Just wrapped up the Calendar AI Agent build — here's what I built and some things I learned along the way. The idea: a customer messages in, the agent handles everything from quoting to scheduling to record-keeping — no human needed. What I added on top of the base agent: → Custom pricing engine that calculates quotes based on service type, home size, add-ons, and surcharges (weekend, same-day, parking) → Dynamic scheduling — the agent uses the estimated job duration from the quote to figure out which time windows actually fit on the calendar. A 4-hour deep clean gets different availability than a 1.5-hour regular clean. → 30-minute buffers between bookings so jobs don't overlap → Airtable CRM integration — saves customer info and full booking records automatically → Pinecone knowledge base so the agent can answer questions about services, pricing, and policies → Owner notification on every new booking → Full rescheduling and cancellation flows Tools: n8n + Google Calendar + Airtable + Pinecone + OpenAI Biggest lessons: 1. Prompt engineering is where the real work is. Wiring nodes together is the easy part. Getting the agent to actually think correctly — collecting info in the right order, not double-booking, handling edge cases — that took 80% of the time. 2. Tool descriptions matter more than you think. If the tool description is vague, the agent will use the tool wrong. I had to be extremely specific about what to pass and when to call each tool. 3. Test edge cases early. I found bugs like: the agent booking the same event twice when the customer confirmed twice, not updating records when customers added info after booking, and trying to schedule on Sundays. Each one needed a specific fix in the prompt. 4. Get the quote before checking availability. This was a design decision that changed everything — you can't check if a time slot works without knowing how long the job takes. Sounds obvious in hindsight but the original flow had it backwards. Demo video is attached. Happy to answer any questions about the build.

First solo build and made a simple but fast social media automation in Make.com to my 2 active profiles in Facebook and Linkedin creating customized posts in each app from URLs entered into a Google Sheets table.

Hi everyone. My name is Melanie Armstrong. I am from Cleveland. I am an Epic Analyst and a Real Estate Investor. I would like to build a successful AI Consulting Agency , land clients ASAP, and use these skills to build financial freedom. I have been wanting to jump in this space for awhile but didn't know where to start. CHAT GPT advised that this is one of the best courses in the SKOOL Community so I am here. 🥰

Just built an entirely automated client intake + onboarding workflow. Case study: Client was spending 3–4 hours a day manually: - Reviewing Typeform submissions - Sending Calendly links - Updating Airtable CRM - Creating Drive folders - And hoping leads didn’t go cold in the process... Not anymore. With the help of n8n, I’ve now built two connected workflows: 1. Workflow A — Typeform → CRM scoring → Email + Slack notifications 2. Workflow B — Calendly booking → CRM update → Google Drive + ClickUp + Coach alert The system handles: - Lead scoring & qualification - Duplicate detection - CRM creation/updating - Personalized emails & Slack alerts - Folder generation in Drive - Pre-call summary docs

The setup: - Chatbot in Voiceflow - Voice agent in VAPI - Airtable for middleware CRM - Both need identical user journeys The user experience on the website chatbot had to match the voice agent experience. 🙌 Similar questions. Similar flow. Similar outcomes. 🙌 Problem is that that the Voice Agent is a different beast to a chatbot. Compromises had to and have to be made. The CRM problem: Their current CRM isn't full-featured. Limited API. The real pain? Maintaining OAUTH sessions. Each request needs proper logging. Session tokens expire. The solution: 🚖 Built a middle data layer in Airtable. Feeds both chatbot and voice agent. 🚖 Now: - Information is consistent across both channels - Client can update messaging easily - No technical skills needed to change offers - One source of truth Their existing CRM was creating more problems than it solved. Especially as the client's current way of operating did not fit neatly into a simple automation. Airtable helped a lot, especially as the usage fits neatly into the free tier. 💪🏿 Don't force yourself to work with bad infrastructure. 💪🏿 Sometimes, building a bridge might help. I generally dont like adding new tech to current infrastructure due to the added complexity. But in this case it seems to be the right thing to do. Their CRM stays. My Airtable layer handles the AI interactions. Everyone's happy. The result: - Consistent experience across voice and chat. - Client can manage their own content. - No developer needed for updates. Ever had to build middleware because the client's systems weren't AI-ready?