~/talk

Demand-Driven Context: What 300 Incidents Reveal About Tribal Knowledge

slides:none on file

An AI agent is run against ~300 real e‑commerce incidents and repeatedly fails until failure is used as a signal to document only what’s missing, a method called Demand-Driven Context. The pipeline uses RAG with Opus 4.5/5, clusters incidents into ~20 types, and runs nine DDC cycles until convergence at 46 entities. A demand_context skill makes the agent list missing vocab, systems, or region rules; a propose_knowledge flow opens PRs to a reviewed KB so context evolves without rotting.

AI-written summary · about

  1. 0:00Introduction and context
  2. 1:47The problem with incident response
  3. 4:47First failed attempts at AI agents
  4. 7:50The difficulty of documentation
  5. 10:33Learning from AI failures
  6. 13:17Introducing demand-driven context
  7. 15:48Analyzing the demand logs
  8. 18:34Validating the framework
  9. 26:04Preventing knowledge rot
  10. 27:44Continuous knowledge improvement
  11. 34:38Summary and key takeaways
  12. 36:34Closing thoughts and resources
~/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.