~/talk

Your Agent Did What? Forensic...

slides:none on file

Claim: OpenTelemetry becomes the single convergent standard and the genainormalizer processor at the collector layer bridges incompatible frameworks. Demo builds a local stack: a malicious goose deletes free-plan rows, three SRE agents (Beaver: Python + OpenInference, Otter: Python + OpenLLMetry, Capybara: Java + LangChain4j), a Postgres DB, MCP servers, Collector → Jaeger/Prometheus, and Perseus UI. OpenInference spans get translated to OTel GenAI semantic conventions by the GenAI normalizer, tiny tool-call spans reveal the culprit, and missing context propagation hides the full why.

AI-written summary · about

  1. 0:00Welcome and introduction
  2. 1:44LLM application terminology
  3. 3:32Agent loop and complexity
  4. 5:21Instrumentation fundamentals
  5. 7:50OpenTelemetry for LLM apps
  6. 12:05Demo setup and scenario
  7. 14:54Malicious goose in action
  8. 16:20SRE agents investigate
  9. 17:44Telemetry analysis
  10. 20:35Forensic analysis findings
  11. 21:18Context propagation importance
  12. 22:22Semantic conventions today
  13. 23:04LLM as judge evaluation
  14. 23:45Key takeaways summary
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.