Never miss a new edition of The Variable, our weekly newsletter featuring a top-notch selection of editors’ picks, deep dives, community news, and more.
We’ve seen the same cycle play out in recent years: a new type of AI-powered technology arrives with great fanfare, generates a slew of buzzwords, and then leaves many practitioners scratching their heads, unsure of they can even do anything useful with it.
Agentic AI has been following a similar path in the past year. To help you separate hype from reality, we’ve collected three standout articles that tackle the nitty-gritty details of working with these AI systems.
From multi-agent workflows to the intersection of agents and knowledge graphs, you’ll leave this edition of the Variable with a deeper, hands-on understanding of this trending topic. (If you have your own nuanced take on it, do share it with us!)
Agentic AI: Single vs Multi-Agent Systems
How does the number of agents and the complexity of their tasks affect the construction and performance of agentic-AI systems? Ida Silfverskiold presents a focused walkthrough that unpacks the process of building a tech-news delivery app.
Agentic GraphRAG for Commercial Contracts
Tomaz Bratanic leverages his deep expertise in knowledge graphs in a new deep dive that brings together agents, RAG, and the challenges of working with legal contracts.
AI Agents from Zero to Hero — Part 3
Many of you have been following Mauro Di Pietro‘s popular series on agentic AI; don’t miss the latest installment, which shows how to build different types of multi-agent systems.
Other Recommended Reads
If you feel like exploring a wider set of topics this week, we invite you to read these excellent articles on the challenges of career transitions, graph neural networks, generative modeling, and more.
- In a candid and insightful account, Amy Ma charts the highs and lows of switching from a data scientist role to that of machine learning engineer.
- Interested in GNNs? Don’t miss Hennie de Harder‘s latest addition to her accessible series, focusing this time on the power of GraphSAGE.
- Moving to the theory-oriented end of the spectrum, we’re thrilled to share a lucid exploration of Hamiltonian mechanics for generative modeling and MCMC, courtesy of Soran Ghaderi.
- Could AI play a role in addressing the difficulty of conducting political polls? Stephanie Kirmer weighs the potential benefits against some valid concerns.
- If you’re in the mood for a technical deep dive, Umair Ali Khan published a comprehensive guide to developing an interactive AI application for video-based learning.
Meet Our New Authors
Explore top-notch work from some of our recently added contributors:
- Sudheer Singh joins TDS with a wealth of industry know-how, and devotes his debut article to circuit tracing, a novel AI-interpretability approach.
- Arne Johan Pollestad leans into his research interests in his new post, which looks at uncertainty quantification in the context of real-estate valuations.
- Jeremy Debattista works at the intersection of data governance and semantics (among other areas); his TDS debut focuses on the RDF and LPG data models.
Contribute to TDS
We love publishing articles from new authors, so if you’ve recently written an interesting project walkthrough, tutorial, or theoretical reflection on any of our core topics, why not share it with us?
