Hey everyone! Hope you're all doing well. I'm working on an automation and running into a frustrating issue that I'm hoping you brilliant minds can help me solve. Here's what my automation does: - Triggers when a new record is created in Airtable (from a form submission) - Make scenario activates and connects to my survey database - Identifies if the person is a "participant" or "evaluator" - Searches for both the rater's email and participant's email to create a match - Updates the records accordingly - Finally updates some Google Sheets tables The Problem I'm Facing: The automation breaks down when searching for the Evaluator's email because people fill out their names inconsistently: - Sometimes they misspell names - They simplify names (like "Mike" instead of "Michael") - Add extra spaces or formatting issues - This prevents proper matching and breaks the flow What I'm Looking For: I need a formula or solution that can handle these name variations and still find the correct matches, even when the input isn't perfect. Has anyone dealt with something similar? Any suggestions for fuzzy matching or name standardization techniques that work well with Make/Airtable? Thanks so much in advance for any help you can offer! Really appreciate this community

1. Open ChatGPT 2. Upload Your Image 3. Try Two Prompts #1 A cinematic double exposure of a man in profile, with a post-apocalyptic cityscape inside his silhouette. The inner scene shows the man walking through a destroyed, burning urban street, buildings in ruins, glowing embers and fire, with a dramatic sunset in the background. Moody lighting, warm tones, emotional and introspective mood, high detail, 8K resolution #2 Upload your photo to Chatgpt and prompt: Create a high-contrast black and white close-up portrait of the referenced man. Exact face features. The image should depict only the left half of his face, partially submerged in water, with water droplets and bubbles visible on his skin and hair. Illuminate the left side of the face dramatically, casting the rest into deep shadow. dark background. detail in skin texture, beard stubble, and eye focus to evoke a moody cinematic atmosphere. 1:1 orientation Tried it? Drop your results in the comments 👇 Let’s see your most cinematic version! P.S. Connect with me on Instagram too — @jahar.ai 📸

Hello community! Can anyone help me? I'm looking for a way to capture an entire YouTube channel, convert all its videos into text, and then utilize all that channel information in GPT Agents or the Projects section in Claude or OpenAI. Do you know of an effective and inexpensive way to do this? Thank you all very much!!! @Mohamed Jahar

Hey everyone! 👋 Super excited to share a new automation I've been working on over the past few weeks. If you're looking to revive or optimize your YouTube channel, this might give you some inspiration! 🎯 The GoalAutomatically update titles, descriptions, and keywords for all my YouTube videos — using data, transcripts, and SEO best practices. 🔧 What It Does 1. Pulls all videos from my YouTube channel via the YouTube Advanced API. 2. Checks which ones haven’t been processed and creates records in a tracking table. 3. Grabs video stats (views, comments, likes) and full transcriptions (even for 2hr+ videos). 4. Generates summaries and full transcripts, saved to Google Docs via Dropbox (to get public URLs). 5. From the transcript, it creates: 6. Updates the tracking table and pushes the content live to YouTube! 💡 Why I Built ItI have a lot of long-form content that still has potential but wasn’t optimized for discovery. This automation helps me breathe new life into those videos — at scale. 📊 Stack Used - YouTube Advanced App - Supabase (Trial subscription) - OpenAI - Google Docs + Dropbox integration - Automation and logic flows with a tracking table (Airtable) If you’re interested in automating your content workflows or want to see a walkthrough, let me know — happy to share more!

We’ve built a smart, AI-powered system that helps sales managers evaluate how well their team members perform real sales conversations - without needing live supervision or manual call reviews. 𝐇𝐞𝐫𝐞’𝐬 𝐡𝐨𝐰 𝐢𝐭 𝐰𝐨𝐫𝐤𝐬 👇 📞 Team members initiate a call to an AI Voice Bot, built using Vapi. The bot plays one of three customer personas: 🎧 Neutral 🤨 Skeptical 🤝 Engaged 🤖 A Make.com scenario randomly picks a persona on each call — simulating unpredictable, realistic customer behavior. 📊 After the call ends, another Make scenario automatically evaluates the sales agent’s performance based on key metrics: -Opening clarity -Need discovery -Value explanation -Personalization -Objection handling -Call outcome -Total Score ✅ The scores are pushed to Google Sheets — giving managers a clear, structured view of how each rep handles different types of customers. 🎥 I’ve included a video showing the full setup, logic, and real-time demo. This system it helps managers identify gaps, strengths, and improvement areas so they can make better decisions around training, assignments, or next steps. Comment "AI Training" to get the blueprints and prompt for free.