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
This was a more complex build. The system receives incoming data through a webhook, stores the context in a Data Store so it remembers what's been said, then runs it through OpenAI (ChatGPT) to generate an intelligent response. Depending on what comes back, it takes one of two paths either responds directly through the webhook, or triggers additional HTTP calls and a second AI pass before replying. The result is a bot that doesn't just react to messages, it actually thinks about them first before responding. Built entirely in Make, no extra infrastructure needed.
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
Related posts
This is so cool!
Before you add AI to your product, find the screen where your users already copy and paste.
That's usually where the real AI feature lives. Not a chatbot in the corner, but a step people already do by hand: summarising a ticket, drafting a reply, tagging an upload, pulling fields out of a PDF.
Here's the order I follow when a founder asks me to add AI to an existing SaaS:
1. Pick one workflow, not "AI everywhere." Watch where users leave your app to paste something into ChatGPT and come back. That round trip is your feature.
2. Keep the model behind your own API. One service owns prompts, retries, logging and cost limits, so you can switch providers without touching the frontend.
3. Make it tenant-aware from day one. Each customer's data, prompts and usage stay scoped to their account, or the first enterprise security review will stop you.
4. Ship a draft, not a decision. Let the AI suggest and the user approve. You earn trust and get real feedback before you automate anything.
5. Measure accepted output, not tokens. If users rewrite most of what it produces, the prompt or the context is wrong, and that's your real roadmap.
Most AI features that flop didn't fail because of the model. They were bolted onto the wrong step.
What's the one task your users still copy into ChatGPT?
Watching where users paste into ChatGPT and come back is such a practical way to find the real feature. Most teams start with the chatbot instead.
AI Transformation Timelapse Video | Before to After
AI-powered transformation timelapse showcasing the evolution from a starting concept to a final visual result. I create cinematic before-and-after sequences using AI tools, creative direction, and video editing techniques. Suitable for product showcases, real estate visualization, marketing campaigns, and social media content that require engaging visual storytelling and premium presentation.
