The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
AI CHATBOT ON TELEGRAM | n8n | Automated workflow
Built an AI-powered chatbot on Telegram using n8n as the automation engine. The bot handles incoming messages through a Telegram trigger, routes them through an AI Agent connected to OpenAI and Groq models, and uses memory nodes to maintain conversation context across messages. The workflow also includes image analysis, JavaScript-based data processing, HTTP requests for external integrations, and dedicated error handling to keep the bot stable in production. The result is a smart, always-connected assistant that responds naturally and reliably to users in real time.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
NIVEA MEN Deep Impact Body Lotion — AI Commercial
A cinematic AI-generated product advertisement created for NIVEA MEN Deep Impact Body Lotion, focused on deep hydration, fast absorption, and healthy-looking skin.
The concept follows a man through his skincare routine, from experiencing dry skin to applying the lotion and transitioning into a confident, active lifestyle.
My Process:
ChatGPT — Creative direction and storyboard generation
Google Flow — AI video generation and cinematic animation
CapCut — Editing, pacing, transitions, and sound design
The commercial was produced in 16:9 format, with cinematic lighting, product-focused shots, lifestyle scenes, and a consistent visual identity throughout.
This project demonstrates how I combine AI video generation, creative direction, storytelling, and post-production to create commercial-ready product content.
Need AI-generated content for your brand or product?
Let's create something that makes your product stand out.
The product consistency is impressive here, especially keeping the NIVEA packaging recognizable while still giving the shot a cinematic AI look. Nice work Ajayi, the lighting and depth make it feel much closer to a real commercial frame.
Proud to share one of our recently completed projects — JOMP, a UK-based mobility technology platform built to transform the roadside assistance experience.
When a driver breaks down, getting help shouldn't be stressful.
With JOMP, users can request assistance instantly, receive transparent pricing, get matched with a verified service provider, and track help in real time — all from a single platform.
What makes this project special is that we didn't just design the experience.
We handled both the UI/UX Design and Full Product Development, turning an idea into a complete digital ecosystem.
🚗 Customer App
Request roadside assistance quickly and track support in real time.
🔧 Provider App
Accept jobs, manage requests, navigate to customers, and monitor earnings.
📊 Admin Dashboard
Manage operations, providers, pricing, service regions, analytics, and platform performance.
From product strategy and user experience design to development and implementation, every part of JOMP was built to create a seamless connection between drivers, service providers, and platform administrators.
Projects like this remind us that great technology isn't just about features—it's about solving real-world problems for real people.
A big thank you to our team and partners who helped bring this vision to life.
hashtag#JOMP hashtag#MobilityTech hashtag#RoadsideAssistance hashtag#ProductDesign hashtag#UIUXDesign hashtag#UXResearch hashtag#MobileAppDevelopment hashtag#WebDevelopment hashtag#SoftwareDevelopment hashtag#DigitalTransformation hashtag#StartupTechnology hashtag#SaaSDevelopment hashtag#AppDevelopment hashtag#CustomerExperience hashtag
Simple, elegant, and impactful. 👌
𝗬𝗼𝘂𝗿 𝗔𝗜 𝗰𝗵𝗮𝘁𝗯𝗼𝘁 𝗺𝗶𝗴𝗵𝘁 𝗯𝗲 𝗹𝘆𝗶𝗻𝗴 𝘁𝗼 𝘆𝗼𝘂𝗿 𝗰𝘂𝘀𝘁𝗼𝗺𝗲𝗿𝘀. 𝗔𝗻𝗱 𝘆𝗼𝘂 𝗱𝗼𝗻'𝘁 𝗲𝘃𝗲𝗻 𝗸𝗻𝗼𝘄 𝗶𝘁.
Real story from a recent client project.
An ecommerce brand came to me with separate AI agent workflows on n8n, one per platform, handling customer chats on WhatsApp, Facebook, Instagram, and Twitter/X. Sounded fine on paper. Then reality hit: 1,000+ customer messages a day across four channels.
The bot started breaking down:
• Making up order details that weren't real, straight up lying to customers
• Pulling the wrong info from their data, wrong context, wrong answers
• No way to trace why it said what it said
• Fixing one flow quietly broke another
• Couldn't handle the volume across four platforms at once
No-code tools like n8n, Zapier, and Make.com are great for simple automation. I use them too.
But a customer-facing AI agent live on four channels isn't simple automation. It's a thinking system under real pressure, and that needs real engineering, not drag-and-drop boxes.
So I rebuilt it as a custom-coded, production-level system:
1. Real RAG retrieval, pulls the correct answer from their data instead of guessing
2. Hybrid search plus reranking, checks data multiple ways and picks the best fit
3. Anti-hallucination guardrails, stops the bot from making things up
4. Structured outputs (Pydantic), clean fixed-format answers, not random text
5. Human-in-the-loop, a real person steps in on anything tricky
6. Full observability, every decision logged, nothing's a black box
7. Automated eval gate, quality check before anything goes live
8. One unified system behind all four platforms, instead of four fragile flows
Result: hallucinations dropped hard, answers got accurate, and for the first time we could explain every single thing the bot said, on every platform.
Simple truth: no-code is great for internal tasks and small automations. But if your AI agent talks to real customers and revenue depends on it, it needs real code, real testing, and real engineering, not just a workflow diagram.
If you're running a similar setup and it's starting to crack under real traffic, happy to talk through what a production-grade version would look like. That's exactly the kind of work I do.
