I built this system for a locksmith company that needed a better way to handle incoming emergency calls and assign jobs to technicians automatically. Here’s what the system does: • AI answers incoming calls • Collects customer details (name, address, issue, phone number) • Creates a job record in the database • Sends the job to technicians one by one • Includes Accept / Reject buttons inside the email • Waits for a response • If ignored → automatically escalates to the next technician • Stops immediately once someone accepts The main challenge was building the loop logic in n8n so it doesn’t notify everyone at once, and making sure the workflow instantly stops once the job status changes to “accepted.” Result: Replaces manual dispatching, prevents double assignments, reduces missed calls, and ensures technicians are assigned faster without a human coordinating everything. I recorded a Loom walkthrough showing: – A live AI call test – The n8n workflow logic – How accept/reject works – How the escalation system is structured If anyone’s curious about the backend setup, here’s the full breakdown: https://youtu.be/fG83tKiWcgA Would love to hear how you’d improve the routing or escalation logic.

Hey everyone, I’m building a live AI phone receptionist and I’m facing an issue when the assistant has to repeat numbers back to the caller. Problems: • When a caller gives an 11-digit phone number → digits merge or sound unclear • When repeating prices like £1500 → pronunciation sounds distorted • Works fine sometimes, but inconsistent on real phone calls Stack: Vapi + Twilio + n8n + ElevenLabs (also tested Gemini/OpenAI) Tried already : – Increasing end-of-turn timeout (0.5 → 2s) – Changing voices/models/LLMs How do you normally solve this in production systems? Is it formatting, TTS settings, buffering, or another approach?

Hey everyone, I recently built an AI-powered lead qualification and routing system designed to automate how inbound leads are evaluated and distributed across a sales pipeline. Here’s what the system does: • Captures inbound leads (from Facebook Ads) via webhook • Normalizes and validates incoming data • Checks historical lead data to identify new vs. returning prospects • Uses AI to score intent and classify each lead • Logs AI decisions for transparency and auditability • Automatically routes leads to Sales, Nurture, or Discard • Updates HubSpot accordingly • Sends real-time Slack notifications for high-intent prospects How It Works Once a lead enters the system, it goes through a structured validation and enrichment layer before being passed into an AI decision engine. The AI evaluates intent and recommends the next best action. Based on that recommendation, the workflow automatically routes the lead to the appropriate pipeline while maintaining clean CRM data and logging all decisions. The architecture is modular and production-ready, meaning it can scale across different lead sources and CRM environments. Benefits • Eliminates manual lead qualification • Improves response time for high-intent leads • Keeps CRM clean and structured • Reduces sales team workload • Scales automatically as lead volume increases If anyone’s interested, here’s a complete overview of the workflow where I walk through the full system architecture: 👉 https://youtu.be/CknV7KcYVWA Happy to answer questions or discuss improvements.

A lot of people talk about “doing outbound consistently,” but what usually breaks isn’t effort — it’s friction. Recently, I built a LinkedIn outreach system to remove that friction completely. What the system does: - Scrapes targeted LinkedIn leads - Researches each profile - Writes a personalized connection message per lead - Sends the connection request - Automatically sends the 1st and 2nd follow-up What this removes from the process: - Searching and opening profiles - Copy-pasting profile data - Writing messages one by one - Manually remembering and sending follow-ups Realistic time impact: ~20 minutes saved per lead. At ~30 leads/week → ~10 hours saved every week. The bigger outcome: Outbound runs in the background. Messages stay personalized.Follow-ups never fall through .And consistency finally becomes boring (in a good way). If you’re curious and want to see the exact workflow or explore setting something similar up for yourself, feel free to DM me and we can walk through it on a quick call.

I’m building an AI voice agent in Vapi and I need a provider that can handle both: ✅ Inbound/Outbound calling (UK numbers) ✅ SMS (send + receive, ideally) ✅ Good reliability in the UK (deliverability + call quality) ✅ Reasonable pricing + easy setup I know Twilio is the common choice and looks cost-effective, but I’ve heard mixed feedback about reliability in the UK. For anyone shipping real client systems in the UK: Which provider has been the most reliable for you? - Twilio? - Vonage / Nexmo? - Telnyx? - MessageBird? - Sinch? - Anything else? If you’ve used it with Vapi specifically, I’d love to know: - call quality experience - SMS deliverability - pricing surprises - any setup gotchas Thanks in advance — want to pick something stable before I roll this out to clients.