Deploy AI #3: Safety and Efficiency in AI Engineering
Details
⚠️ IMPORTANT: Registration is required through Luma. RSVP on meetup.com does not confirm the attendance. ⚠️
Deploy AI is where engineers share stories about what they’ve built and what it taught them. This time, our Speakers prepared two talks on working with LLMs in efficient and safe manner.
TALKS:
→ Wiktor Daniec (Senior Software Engineer, Upside) with a talk Learn the Taxonomy First: The Key to Efficient LLM Use
The key to using LLMs efficiently is learning the taxonomy of a field first. Precise names lead to precise answers: faster, sharper, and with fewer corrections. This talk shows why taxonomy comes first and how to approach it.
→ Krzysztof Pokorski (Software Engineer, Upside) with a talk Sandboxing Claude Code: Running AI Agents Safely
AI coding agents are most useful when they run autonomously, but every skipped permission prompt hands more control to a model that can make mistakes or be manipulated. I'll share how I give Claude Code real freedom without putting my machine, secrets and codebase at risk.
Q&A:
After the talks, we stay for Q&A session and networking.
Who's it for?
Developers, architects, and tech leads working with complex AI solutions
Details:
- 20th October 2026 (Tuesday)
- Doors open: 17:45 | Start: 18:00
- Registration is required via Luma