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
A chatbot that only matches keywords isn't really understanding your customer.
Modern AI chatbots can interpret intent, remember context, handle follow-up questions, and guide users toward the right action.
The goal isn't to make conversations sound human.
It's to make getting things done feel effortless.
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
Designed the landing page for Smug — an AI support agent that resolves tickets, knows exactly when to escalate to a human, and has zero interest in pretending otherwise.
Most AI support tools go the humble, over-apologetic route. Smug does the opposite — the whole brand is built around a smug little cat mascot and copy like "Handled it. You're welcome." It's a genuinely fun brief: figuring out how to make confidence read as charming instead of obnoxious.
Bold electric blue and orange instead of the usual muted SaaS palette, because a product this confident shouldn't look shy about it. 💙
cool
THREADLINE ATELIER
A premium booking experience for a custom fashion studio in Lagos.
I wanted to solve a simple problem: when someone asks, “Can I book with you?”, the designer shouldn't have to spend the next hour going back and forth about availability, measurements, event dates, and scheduling.
Threadline Atelier turns that into one smooth flow:
Inquiry → Design Brief → Availability → Booking → Deposit → Confirmation
Customers can choose what they're making, share their occasion and event date, upload inspiration, select a real available consultation time, pay the consultation deposit, and get booked.
For the designer, it reduces manual coordination, follow-ups, and scheduling headaches.
Visually, I wanted it to feel like a luxury fashion house with a digital experience editorial typography, contemporary African fashion, cinematic motion, and subtle thread-inspired interactions.
The signature moment:
“YOU'RE BOOKED.”
This is a well structured website but the booking experience is what I looks good.
Before adding AI to your SaaS, write the failure contract.Most AI feature briefs describe what should happen when the model works.Production problems begin when it doesn’t.Before adding AI to an existing SaaS product, I think the team should define: 1. LatencyHow long can the user wait before the product falls back, continues asynchronously, or offers another path?2. UncertaintyWhat happens when the output is incomplete or confidence is too low? Does the product ask for clarification, request human review, or refuse the action?3. PermissionsWhich records can the model access for this user, role, and organization? AI should inherit the product’s access rules rather than bypass them.4. Action boundariesCan the AI recommend, draft, or execute? Sending an email, changing a payment state, and updating a customer record should not share the same approval rules.5. CostWhat is the usage limit per user or tenant? Which model or workflow becomes the fallback when a request is too expensive?6. RecoveryCan the team see which model, prompt, data, and tool call produced the result? Can a failed workflow be retried without duplicating the action?Connecting an API is usually the easy part. The real product work is deciding how the feature behaves when reality does not match the demo.If you are building AI into a product, which part is hardest to define: latency, permissions, human approval, cost, or recovery?
Recovery is the one I find hardest to define. If an email goes out and the next step fails, I want the retry to know it was sent so the customer does not get it twice.