Pinned
Nov '25 •
spent around 2 years working with ai tools and here are my thoughts so far
Good morning everyone! After spending 2 years testing various AI development tools, I wanted to share my experience to help you save time and money. Disclosure: Some links below are referral links. 🏆 Top Tools Tested: - Replit - Manus - Lovable - Cursor - Claude Code My Top Recommendations 1. Replit - 9/10 Replit impressed me the most. With a single prompt, I built a fully functional real estate platform featuring: - User registration and authentication - Property listing system - Profile management - Image uploads - Clean, professional UI/UX - Zero bugs in initial deployment The polish and functionality right out of the box were remarkable. 2. Manus - Highly Recommended Using just 3 prompts, I created a comprehensive self-improvement web app tracking: - Workout routines - Sleep schedules - Health metrics - Goal achievement progress While the UI isn't as polished as Replit's output, the functionality is solid and works flawlessly. web app demo: https://rebourneapp-kk4y2c3m.manus.space/Referral link for manus: https://manus.im/invitation/UDSSKCGJRZTZQ6M 3. Lovable - Strong Contender Lovable has improved significantly and now offers competitive features. I've built my largest projects here, and it uses Supabase for the backend, which I've grown to appreciate. One caveat: You'll need Supabase MCP integration to work on Lovable projects in other tools like Cursor or Claude Code. However, once set up, these tools excel at adding features and debugging. Referral link: https://lovable.dev/invite/AD45UMY What's your experience with AI development tools? Any questions about these platforms? what is your favourite tool so far ?
Poll
Cast your vote
2h •
Fixing a Fragile Email Automation in Make.com
Today I worked on stabilizing an Airtable to Email automation that was failing due to validation errors. The workflow itself was simple Airtable trigger to email send but the details were causing issues. Errors like invalid email address and array of objects expected usually mean the data structure is slightly off even if it looks correct on the surface. The first step was making the automation future proof by switching all Airtable mappings to Field IDs instead of column names. That way the scenario will not break if fields are renamed later. Then I rebuilt the To CC and Reply To logic properly. Instead of raw strings I used correct array formatting with split flatten deduplicate and remove. This ensured empty fields do not create invalid values and a fallback email is always included without breaking the module. Finally I added basic checks so the workflow never attempts to send an email without a subject or body. This was not about adding complexity. It was about making the automation reliable predictable and safe to run in production.
1
0
3h •
If you’re posting and getting under 100 views, it’s usually one of 3 problems:
Wrong niche Weak thumbnail psychology Poor first 30 seconds hook Most people guess instead of fixing the real issue. If you want me to break down your situation, message “AUDIT” through any of these: Telegram (Direct): http://t.me/akeemkazeem� WhatsApp: https://wa.me/message/GRBUJBSTEZIBA1� Telegram Community: https://t.me/+x37a60CxHCRkYzhk�
2d •
Fixing a Silent API Failure in an n8n Workflow
Today I helped fix a small but blocking issue in an n8n workflow that looked simple on the surface but kept failing at the API step. The flow was straightforward Webhook to HTTP request to Google Sheets and then an email notification The webhook was receiving data correctly but the workflow kept stopping at the HTTP request node. After digging in I found the issue was a mix of API authentication and how the JSON response was being handled. I debugged the HTTP request node checked headers tokens and payload structure then fixed the authentication logic. I also cleaned up the JSON parsing so the data mapped correctly into Google Sheets without breaking the execution. After that I ran multiple end to end tests to make sure the workflow completed successfully every time and triggered the email notification as expected. This is a good reminder that most automation failures are not about complexity. They usually come down to small details in API calls and data structure. Once those are right n8n workflows become very stable and predictable.
1
0
3d •
Built a Simple AI Lead Qualification Workflow in Make.com
Today I worked on a small proof of concept for a B2B lead generation setup called NexaGrowth. The goal was to see how AI could quickly qualify incoming leads without adding complexity. The workflow starts with new leads coming in through a Google Form and webhook trigger. Once a submission comes in, the data is sent to OpenAI where the lead is analyzed to classify the industry, estimate company size based on the description, and assign a lead score from 1 to 10. That output is then structured cleanly and pushed into Airtable so the data is easy to review and filter later. If the lead score comes back as 8 or higher, the automation instantly sends a Slack notification so the team can act fast on high intent leads. Nothing fancy, just clean logic, clear prompts, proper data mapping, and basic error handling to keep the flow stable. This kind of setup is a great example of how AI can support lead qualification without replacing existing systems or overengineering the process. Simple automations like this often deliver the quickest wins.
1
0
1-30 of 78
powered by
skool.com/automationfordays-6390
AutomationForDays: Build automations with Artificial Intelligence (AI) and language models using n8n. Weekly sessions, templates, friendly Q&A.
Suggested communities
Powered by