Engineering Your Own AI Assistant
Deep Research, Personal Automation, and the Agentic Workflow with Paul Iusztin
As AI tools become increasingly accessible, the frontier is shifting from massive enterprise applications to highly customized personal automation. In this live event, Paul Iusztin returns to dive deep into the mechanics of building personal AI assistants.
Moving past our previous discussion on enterprise LLMOps, Paul will break down the practical realities of agentic AI engineering for the individual developer. We will explore how to architect specialized agents for deep research, how to safely manage unstructured personal data, and why over-engineering multi-agent systems is the fastest way to end up in proof-of-concept purgatory.
He’ll cover:
The mechanics of personal automation: knowing when to build vs. prompt
Architecting autonomous agents for deep research and content creation
Escaping proof-of-concept purgatory: lightweight infrastructure for individual developers
Insights from the Agent Engineering: Building Multi-Agent Systems course and core skills for 2026
About the Speaker:
Paul Iustin is the author of the bestseller LLM Engineer’s Handbook, lead instructor of the Agentic AI Engineering course, founding AI Engineer of a San Francisco start-up, and obsessed with making knowledge accessible through AI.
With over 10 years of experience and 20 apps shipped, he teaches AI Engineering as he wanted to at the beginning of his career. End-to-end. From idea to production. From data collection to deploying, monitoring, and evaluation. With a focus on AI principles, software patterns, and infrastructure systems that will thrive in a future dominated by AI coding tools.
His ultimate goal is to help other engineers escape PoC purgatory and 10x their AI Engineering skills.
DataTalks.Club is the place to talk about data. Join our Slack community!