What started as a simple experiment has turned into 7 different AI call assistants, with another one currently in development. Some of the capabilities I've implemented so far: • Inbound call handling• Outbound calling workflows • Lead qualification• Appointment scheduling • Rescheduling and cancellations • SMS confirmations and follow-ups • Reminder calls before meetings • CRM updates and record management • Call transfers when needed • Multi-step business workflows The most interesting challenge wasn't getting the AI to talk. It was getting it to remember. One of the assistants can remember previous conversations across multiple calls, retrieve historical context, and continue the conversation naturally instead of treating every call like it's the first interaction. Building these systems taught me that the hard part isn't the voice model itself—it's the orchestration behind the scenes. Memory, workflows, CRM integration, scheduling logic, error handling, and all the small edge cases end up being where most of the work happens. Still a lot to improve, but it's been fascinating seeing how far AI voice technology has come in such a short time. Curious what everyone else is building in the voice AI space right now.

Recently worked on an AI system for a music industry website redesign. There were two parts to it: 1. A public-facing AI chat widget for general queries + lead capture 2. A private, full-screen AI assistant inside the client portal. The second one was more interesting. The client didn’t just want “AI support” — they were concerned about users overusing it and burning unnecessary tokens. So instead of a typical chatbot, I designed a session-based interaction system: - Each user gets a 5-minute active window - At minute 4 → a warning is triggered (“1 minute left”) - At minute 5 → session ends + redirects to an external GPT - Then a 5-minute cooldown kicks in - After cooldown → user can start again It basically runs in a loop. What’s interesting is how this changes behavior: Users become more intentional with their questions instead of treating it like an endless chat. Also ended up optimizing one of their internal workflows in the process: A task that used to take ~6 hours manually is now done in under 10 minutes. No fancy theory here—just structuring AI usage in a way that actually makes sense operationally. Still experimenting with how far this “controlled AI interaction” approach can go.

Hey everyone 👋 I’ve been working on an automation system recently and wanted to share it here to get some genuine feedback. Most chat systems I’ve seen are good at replying — but once conversations continue, things start breaking: users return, details change, meetings get rescheduled, timezones create confusion, and follow-ups don’t happen properly. So I built something called TalkPilot. The goal wasn’t to create another chatbot, but a system that can actually manage conversations end to end. It can: • remember users and past conversations • update details naturally during chat • book, reschedule, or cancel meetings • handle everything in the user’s timezone • send reminders automatically • ask for feedback after meetings • handle no-shows with reschedule links I’ve shared a short overview video on LinkedIn showing how the system looks in action. 👉 Watch here: https://www.linkedin.com/posts/yash-maheshwari5_problem-most-businesses-rely-on-chat-systems-ugcPost-7418271469211865088-RRt9 This is just an overview — next I’ll be sharing how the whole system is built behind the scenes. Not selling anything here, just building and learning in public. Would genuinely love to hear your thoughts or suggestions 🙌

This is my first post here, so I wanted to share something I recently built and get your feedback. I just completed an end-to-end automation system using Jotform, Make, Salesforce, and GoHighLevel. What this system handles: - New lead intake from Jotform - Automatic Salesforce checks (existing applicant or new) - Household creation when a spouse is involved - Auto-attachment of Jotform PDFs to the correct applicant - Backend document uploads auto-attached to Salesforce - GoHighLevel handling follow-ups, SMS, emails, emails, and pipeline updates The main goal was to eliminate manual work, avoid duplicate records, and make follow-ups fully reliable. I’m sharing: - Workflow images (logic + scenarios) - LinkedIn post link: https://www.linkedin.com/posts/yash-maheshwari5_today-i-want-to-share-a-automation-system-activity-7414265293692153856-RQjb?utm_source=share&utm_medium=member_desktop&rcm=ACoAADVOdbgBS1rmSmlKuqAwaxmU8y3VEyx4HzU Would genuinely love feedback on: - System design - Logic flow - Anything you’d improve or simplify Appreciate being part of this community 🙌

Hi, I'm trying to send the record ID from Salesforce to Make.com based on a specific condition using a webhook. It’s almost working, but not always accurately. I’m using Salesforce Flow Builder for this. If you have experience with Salesforce, I’d really appreciate your help. Thanks!