as a node: python from langgraph.graph import Graph from decide router import RouteTable rt = RouteTable "routes.yaml" def routing node state : rule, = rt.match state "input" state "domain" = rule.domain if rule else "unknown" return state graph = Graph graph.add node "decide route", routing node graph.set entry point "decide route" Your LangGraph agent now routes with rules , not guesses. Same input → same domain. Every time. The best part wasn't planned — it emerged from using it. I noticed I kept correcting wrong routes. "That's monitoring, not coding." Every correction was a signal. So I added a feedback cache: User corrects once → remembers immediately rt.record feedback "check nginx errors", "monitoring" Same correction 3 times → becomes a permanent routing rule at priority 70. Rules not used in 30 days auto-delete. The system gets smarter with every correction. No fine-tuning. No prompt engineering. The core module is one file, 200 lines of Python. Read the whole thing in 5 minutes. pip install decide-router Or browse the code: github.com/chex0210-crypto/decide-router https://github.com/chex0210-crypto/decide-router I built this because I was tired of guessing why my agent picked the wrong tool. If you've had the same frustration, star the repo — it helps other people find it.