WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

Hard Problems Hide in Boring Places: Turning Accounting Workflows into AI Products

Oleksandr Korotkykh , Tolga Sümer

How do you deploy LLMs in fintech without failing strict compliance audits? Discover how Pliant’s dual-LLM architecture balances real-world reasoning with fully traceable, fintech-grade rule enforcement.

Pause
Mute Enter Fullscreen
#1 about 4 min

Managing corporate payments with programmable virtual cards

Treating corporate credit cards like scoped API tokens enables granular control over merchant spending and expiration limits.

#2 about 3 min

Extracting compliance rules from unstructured expense policies

Company expense policies are typically long, obfuscated legal documents that hide complex compliance requirements deep in text.

#3 about 2 min

Analyzing structured transaction data and invoice line items

Transactions arrive as complex JSON payloads containing detailed accounting metadata and OCR-extracted receipt items for evaluation.

#4 about 3 min

Evaluating deterministic rule engines for transaction compliance

Traditional rule engines offer processing speed and transparency but struggle to scale with rapidly changing bespoke customer configurations.

#5 about 2 min

Replacing manual code creation with naive LLM prompts

Directing an artificial intelligence model to blindly assess compliance handles natural ambiguity well but completely destroys system auditability.

#6 about 2 min

Compiling natural language policies into strict deterministic rules

Using underlying language models to generate executable code initially seems like the perfect structural balance of flexibility and transparency.

#7 about 4 min

Failing to catch real-world nuance with fixed lists

Code-based pipelines fail when receipt items require generalized contextual knowledge, forcing engineering requirements to mandate flexible judgment alongside auditability.

#8 about 3 min

Designing an auditable language model evaluation architecture

Extracting simplified rules linked directly to original source documents allows dynamic evaluation while enforcing strict boundaries and human-in-the-loop approvals.

#9 about 2 min

Surfacing system reasoning and rule violations visually

Returning specific violated policy IDs and grounded reasoning ensures user interfaces can explicitly map decisions back to trusted documentation.

#10 about 3 min

Trading operational latency and reproducibility for actual accuracy

Utilizing large language models in functional paths requires processing queues in periodic batches and ultimately accepting non-deterministic execution states.

#11 about 1 min

Exposing hidden failures using messy production data immediately

Constructing robust AI features necessitates testing against raw, unstructured real-world data instead of sanitized inputs to discover actual limitations early.

Matching moments

4:32 min

Testing AI limits in enterprise software design

David Tielke David Tielke · World Congress 2026 Europe

2:11 min

Securing heterogeneous legacy payment infrastructure against AI

Michele Zuccala Michele Zuccala +4 · World Congress 2026 Europe

3:05 min

Transitioning from demos to real business processes

Deivids Vilkinsons Deivids Vilkinsons +3 · World Congress 2026 Europe

1:55 min

Identifying and fixing over-engineered AI calls through observability

diabhey diabhey · World Congress 2025

44 sec

Addressing corporate compliance challenges with secure enterprise AI

Hissan Usmani Hissan Usmani · World Congress 2025

5:20 min

Shifting from AI hype to enterprise operations

Deivids Vilkinsons Deivids Vilkinsons +3 · World Congress 2026 Europe

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 25, 2026 · 16:50–17:20

Stage 7

You Can’t Rerun Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

September 24, 2026 · 15:30–16:00

Outdoor Stage

From Boardroom to Build Pipeline: What AI Governance Actually Looks Like in Practice

Anita Ganti

Board Director & Technology Executive

Anita Ganti
Open session

World Congress 2026 North America

September 24, 2026 · 11:10–11:15

Outdoor Stage

Architecting the 100X SDLC: Building Production Trust into AI-Assisted Delivery

Ranjan Parthasarathy

Founder, CPTO/CEO at AXIOMSTUDIO.AI

Ranjan Parthasarathy
Open session

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Stage 2

Reinventing Testing Practices in the AI Era

Eric Deandrea

Java Champion & Senior Principal Software Engineer at IBM

Eric Deandrea
Open session

World Congress 2026 North America

September 24, 2026 · 14:10–14:40

Tech Leaders Stage

AI Governance & Compliance: Who Is Responsible When the Bots Start Acting?

Kumesh Aroomoogan, Paul Anthony Claxton, Eric Osiakwan

Kumesh Aroomoogan
Paul Anthony Claxton
Eric Osiakwan
Open session

World Congress 2026 North America

September 25, 2026 · 09:00–09:30

Stage 7

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel

Related videos

The Limits of LLMs in Real-World Applications thumbnail
31:07
World Congress 2026 Europe • 3 months ago

The Limits of LLMs in Real-World Applications

Deivids Vilkinsons, Guillaume Esnou, Laura Moritz, Mariam Hakobyan

The Missing Layer Between Enterprise Data and AI Agents thumbnail
30:17
World Congress 2026 Europe • 3 months ago

The Missing Layer Between Enterprise Data and AI Agents

Jannis Eickenroth, Sebastian Klenke

Detecting Money Laundering with AI thumbnail
29:37
LIVE • over 5 years ago

Detecting Money Laundering with AI

Stefan Donsa, Lukas Alber

Agentic employees in world's most downloaded FinTech app thumbnail
30:37
World Congress 2026 Europe • 3 months ago

Agentic employees in world's most downloaded FinTech app

Sasa Fajkovic

Running AI at Scale: The Secret Ingredients thumbnail
30:04
World Congress 2026 Europe • 3 months ago

Running AI at Scale: The Secret Ingredients

Boris Hecker, Max Tschochohei, Peter Kürpick, Tomislav Tipurić

Intelligent Automation using Machine Learning thumbnail
2:11:02
LIVE • over 5 years ago

Intelligent Automation using Machine Learning

Boris Krumrey, Andreas Palfi, Radu Pruna

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.