Slides: Make your LLM app a Domain Expert: How to Build an Expert System — Christopher Lovejoy, Anterior
Source Video
Make your LLM app a Domain Expert: How to Build an Expert System — Christopher Lovejoy, Anterior
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:
aWws
en)
@®Graphite W Windsurf MongobB
Mdaily £3 augmentcode WorkOS
OCR text:
Own yourvertical Aolaysook for buildinga o
comain-native LLM application ha,
i”
i oO
| a Microsoft Qo)
OCR text:
Anterior
WereaNewYork-based,clinician-led
companythatprovidesclinical
AIE
reasoning toolsandsolutionsto
accelerateandautomatehealthcare
administration
BACKEDBY
NEA
SEQUOIA
andFOUNDERSOF
DoooMod
ALLIMNCF
Meta
Microsoft
amazon
McKinsey
&Company
IMPERIAL
NHS
aws
OCR text:
OUP BET FOR VERTICAL AT APPLICATIONS:
an
LE ee ese
5 ra
SYSTEM Tor an pane Lae Megas yaseaeaacdllet
; le : SOONISTICATION
I RICS Se Olee kel ale we ay veliaane aia
ate tetclealaicie igi een eee
ec and pipelines
c
OCR text:
Wirvy is tt arc! to successfully agply
| Lis to specialized incustries’
mvt i)
| mw Microsoft §GDOU
OCR text:
An exampic cinical case processed by
On eee ne oa ee eet
Gh ls there documentation of unsuccesstul
merinpakvic tarrearis fae atk aan ae
conservative therapy for at least 6 weeks?
E -—T, i)
u Microsoft §=Gocl)
OCR text:
We achieved a paseline performance of 95% tor approvind Care...
| V1 fai)
mw Microsoft § SOU
OCR text:
Ve acnieved a baseline performance of O5% tor anproaving care...
then tlerated with asoectific customer to >OS% within 6 weeks
—— ee Nic
KDE Deal
V1 9
a Microsoft §= SOU
OCR text:
(2)Empowerdomainexpertstodefineand
maintain afailure mode ontology
AIE
Photo
Teke
extraction
ertrastion
location
Handuriting
Medcolrecord
Under-inference
extraction
extraction
Chgckbox
MedicalNecessityReview
extraction
Failure Modes
Logic
representation
reaso
Rles
interpretation
21Em
Rudlesouree
seeetion
Microsoft
smol?
OCR text:
(3) Measure eras together
on oroduction data to uniock tarceted Insiqnts
; i. a . 7 ; oe a os
Ree eee ae
i | 7 |
| ' wick aS 000 Oh
OCR text:
AIE
MEASURE
SpecfyFailuremode'tofx
Makechanges
ReviewAIoutputs
Analyze perfornance
toprioritisework
Produetion
Performance
opplication
insights
"Failure mode
dataset"eval
Chnica!
AI
ChnicalPA
engineer(s)engineer(s)
Make decisions
aboutnaking ive
See inpact of changes
aws
OCR text:
catasets enable target
ae enable targeted product
.
OCR text:
Empower your to make
Improvements cirectly with soon ric and
a x 7 ne
al . \
os a ca. aa y
ao ; F “
. : / 7
| 1 - Kr - ve Bi =) /
|
7 | a Microsoft ary?
f _ ©
OCR text:
A
AIE
Putting it together
Microsoft
smol?
OCR text:
Takeaways
2 ‘lobuild domain-native LUM applications you necd to salve tne
uO TAG Ran emeretmeROcercHMl- BRM cTs 01016 RR Ole R18 OeHOESl0/ | CNT in
a pover this system by reviewing Al outputs to
arora leiaatie! ; an O Rn tee esetete
Tee ei
» This takes production cata and uses it to give your LLM oreckicta
ees ercreROlALe(Crecteala.el (BRO) MOLU(CKOIRA CT UIOlE-C1 ODIs
« Jhoeresultis asel’-imoroving, data-driven process that can be
—. ereenovaa meas
- q :
|:
F
OCR text:
AIE
Thankyou
pherovejyMD
chris@anterior.com
chrislovejoy.me
Anterior.com/Company
Microsoft
smol?
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.