I was wondering if anyone has any advice on how to improve the reliability of an agent we’re testing for a customer. See context and detailed questions below: We suspect it may be an issue with the prompt: - Currently the prompt has 1 main workflow split into 4 sections in the prompt (authenticating the caller, performing the workflow variation #1 or #2, and giving closing confirmations) - which is about 15-20 steps in total. - We also need the agent to be able to be interrupted during the workflow at any point and answer questions. - We have 9 custom tools that the agent is using including answering FAQs What we’re trying to understand is: - what model are you using for the LLM? - is your agent able to reliably do what it’s supposed to with instructions in a single prompt? or do you end up having to create sub prompts / sub agents that handle the separate workflows of ordering vs reservations - do you allow your customers to give you any set of FAQs they have? is it just text dumped into one faq tool that calls another LLM?

Hi there, Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from 9:00 AM to 8:00 PM Pacific Standard Time (PST). We’ll get back to you as soon as possible during our normal business hours. If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly. Warm regards, Vapi Customer Support Team

To help you best: Could you clarify if your main challenge is with the agent handling interruptions (e.g., answering FAQs mid-workflow), or is it more about the agent following the main workflow steps reliably from start to finish? This will help me suggest the most effective prompt or workflow structure for your use case. Sources: - [Squads Overview](https://docs.vapi.ai/squads) - [Prompting Guide](https://docs.vapi.ai/prompting-guide) - [Multilingual Support Agent Example](https://docs.vapi.ai/assistants/examples/multilingual-agent)

Primarily handling interruptions and answering faqs mid workflow @Vapi Support Bot

To improve interruption handling and allow your agent to answer FAQs mid-workflow, configure the

stopSpeakingPlan

for fast, VAD-based interruption detection. Here’s a sample configuration:

json
"stopSpeakingPlan": {
  "numWords": 0,
  "voiceSeconds": 0.2,
  "backoffSeconds": 1
}

This setup lets the agent stop speaking as soon as the user starts talking, making it highly responsive to interruptions and FAQ requests during workflows. Adjust

voiceSeconds

as needed to balance sensitivity and avoid false triggers from background noise. See more: [Voice Pipeline Configuration](https://docs.vapi.ai/customization/voice-pipeline-configuration) Source: - [Voice Pipeline Configuration](https://docs.vapi.ai/customization/voice-pipeline-configuration)

It’s less about handling interruptions and more about calling right tool when FAQs come up throughout the call

Hi, could you please provide a call id where you experienced this issue? We would like to review the logs to identify the cause.