Today feels like a good moment to pause, breathe and send a bit of warmth your way. Whether you’re celebrating Thanksgiving or simply enjoying a quieter Thursday, I hope you get a slice of time that feels yours. A moment to reset, to think, or to stare at a potato and refuse to roast it. (That's what I'll be doing as I pour another glass of wine - just another wet, miserable day in the UK). However, as Maya Angelou put it, “Let gratitude be the pillow upon which you kneel to say your nightly prayer.” A gentle reminder that gratitude doesn’t need a ceremony, just attention. So here’s mine. I’m grateful for the assets that keep my businesses moving, for the conversations we have here, and for the fact that you’re building something Evergreen rather than something exhausting. If you fancy joining in, share one asset, habit or tiny system you’re thankful for this year. No pressure, just a bit of human connection. 💚 Kerry P.S. Isn't Gemini Veo just super marvellous - I can practically taste that wine!

I’m working on a voice-powered booking system that uses Retell AI to talk to callers and n8n as the backend. Retell collects all the booking details, confirms the exact UK date and time with the caller, and then sends one clean function call into n8n, for example: Book a table for four under Michael on 25/11/2025 at 2 PM. n8n’s Calendar Agent is then supposed to interpret this text and create, update, or cancel the event in Google Calendar. What’s going wrong Even though Retell now always sends explicit UK-format dates (dd/mm/yyyy) after confirming with the caller, the Calendar Agent inside n8n sometimes reinterprets that date — usually by shifting the year backwards (e.g., 2025 → 2024) or otherwise assuming a different date before creating the Google Calendar event. There are no node errors; the workflow technically “works”, but the booked date in Google Calendar is sometimes wrong unless the caller corrects it manually during the conversation. A typical example Retell sends: Book a table for four under Paul on 26/11/2025 at 11 AM. But the Calendar Agent replies with: “Do you mean Wednesday 27/11/2024?” Which is obviously not what was said. This behaviour suggests the LLM inside the Calendar Agent is unnecessarily re-interpreting an already explicit date. What I've already tried I rewrote the Retell system message completely (the new 26 November version): Anchors today’s date Forces future-only dates Requires explicit dd/mm/yyyy internal conversion Confirms the exact UK date verbally with the caller before sending anything to n8n Ensures Retell never sends vague phrases like “next Tuesday” in the backend call I also updated the n8n Calendar Agent system message: If chatInput already contains a numeric UK date, it should trust that date 100% It should not convert “26/11/2025” into anything else It should only reject dates that are actually in the past Removed all automatic reinterpretation of relative dates when an explicit one is provided Removed availability checks unless the caller explicitly asks for it

We are officially live. Introducing AutoScale Labs. For too long, "scaling" has been synonymous with "hiring." When operations got messy, businesses added more people. When leads increased, they added more sales reps. We believe there is a better way. AutoScale Labs is a modern AI automation agency designed for one purpose: To help your business grow without expanding your workforce. We don't just patch holes; we engineer intelligent workflows that run 24/7. What we do: 🔹 AI Automation: End-to-end workflow engineering to eliminate manual tasks. 🔹 Operations & Outreach: Automated onboarding, fulfillment, and delivery systems. 🔹 Sales & CRM: From lead capture to pipeline automation. 🔹 AI Agents: Custom internal assistants that handle support and retrieval. Our mission is simple: More growth, same team. I founded this agency to build the systems that let businesses scale leaner and faster than the competition. Ready to start? Skip the website forms and the wait times. If you want to discuss your bottlenecks, just DM me here or drop a comment below, and let's get in touch directly.

Hey everyone, I’m following Nate’s RAG Pipeline & Chatbot tutorial, and the Pinecone Vector isn’t working. Thoughts on why?

brothers is there any free image generation models that give free tokens in order to use it in n8n