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
Deep Research Agent, an autonomous research agent built on an agent-controller pattern. It breaks a question into ordered sub-tasks, searches the web with Tavily, and writes a report with citation tracking and contradiction detection. LLM providers are swappable through dependency injection.
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
just shipped a new framer template for a customer AI agent support platform
get it here: https://www.framer.com/marketplace/templates/wrenai/
Congrats on shipping it! AI support tools all start to look the same, so a template with this much personality will stand out. How long did it take from idea to marketplace?
Designed an AI agents dashboard where you approve work, track running tasks, and see your whole team of agents in one place.
Same screen, two shots. Which one would stop your scroll? 👀
1 voted
50%
1 voted
50%
2 votes
Closed
nice one dude
A WhatsApp chatbot that automates tasks is NOT the same as a custom-built web application.
And honestly, I’ve noticed how much people love AI-powered WhatsApp bots lately.
As someone who develops AI workflows and custom websites, I personally believe that combining a well-built web application with AI puts you one step ahead.
Imagine having a custom interface, your own database, automated workflows, and an AI agent working together in one place.
That’s a completely different level of flexibility.
Don’t get me wrong: WhatsApp bots aren’t always the inferior option. They’re great for customer-facing interactions and quick communication.
But personally? I’d rather give customers a dedicated web experience whenever the project calls for it.
Are you Team WhatsApp Bot or Team Web Bot?
When the web app and the bot share one database, which side owns the conversation state: the n8n workflow or the app? That choice seems to decide whether a customer can switch between WhatsApp and the web view mid-request.