Mind the Loop: Empowering AI Agents to Reason, Decide, and Do

**In-person and live on YouTube:** https://www.youtube.com/@AICDMX

English with live Spanish subtitles
Este evento será en inglés con subtítulos en español en vivo.

Step into an evening built for people who want the real story of agent engineering. Told by someone who actually ships them. Alejandro Krasovsky has been building software for over a decade, and now he’s lifting the lid on how AI agents really think, plan, and act. Expect a relaxed vibe, honest war stories, and a practical guide you can take back to your own projects the next morning.

We’ll break down the fundamentals of LLMs, explore when agents are the right tool, and map the frameworks (Mastra) Alejandro uses to help them take action in the wild. You’ll hear candid advice on avoiding common pitfalls, empowering agents with the right tools, and what “good” looks like when you’re orchestrating complex systems that need to move fast without breaking everything.

**Key Takeaways**
- Understand the LLM building blocks that drive agent reasoning, planning, and action.
- Spot the use cases where agents shine—and the red flags that signal a different approach.
- Learn the frameworks and tool strategies Alejandro uses to let agents operate safely in the real world.
- Leave with practical guardrails and patterns you can plug into your own builds the next day.

**Speaker**
Alejandro Krasovsky · Senior Software Engineer
LinkedIn: https://www.linkedin.com/in/alejandrokrasovsky · GitHub: https://github.com/alejandrok93

**Schedule**
6:00 p.m. Doors & check-in
6:30 p.m. Conversation begins
7:15 p.m. Audience Q&A
7:30 p.m. Networking
8:00–9:30 p.m. After party at a nearby spot (5 min walk; indoor/outdoor, bring a jacket and your drinking/eating shoes)