Our Two Agentic Apps Built with CrewAI
Recap of powerful agentic apps.
Production-grade AI Orchestration with CrewAI [Open-source]
CrewAI is a production-grade framework for orchestrating advanced AI agent systems, from automations to complex applications. It helps you gain precise control and deep customization for your AI projects.
Provides customizable agents that give you full control over roles and behaviors.
Enables collaborative Intelligence, which results in seamless agent teamwork.
Has flexible task management, that lets you define agentic tasks with precision.
Provides highly reliable architecture with robust error handling.
Comes with a versatile orchestration with support for sequential, hierarchical, and custom workflows.
Some more plus points:
Works with OpenAI and most popular open-source models.
Lets you build event-driven (conditional) workflows.
Produces reliable outputs with guardrails.
Has a comprehensive documentation.
We have showcased two agentic demos in this newsletter with CrewAI.
Today, let's do a recap of them.
1) Our agentic workflow to write and publish social content
Recently, we built a personal multi-agent app that can automatically write and publish social media content.
Here’s our tech stack:
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 below.
Here's a brief summary of 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 a 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.
Also, the code is open-source. You can find it here: Content creation agent.
2) Building a multi-agent news generator
Recently, we also shared a demo on building a multi-agent news generator using CrewAI:
The app takes a user query, searches the web for it, and turns 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 →
P.S. For those wanting to develop “Industry ML” expertise:
At the end of the day, all businesses care about impact. That’s it!
Can you reduce costs?
Drive revenue?
Can you scale ML models?
Predict trends before they happen?
We have discussed several other topics (with implementations) in the past that align with such topics.
Here are some of them:
Learn sophisticated graph architectures and how to train them on graph data: A Crash Course on Graph Neural Networks – Part 1.
So many real-world NLP systems rely on pairwise context scoring. Learn scalable approaches here: Bi-encoders and Cross-encoders for Sentence Pair Similarity Scoring – Part 1.
Learn techniques to run large models on small devices: Quantization: Optimize ML Models to Run Them on Tiny Hardware.
Learn how to generate prediction intervals or sets with strong statistical guarantees for increasing trust: Conformal Predictions: Build Confidence in Your ML Model’s Predictions.
Learn how to identify causal relationships and answer business questions: A Crash Course on Causality – Part 1
Learn how to scale ML model training: A Practical Guide to Scaling ML Model Training.
Learn techniques to reliably roll out new models in production: 5 Must-Know Ways to Test ML Models in Production (Implementation Included)
Learn how to build privacy-first ML systems: Federated Learning: A Critical Step Towards Privacy-Preserving Machine Learning.
Learn how to compress ML models and reduce costs: Model Compression: A Critical Step Towards Efficient Machine Learning.
All these resources will help you cultivate key skills that businesses and companies care about the most.