After scoping 15+ custom voice agents, I realized most projects fail for the same reason: the scope is vague. Everyone jumps into “Let’s just build it,” but no one agrees on the systems, intents, or actions that actually define the project. Here’s the simple 3-pass checklist I now use to scope any AI voice agent cleanly: 1. Systems Write down every tool the agent will touch: CRM, calendar, voice platform, automation layer, SMS/email, external APIs, KB sources, phone routing, and any compliance checks. If it's not on this list, it’s not in the scope. 2. Intents Map all possible caller intentions from a single “Welcome” node: - New inquiry - Existing customer - Reschedule - Support request - Out-of-scope - Spam Each intent becomes its own branch you can design independently. 3. Actions For each intent, define two things: - Data: What fields must be collected? - System actions: What does the agent do in your stack? (create/update contact, check availability, book appointment, send SMS, tag lead, generate call report) Most scoping issues happen because one of these three passes was skipped. If you can’t visualize the full flow on one clean page, you're not ready to build yet. If you want the exact guide I use to scope any AI voice agent project, I’ve linked it here: https://how-to-scope-ai-voice-ag-7i8lpn7.gamma.site/

After building voice agents for 15+ clients, I turned my entire QA process into a quick LLM-powered workflow that cuts out 80–90% of the manual testing. Testing voice agents used to drain my week. Every small update meant another round of manual calls. Fix a node → retest. Update a fallback → retest. Change a price → retest everything again. It was brutal. So I built a tiny internal system to automate almost all of it. Here’s the exact flow: 1. Export the full agent as a JSON file. 2. Drop it into an LLM along with the client’s FAQ, KB pages, and policies. 3. Paste a system prompt that forces the model to understand every branch and condition. 4. Auto-generate 15–25 realistic test cases with: – emergencies – confused callers – angry callers – pricing checks – spam filters – function call tests – out-of-order info – multi-language attempts 5. Convert the whole output to Retell’s JSON format. 6. Import it into simulations. 7. Run everything at once and skim transcripts for anything weird. Total time: ~12 minutes. The real win isn’t just speed — it’s consistency. Every agent gets tested the same way. Every update gets retested with the same suite. No more “Oh I forgot to test billing flows” moments. If you want this level of sanity back, here's my exact SOP

We are scaling fast and I’m officially looking for sharp AI voice agent (MAINLY) and chatbot developers Who can not only build workflows but actually think through business problems & design systems around them. Dream candidate is someone who’s been in the trenches of both automation and business. I.e maybe you’ve run your own thing, maybe you’ve built systems inside a company and seen firsthand where the bottlenecks are. In general, if you can diagnose problems, design solutions, and then execute them, I want to hear from you. Deliverables - Day-to-day will be a mixture of building systems (Vapi, Retell, GoHighLevel, CRMs, API integrations, etc), scoping client needs and making sure what you build actually moves the needle for the business. - Design and deploy AI voice agent solutions that solve real business problems - Integrate voice agents with CRMs, databases, and client systems via APIs - Sometimes you'll work behind the scenes, sometimes you'll be client-facing - Mostly no-code, but if you have a coding background, even better. Key is delivering solutions that drive the needle and are maintainable. Compensation - This one is experience-based. I know we all have different levels of skill here, so pay will scale with what you bring to the table. - Nonmaterial: you'll get the upside of working directly with me + seeing how a fast-growing AI agency operates from the inside. - Also obviously big growth opportunities as we build out the team. Work - We'll set you up in our Slack for comms. - We're basically hiring mini-operators rn, looking into seeing how that scales. Tech Stack - Retell (Mainly), Vapi - n8n - GoHighLevel, CRMs - APIs - you should be comfortable working with RESTful APIs, webhooks, and integrations Process - Share any examples, projects, or case studies that show what you've built. - If we like the experience, we'll reach out to you, so show off as much as you can. BONUS: If you speak good English and comfortable speaking to clients.

Hey all—I’ve been messing around with AI Voice Agents at my agency, qwickstep.ai. Just wrapped up an appointment booking agent… worked really well. And another project for recovering Shopify abandoned carts by calling up customers and looking to recover the sale. I’ve attached some of the basic version of the flows from those builds if you’re interested to check them out. But right now, I’m looking to focus on something that could potentially make an even bigger impact—a speed-to-lead voice agent. Calls a lead seconds after a form submit or booked all. Instant engagement. Higher conversions. I’m itching to test it out. See if it actually boosts conversions. Currently building out such a solution for one of my mates who runs a coaching business—would love to see how that converts. Have a look at one of the flows attached too. I’m curious—is anyone here interested in testing this out for their business? Or if you run an agency and want to offer this to your clients, I’d love to collaborate. Let me know. 💪

Hi all—I’ve built out a solution for a client struggling with abandoned checkouts in Shopify. Those in the Ecommerce space probably faced this too. It can be frustrating. Customers adding items to their cart, and then… poof. They’re gone. I spent some time last week building a Shopify workflow to recover as many checkouts as possible. The best part? It costs me $0 extra since I already use Shopify and n8n. Here’s how I did it. First, just to explain how it works. When a customer abandons their checkout, this workflow grabs all the important details—like their name, email, phone, and cart info. It then sends these info through an HTTP request. This can be integrated to automation tools like Make.com or n8n where we could trigger phone calls. Here’s the step-by-step: 1. Set up a Shopify trigger. I used “Customer abandons checkout” as my starting point. 2. Add a condition. I only want checkouts worth more than $0. No empty carts here. 3. Wait 30 minutes. Allow customer a little time to maybe come back on their own. 4. Check if they still haven’t checked out. If they have, we stop here. 5. Add another condition. We only want checkouts with products still in stock and available. 6. Send the HTTP request. I set this up in n8n to grab all the details—like first name, email, and cart items. 7. From here on out I built out an automation where it makes an outbound call/generate discount/handle objections etc… The HTTP request body in the shopify workflow looks something like this: { "first_name": "[[abandonment.customer.firstName]]", "last_name": "[[abandonment.customer.lastName]]", "email": "[[abandonment.customer.email]]", "phone": "[[abandonment.customer.phone]]", ...so on. } Let me know if you’d like the entire HTTP request body. I’ll shoot you a DM. If you’re interested in knowing more about the next steps—like building a voice agent or setting up the n8n workflow, let me know in the comments. I’d be happy to share. Hope this helps you.