
How to evaluate AI agents before giving them write access
An agent's reply is a claim, and only the record can prove it

See our fireside chat with LinkedIn's Kafka and Samza teams as we dive deep into the technical architecture of Redpanda.
On Oct 28th, we had a deep-dive technical chat with a team of storage experts at LinkedIn that built Apache Kafka® and Apache Samza®. 1hr 30mins prior to the presentation, I had a single slide with my name on it. Luckily, the conversation quickly moved into details of memory pressure of the per core data structure materialization and we felt right at home.
Thanks to the storage and stream processing teams at LinkedIn for having us. Always fun to nerd out on tech. Stay tuned until the end for 30 mins of Q&A.
Engage with us on twitter via @redpandadata or personally at @emaxerrno
Special thanks to Noah, Sarah, and Denis for helping me put together a presentation one hour before the meeting.

An agent's reply is a claim, and only the record can prove it

Why AI agent accountability starts with observability, and how to mitigate risk with AI governance

Make sure you’re buying actual agent governance, not lock-in
Subscribe to our VIP (very important panda) mailing list to pounce on the latest blogs, surprise announcements, and community events!
Opt out anytime.