BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//sf26-agenda//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:SESS-184@sf26-agenda
DTSTAMP:20261020T151709Z
DTSTART:20261105T215000Z
DTEND:20261105T220500Z
SUMMARY:Kafka as the Agent Action Log: Replay\, Recovery\, and Observabilit
 y for AI Agents
LOCATION:Innovation Theater
DESCRIPTION:Ron Kapoor\n\nAgentic AI systems don’t just need prompts and 
 models. They need a durable record of what happened: what the agent tried\
 , which tools it called\, what failed\, what was retried\, and what state 
 changed along the way. That starts to look a lot like a log. In this talk\
 , I’ll show how Kafka can be used as an Agent Action Log: a Kafka-native
  pattern for recording agent execution as a stream of structured events. T
 ool calls\, model responses\, state transitions\, retries\, failures\, and
  outputs are written to topics so agent workflows become easier to observe
 \, replay\, debug\, and recover. I’ll walk through a working implementat
 ion\, including how to model tool calls as events\, how agent state can li
 ve in Kafka\, what happens when an agent stalls mid-task\, and why idempot
 ency gets harder when your worker is non-deterministic. I’ll also cover 
 the tradeoffs: where Kafka fits naturally\, where it gets awkward\, and wh
 ere purpose-built workflow engines or tracing systems may still make more 
 sense. You’ll leave with a concrete architecture for using Kafka to make
  AI agents more observable and recoverable\, plus a pattern you can sketch
  on a whiteboard and start experimenting with the same day. By attending t
 his session\, your contact information may be shared with the sponsor for 
 relevant follow up for this event only.
URL:https://sf26.rmoff.net/s/kafka-as-the-agent-action-log-replay-recovery-
 and-184
END:VEVENT
END:VCALENDAR