This is a submission for the Agent.ai Challenge: Assembly of Agents (See Details)

What I Built

I created an agent that takes any X profile handle, and based on the username, bio, and posts, delivers witty, hilarious roasts tailored to the profile. Why did I make this? Because we all need that roasting buddy to add some spice to our day, right? 😁🔥

This 24/7 roasting agent is always ready to roast you (or anyone you choose) with clever, personalized comebacks. Oh, and I used another agent— Twitter/X Personality Analyzer— to help gather the user's X account analysis.

Demo

You can check out my agent at:- X Profile Roaster

A video demo showing my agent in action:-

Screenshots of this agent(showcasing its roast for me 😅☺️):-

Agent.ai Experience

Exploring the agent.ai platform was a surprising delight! I kicked things off with this fantastic course: Agent Builder Intro Course, which taught me about the making of an agent- Planning for it, Choosing a template(or starting from scratch), and finally building the agent in the agent.ai ecosystem.

From there, I created this agent, which turned out to be surprisingly straightforward.

The process boiled down to just four main steps:

1️⃣ Take the user's X profile username for input.

2️⃣ Call the Twitter/X Personality Analyzer (https://agent.ai/profile/vxxmvpn1x6afng0f), storing the analysis results in a variable.

3️⃣ Generate a roast using an LLM agent based on the X profile analysis.

4️⃣ Display the roast to the user as the final output.

Here’s a sneak peek of the actions tab of my agent, showcasing the workflow behind :

Agent.ai made this process intuitive, simple, and, most importantly, fun to build and execute!

Conclusion

I’ll admit, this was my first time using Agent.ai, and I was a bit apprehensive about the time commitment needed as well. But then I discovered a course specifically designed for beginners like me— and I drove into it! It boosted my confidence immensely. Initially, I was determined to build everything on my own without relying on any other agents. However, the process quickly became overwhelming and chaotic. So, I decided to call in another agent for support, and let me tell you—I’m so glad I did! The experience was rewarding, and I’m genuinely proud of how it all turned out.

So, that's it!

If you're still here, Thank you 🙏🏻.

Please share your thoughts, feedback, and suggestions in the comment section below 🗨️