Slides: From MCP to Scale: Pipelines That Build Themselves — Rafael Levi, Bright Data
Source Video
From MCP to Scale: Pipelines That Build Themselves — Rafael Levi, Bright Data
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:
€3 Braintrust €} WorkOS OpenAl
OCR text:
a - at Sete eel |
mn . = aren to Scale:
an Je Some :
| BUILD THEMSELVES
a Pe ae :
a
| Pb tcnmet iene
= ns La] Ce yr e : a ;
i Engineering the future of Al
| — i ; a
OCR text:
_ Ee
. 7 p Bs . PG cs .
| Engineering the future of Al
— _
OCR text:
a *& an 7 ce ea rs
bd * rt omen
“ee
5g bd
Sd * bd
-
bd Feet. mee es ; ad Cy , é c
a Al Engineer
/ aU telaa
OCR text:
AIE
Keep
bicda
ublic
Engineering the future of Al
OCR text:
; |
, a ee yy 2 ties
a
ze Engineering the future of Al
OCR text:
B
rtlogging
etreqoests
oetBeavtLfulsoop
Coefigoratiea
AIE
20.s.vn.gt（*ATA_，ocker)
OTRT_-.ah.（o.path.abst（_f1l_）)
logging.scConfig（1ev）-eggig.DFo,fort-s（ncte
log-logging-getlegger（_ae_)
ffetpae：tr，reriet3）t
.Fetor....
"fetchpage throupBrigt Detawoonlocker.
foattept inrage[retries）:
try:
response.reqsts.postc
"https1//ags.brightdata.com/regest",
ders(aethorLationrerer（aP_r）),
tlseout-50,
response.raise_fer_status()
escept reqoests.heqoestExceptlon ss )
1og.rng（fattpt（attmgt·1）falled for （or1)：[0）²)
fattt（etrses-）
（.lg（2ttt）
raise lontlaetrrer(fFailed te fetch [or1)aftee (retries)atteapts°)
AIEngineer
EUROPE
OCR text:
bd * ae
an seen
ae ee
od os *
}
7 " feo. mec: Pad é , aoe
Bei: | AlEngineer |
( EUROPE
ial
OCR text:
Keep
blicdat
ublic
AlEngir
EUROP
OCR text:
| Al Engineer |
EUROPE
AI.ENGINEER
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.