​AI demos are everywhere.

​But how do companies actually build AI products that work reliably with live data, low latency, and thousands of users?

​Join engineers as they share the architectures behind production AI systems - from streaming data and event-driven architectures to real-time databases, RAG pipelines, observability, and open-source infrastructure.

​No hype. Just practical engineering stories, lessons learned, and opportunities to meet others building modern data systems.

​Food and drinks included 🍻

​

​​Agenda

• ​6 pm - Networking

• ​6:15 - 8:00 pm - Talks

• ​8:00 - 9:00 pm - Networking

​​Speakers

• ​Robert Hodges, CEO @ Altinity

• ​Matt Wimpelberg, Senior Solutions Architect @ Grafana Labs

• ​Brad Miro, Senior Developer Advocate @ Google Cloud

​____

​Description of the talks

​Observing LLMs Without the Hype: How far boring tools get you, and what broke anyway

​Speaker: Matt Wimpelberg, Senior Solutions Architect @ Grafana Labs

​Abstract: Most teams shipping LLM features already run Prometheus, a trace store and a log pipeline. This talk asks how far that stack gets you before you need anything LLM-specific.

We start with what OpenTelemetry has actually standardized for generative AI (spans, two client metrics, token and model attributes) and what is still experimental or missing. Then, in short recorded demos, we run a plain open source stack against a simulated LLM service and watch three assumptions break:

- Cardinality: user and conversation IDs on metrics.
- Sampling: a 5% head sampler discards the errors and the slow tail you care about.
- Payload size: prompts and completions are tens of kilobytes, not tens of bytes.

For each, we show the boring fix and what the fix costs.

We close with a decision rule for when a dedicated LLM platform on a columnar store is worth adding. That is when you need to query prompt and completion content at volume, join it with evals and feedback, or slice cost by high-cardinality dimensions. 

Attendees will leave with

1. A map of what the OpenTelemetry GenAI conventions cover today, and where they stop.
2. Three concrete failure modes of LLM telemetry in a classic metrics, traces and logs stack, with the config that fixes each.
3. A short checklist for deciding whether they have outgrown that stack.

​

​Other talks coming soon!

​Follow the OSA Community

​🌐 Make OSA Con your community!

• ​🌍 Website: www.osacom.io

• ​💼 LinkedIn: /osa-con

• ​💬 Slack: Join our community