~/talk

Architecture Driven AI Engineering

name:JD Black
links:none on file
slides:none on file

Describes a five‑phase agentic software and IT lifecycle that enforces architecture-as-code via SysML v2, traces requirements into automated Gherkin acceptance tests, and runs agents with deterministic exit criteria plus human review gates. Reports small‑batch execution, versioned agents, skills, and workflows; instruments runtime with step timing, token/cost accounting and audit trails. Shows a seven‑person team replacing a $30M/year COTS tool and deploying full integrated ecosystems in minutes. Asks for a standardized AI package manager and deterministic agentic workflow standards.

AI-written summary · about

  1. 0:00Introduction by Gene Kim
  2. 3:26Physics, policy, and rigor
  3. 6:41The Anchorman problem
  4. 9:05Agents, skills, and workflows
  5. 11:29Outer loop and executable requirements
  6. 13:51Systems engineering for AI
  7. 17:34Architecture and EARS requirements
  8. 20:26Explicit workflows and value streams
~/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.