~/talk

Your Agent Passed the Prompt Test. Will It Survive Production?

links:none on file
slides:none on file

Harness shows a reproducible pipeline: run evals as unit tests against a golden dataset and 50 built-in metrics, deploy variations via AI configs/FME as a control plane, route traffic with an SDK and feature flags for a 20% canary, collect traces and thumbs-up/down events, and compare cost and task completion. A cited 74% rollback rate motivates this: tests can pass but production can cost more and leave 4 of 5 users unanswered, so immediate traffic edits and iterating the eval suite closes the loop.

AI-written summary · about

  1. 0:00Introduction: Will Your Agent Survive Production
  2. 0:56Four Questions Before Shipping Agent Changes
  3. 1:19Agent Rollbacks and the Cost Problem
  4. 3:07Evals as Unit Tests for Agents
  5. 5:00FME Configs as the Agent Control Plane
  6. 6:57Canary Rollouts and Traces
  7. 9:42Cheaper in Tests, Not in Production
  8. 11:49Rolling Back and Learning from Production
  9. 14:36Closing the Loop with a Third Wave
  10. 17:14What Your Team Gets from Harness
  11. 19:59Try It Monday
~/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.