Is Your GenAI System Ready for Production Reality? | Maish Saidel-Keesing | LLMday Warsaw 2026 Q1

LLMday Warsaw 2026 Q1 - February 12
Grab your ticket for the next LLMday: https://www.llmday.com
Upcoming LLMday CFPs: https://cfp.ninja/?q=llmday&status=open&page=1

Chapters
00:00 Opening & a quick Polish greeting warm-up
00:14 Have you shipped GenAI to production? Setting the stage
01:37 Meet Mesh: production scars & what this talk will cover
02:20 Observability 101: why you can’t fix what you can’t see
03:45 Inside vs outside monitoring: Strands Agents, metrics & traces
05:19 Sessions, traces, spans explained (and why they matter)
06:10 Live demo: CloudWatch traces, logs, and exporting via OpenTelemetry
07:52 Keeping GenAI spend under control: tokens, tags & inference profiles
08:53 AI Development Lifecycle (AI-DLC): treat prompts like code
09:50 Version everything: prompts, guardrails, eval data, RAG artifacts & docs
13:31 Security for non-deterministic systems: prompt injection defenses
17:20 Embrace failure: incident response, game days & simulations
18:16 Resilience strategies: failover, quotas, gateways & backpressure
20:26 Quality & drift: KPIs, evals, user feedback, and iteration loops
22:42 Recap, resources, QR codes, and audience Q&A wrap-up

Видео Is Your GenAI System Ready for Production Reality? | Maish Saidel-Keesing | LLMday Warsaw 2026 Q1 канала LLMday