~/talk

Prompt Engineering for Agentic Safety Assurance in Physical AI

Talkat Conf42 Prompt Engineering 2026 · on Thursday, 2026-10-29· [ai-assisted-development]
links:none on file
slides:none on file

Argues that prompts alone fail for embodied robots and proposes four pillars anchored by a system graph that encodes ODDs, mission scenarios, requirements and verification tied to ISO 26262/61508. Describes concrete tooling (Claude, Codex, draw.io, Confluence, Jira, Git), a hazard coverage skill schema that emits JSON/MD with unique IDs, and an example workflow that detects a perception model change, maps impacted scenarios, runs golden-case evals, and escalates for human sign‑off. Recommends ship-one-skill, gather traceable evidence, then scale.

AI-written summary · about

  1. 0:00Intro and What Is Physical AI
  2. 0:24Why Prompt Engineering Isn't Enough
  3. 1:23Four Pillars and the System Graph
  4. 2:24Defining the ODD and Hazards
  5. 4:14What Belongs in a Safety System Graph
  6. 5:38How Agents Use the Graph
  7. 6:42Skill Template for Hazard Coverage
  8. 7:27Example Workflow: Perception Model Change
  9. 9:03Prompts as Context and Evaluating Skills
  10. 11:08Roadmap, Takeaways, and Human Accountability
~/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.