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
2 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
2 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
2 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
2 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
2 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
2 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 · 11:40–12:10

Stage 9

You Can’t Re-Run 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 · 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 25, 2026 · 09:00–09:30

Stage 7

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

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

September 24, 2026 · 17:30–18:00

Stage 5

Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale

Abdel Fane

Founder of OpenA2A

Abdel Fane
Open session

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Tech Leaders Stage

The AI Proving Ground

Anna Maria Brunnhofer-Pedemonte, David Hefter, Li Fan

Anna Maria Brunnhofer-Pedemonte
David Hefter
Li Fan

Related videos

The Limits of LLMs in Real-World Applications thumbnail
31:07
World Congress 2026 Europe • 2 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 • 2 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 • 2 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 • 2 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.