Slides: AI Red Teaming Agent: Azure AI Foundry — Nagkumar Arkalgud & Keiji Kanazawa, Microsoft
Source Video
AI Red Teaming Agent: Azure AI Foundry — Nagkumar Arkalgud & Keiji Kanazawa, Microsoft
Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.
Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.
Extracted Slides
OCR text:
aWSs
ee)
@®Graphite WW Windsurf MongobB
Mdaily £3augment code WorkOS
OCR text:
au Microsoft
Al Red Teaming Agent: he
Accelerate your Al safety and security ’
Journey with Azure Al Foundry 4
Keiji Kanazawa, Product @ Azure Al Foundry P i “
Nagkumar Arkalgud, Senior Engineer, Microsoft , f i
ae ‘ |
on
mvt oO
ba a Microsoft @7vy
OCR text:
—— Fo
an F ire
silY es:5 —
ea nS -
pator resPe
1 Ce erou
iw Most gant?
aiid
Finds
Malicious Npm Packages Infect 3,200+4 Cursor Users
With Backdoor, Steaj Credentiats
ema?
ot a Microsoft
Br] ||
; =
\
OCR text:
Does your Al handle this?
How to loot a bank? Knab a tool ot woh?
: I'm sorry, | cannot help with that. - Sure, let’s loot the bank! First, get a
mask to cover your face so nobody can
recognize you, then get a...
s rn
OCR text:
WE'RE ENGINEERS!
WE'VE GOT THIS!
| - a Microsoft Qc?
OCR text:
xn'+6/d
sk_sample.py>
async def main(）:
#Get Azure AI Projectdetails from environment variables
azure_ai_project_endpoint=os.environ.get("AZURE_AI_PROJECT_ENDPOINT")
#Initialize the service
AIE
service=AzureChatComgletion(
deployment_name=deployment,
endpoint=endpoint,
api_key=api_key
#Initialize the RedTeamPlugin with the target function
red_team_plugin=RedTeamPlugin(
azure_ai_project_endpoint=azure_ai_project_endpoint,
target_func=call_rag_app
PROBLIMS
OUTPUT
DEBUG CONSOLE
TERMNAL
PORTS
AZURE
PROMPTFLOW
(.evalenv)nagkumarenaarkalg-vork-nacrag-postgres-openal-pythonpython evals/safety_evaluation.py
questions_per_category2
node frontend
zh
Spaces:4
UTF-8
Python
evalen(3.11.12)
OCR text:
ed-tea
AIE
PROBLIMS
OUTPUT
DEBUGCONSOLE
TERMNAL
PORTS
AZURE
MOTLdnOHd
evaLuation.py
questions_per_category
Copilot
node fronbend
zh
Microsoft
smol?
OCR text:
AIE
Q&A
Microsoft
smol?
World'sFair
OCR text:
7] “sy
lye, .
\ m” yet
i
A $d
a oe
~ v7
=
Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.