WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 9, 2026 • Session details

Event-Driven AI Agents: Orchestrating Long-Context Legal Processing at Scale

Luca Bianchi

Shoving massive payloads into million-token windows guarantees latency and catastrophic timeouts. Discover how event-driven AI orchestration and selective context assembly cut per-request costs by 73%.

Pause
Mute Enter Fullscreen
#1 about 5 min

The complexity of processing enterprise legal documents

Why massive, multi-modal legal documents like the Ponte Morandi case exceed simple request-response paradigms.

#2 about 2 min

Why synchronous LLM calls fail at scale

How blocking API calls lead to cloud provider throttling, timeout walls, and complete application failures.

#3 about 3 min

The limitations of relying on large context models

Why switching to large context windows fails without aggressively breaking down the document logic.

#4 about 3 min

Designing an event-driven architecture for document processing

Utilizing AWS EventBridge to fragment documents alongside SQS, Step Functions, and agent workers for orchestrated extraction.

#5 about 3 min

Managing LLM failures with dead letter queues

Isolating transient processing errors through decentralized producer-consumer workflows and dead letter queues.

#6 about 7 min

Multi-step agent planning and dynamic context loading

Generating structured JSON plans via LLMs to classify chunk semantic roles and orchestrate specialized extraction tools.

#7 about 4 min

Optimizing token costs and intelligent chunking strategies

Compressing processing context significantly by selectively combining indexed chunks with extracted metadata and layered prompts.

#8 about 4 min

Scaling serverless agents with AWS Lambda MicroVMs

Handling immense document processing pipelines using SQS fan-out architectures and highly concurrent serverless environments.

#9 about 2 min

Evaluating document extraction performance with benchmarking tools

Utilizing open-source evaluation tools to score plugin parsing accuracy across messy legal datasets using mathematical metrics.

#10 about 2 min

Evolving architectures and rapidly swapping OCR models

Integrating new vision models rapidly by leveraging the decoupled routing structure and robust fallback tiers.

#11 about 2 min

Mitigating common failure modes in production pipelines

Deploying state machines and programmatic guardrails to handle reasoning failures organically and ensure system scalability.

Matching moments

2:58 min

Architectural challenges of AI-driven data queries

Andrey Abramov Andrey Abramov · WWC Europe 2026

2:16 min

A five-stage architecture for reliable document pipelines

Nazeer Saeed Nazeer Saeed · WWC Europe 2026

2:20 min

Exploring auto-scaling benefits inside event-driven cloud ecosystems

Developersteve · LIVE

4:38 min

Architecting common use cases via serverless design

Oliver Arafat · LIVE

1:39 min

Leveraging generative AI and agents for executive productivity

Katrin Lehmann Katrin Lehmann +1 · Coffee With Developers

1:22 min

Leveraging the comprehensive generative artificial intelligence stack

Duan Lightfoot Duan Lightfoot · WWC 2024

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
about 1 month 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
about 1 month 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
about 1 month 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
about 1 month 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
about 1 month 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
about 1 month 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

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

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anagha Rumade, Apoorva Jaiswal, Anjana Umapathy

Anagha Rumade
Apoorva Jaiswal
Anjana Umapathy
Open session

World Congress 2026 North America

Agents That Own Their Inference: Building Production AI Agents on Dedicated GPUs

Duan Lightfoot

Sr. AI Engineer, Akamai

Duan Lightfoot
Open session

World Congress 2026 North America

Designing APIs That Survive AI Agents at Scale

Phani Pendurthi

Mastercard, Principal Software Engineer

Phani Pendurthi
Open session

World Congress 2026 North America

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Dor Cohen, Yoav Gal

Dor Cohen
Yoav Gal

Related videos

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems thumbnail
32:48
WWC Europe 2026 • about 1 month ago

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems

Matheus Guimaraes

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge thumbnail
42:26
Coffee With Developers • over 1 year ago

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge

Meta Atamel, Guillaume Laforge

Garbage In, Garbage Out: Engineering Reliable AI Document Extraction Pipelines thumbnail
27:24
WWC Europe 2026 • about 1 month ago

Garbage In, Garbage Out: Engineering Reliable AI Document Extraction Pipelines

Nazeer Saeed

LLMs in the wild: Building an AI agent that survives production thumbnail
28:06
WWC Europe 2026 • about 1 month ago

LLMs in the wild: Building an AI agent that survives production

Steven Mi, Giampaolo Casolla

3 Ways to Rebuild the Data Stack for Agents thumbnail
28:02
WWC Europe 2026 • about 1 month ago

3 Ways to Rebuild the Data Stack for Agents

Jordan Tigani

From minutes to seconds: Lessons learned optimizing multi-turn agentic workflows thumbnail
42:44
Europe 2026 Virtual • about 1 month ago

From minutes to seconds: Lessons learned optimizing multi-turn agentic workflows

Douglas Reiser

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.