### Answer --- This issue has been reported by other users experiencing similar behavior where the agent repeats the welcome message and doesn't transition to other nodes. [(1) ]() Here are some troubleshooting steps to try: 1. Check your node configuration - If you're using a Static Sentence in the Welcome Node, the agent will say a fixed sentence first, and if still inside the node, it will generate content dynamically based on that static sentence. [(2) ]() - Consider splitting the node if instructions are too complex, as this can improve consistency. [(3) ]() 2. Try changing the node model - If the instructions are concise but the agent struggles to follow them, try using a more capable LLM model for this node. 3. Review transition conditions - Ensure your transition conditions precisely match your intended triggers. Consider breaking down complex conditions into multiple simpler ones. 4. Check for Logic Split Node issues - If your flow includes a Logic Split Node immediately after the welcome node, this has been reported to cause "Failed to get LLM response" errors. One workaround is to replace the split node with a normal conversation node to test if that resolves the issue. [(4) ]() If the problem persists, you may want to share your agent ID with Retell support for further investigation, as similar issues have required backend fixes in the past. [(5) ]()

​ To learn more, see the sources I considered: [[1] Agent Stucks in Greet-Node (Conversational Flow)](https://discord.com/channels/1186424376300679209/1347905989286035549) [[2] Conversation Node](https://docs.retellai.com/build/conversation-flow/conversation-node) [[3] Debug guide](https://docs.retellai.com/build/conversation-flow/debug-guide) [[4] Failed to get LLM response in Logic Split Node](https://discord.com/channels/1186424376300679209/1423335592753631292) [[5] Conversation Flow agent potentially stay silent after function node](https://retell.discourse.group/t/conversation-flow-agent-potentially-stay-silent-after-function-node/135) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

Appreciate the feedback! Feel free to ask me again with additional guidance or context.

### Answer --- I don't have real-time visibility into current network issues or outages affecting Retell AI's LLM services. The sources I have access to don't contain information about ongoing service disruptions. However, there have been past reports of transient LLM latency issues that were sometimes attributed to server load on Retell's side or OpenAI's side. [(1) ]() Since you're using GPT-4.1 and experiencing "Failed to get LLM response" errors, here are a couple of things to consider: - **Model capability check**: If your prompt structure is complex, you might try switching to a different model tier to see if the issue persists. [(2) ]() - **Prompt structure**: Check if your prompt structure is too complex and consider breaking down complex tasks into clear, sequential steps. For real-time service status or to report this specific issue, I'd recommend reaching out to Retell support directly with your agent ID so they can investigate on their backend. Check out these potentially useful sources: [Debug wrong response]() , [Contact Sales]()

​ To learn more, see the sources I considered: [[1] High LLM latency with gpt-4o-mini](https://discord.com/channels/1186424376300679209/1270503904173494375) [[2] Debug wrong response](https://docs.retellai.com/reliability/wrong-response) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.