Today, we built a personal multi-agent app that can automatically write and publish social media content.
Here’s our tech stack:
CrewAI to build an agentic workflow.
FireCrawl for web scraping.
Typefully for scheduling.
The entire multi-agent system is totally hands-off and automated, and we heavily used CrewAI flows in this demo.
It is easier to explain the process in a video, which we have added above.
But here’s how it works:
We provide a link to a blog (in our case, it’s our newsletter issue).
We use Firecrawl to scrape the newsletter (with images) and save it as markdown.
Since there are multi-agents, one agent has access to our existing social content to understand our writing style.
Next, since we publish content on LinkedIn and X, we built two routers in this agentic workflow. Based on a trigger, another agent gets executed to write a ready-to-publish draft.
Finally, we use Typefully’s API (a social media post scheduling tool) to post the draft to our social channels.
As mentioned above, we heavily used CrewAI flows in this demo.
It allows you to create structured, event-driven workflows by connecting multiple tasks and controlling the flow of execution in your AI applications:
It is covered in much more detail in the CrewAI docs here →
Also, the code is open-source. You can find it here: Content creation agent.
We'll do a much more extensive deep dive on CrewAI covering special use cases very soon.
More about CrewAI
Earlier this week, we also shared a demo on building a multi-agent news generator using CrewAI:
The app will take a user query, search the web for it, and turn it into a well-crafted news article with citations!
We added two agents in this multi-agent app:
1) Research analyst agent:
Accepts a user query.
Uses the Serper web search tool to fetch results from the internet.
Consolidates the results.
2) Content writer agent:
Uses the curated results to prepare a polished, publication-ready article.
The full code walkthrough and demo is available here →
Thanks for reading!
