**We replaced our 223-node agent graph with a single open-source LLM**

> See why we replaced our node agent graph with a single open-source LLM to improve Netic&\#x27;s AI voice capabilities Skip to main content Product Convert Never miss a lead, never miss a dollar. Cultivate Campaigns that run themselves. Empower Empower strategic decisions with data. Evaluate Intelligent call scoring for your call center. Expand (soon) Industries Home Services Pest Control Roofing Consumer Health Veterinary Careers Roles Netician Stories Company Customers Resources Events Press Engineering Book a demo We replaced our 223-node agent graph with a single open-source LLM Aug 20, 2026 • Netic Ajay Arora When Netic initially began exploring new voice agent architectures six months ago, we tested a wide variety of complex harnesses, from graph approaches to planner sub-agents to swarms and codifying conversational flows. None of these solved the main problems with voice agents today: they take too long to respond, they loop, they deflect instead of answering, and they miss things a human would instantly catch. With the release of flagship models like Kimi K2.6 and GLM 5.2, we’ve seen for the first time that open-source LLMs can handle 100s of operating procedures concurrently in context while adjusting on the fly to the nonlinear nature of human conversations. Today, Netic’s agents book at over 15 points higher on containment and appointment booking than they did just three months ago. Time to first token has halved to under 500ms. This post explains the guiding principles behind our decision to switch to a single LLM architecture and how we orchestrate our voice agents to achieve over $500M in autonomous job bookings for our customers. A brief history Netic started encoding Standard Operating Procedures (SOPs) as a graph in 2024. Every step in a procedure became a node, with edges gated by conditions. Some were boolean checks over variables extracted from the caller&\#x27;s speech. Others were natural-language conditions evaluated turn by turn. Existing members, after-hours requests, or any other category got its own branch. In an era when LLMs frequently hallucinated instructions, writing procedures in code let us out-perform competing vendors on reliability. As we grew, the complexity and volume of procedures we supported began to grow too. Single if-else conditions became if-elif-elif-elif-else chains, and edge conditions stopped fitting in one readable sentence. Under vague, real-world caller speech, the agent started choosing wrong branches, so we added dedicated classifiers: intent classifiers, ownership classifiers, trade classifiers, etc. These first lived on our backend behind tool calls, but as the product matured, we built them into the orchestration layer as classifier nodes to remove network hops. The conditions kept misfiring on real speech anyway. This example of a caller trying to buy a full system replacement (a high revenue job) shows where it veered off-path. Transcript Customer New furnace and new air conditioning. Agent Just so I understand, are you looking for an estimate to install a new furnace and air conditioner, or do you need service on your current systems? Customer I need financing for… oh. mention of "financing" → escalation edge Agent Since it's after hours, I'll need to leave a message for a team member to call you back about financing and your new furnace and air conditioner. Customer We need this as soon as possible. I have five kids and a baby. Agent I understand, that sounds stressful with little ones at home. Since it's after hours, I do need to leave a message for our team… The fix was a band-aid commit: “stop escalating when financing is mentioned on new-system calls." As models improved, we kept building pr...

**来源信息**
- **来源**:Hacker News:AI 热帖
- **分类**:ai-products
- **发布时间**:2026-08-21 07:17(北京时间)
- **原文**:[打开原文](https://www.netic.ai/replacing-node-agent-graph-with-open-source-llm)