World Congress 2024 Aug 20, 2024 Session details

Make it simple, using generative AI to accelerate learning

Duan Lightfoot

Generic LLMs introduce data risks and costly hallucinations. Accelerate developer learning safely by building customized RAG pipelines grounded in your verified enterprise documentation.

Pause
Mute Enter Fullscreen
#1 about 2 min

The foundational role of continuous learning in software

Retaining core engineering knowledge remains vital when integrating automated tooling into daily workflows.

#2 about 2 min

Navigating the technical professional learning loop

Breaking down the cycle of gathering, studying, and applying technical information to solve discrete problems.

#3 about 2 min

Overcoming team onboarding and documentation friction

Centralizing organizational knowledge bases reduces the time required to onboard new team members effectively.

#4 about 2 min

The shift towards generative artificial intelligence in production

Transitioning experimental automation projects into compliant, scalable systems fundamentally changes enterprise software architectures.

#5 about 2 min

Core mechanics and multimodal capabilities of generative models

Pre-trained deep learning networks now interpret cross-format data patterns to generate predictive texts, code, and media.

#6 about 2 min

Addressing constraints and security risks in language models

Relying exclusively on public training data introduces hallucination risks and compromises sensitive organizational intellectual property.

#7 about 2 min

Evaluating model customization techniques from prompting to fine tuning

Balancing complexity, cost, and output quality dictates the optimal approach for injecting proprietary context into models.

#8 about 2 min

Implementing retrieval augmented generation architecture for domain context

Converting document chunks into searchable vector representations allows models to reference validated facts dynamically before responding.

#9 about 2 min

Leveraging the comprehensive generative artificial intelligence stack

Abstracting infrastructure complexity through specialized service layers accelerates the deployment of conversational agents and coding assistants.

#10 about 4 min

Identifying baseline model limitations through API generation failures

Testing unconstrained coding queries reveals how models fabricate service concepts when lacking programmatic updates or system instructions.

#11 about 4 min

Applying custom prompt guardrails using cloud model management

Injecting strict behavioral constraints and dynamic variables into centralized system prompts forces bots to decline undocumented requests.

#12 about 3 min

Enhancing chatbot accuracy with vector knowledge bases

Synchronizing canonical reference manuals as embedding sources enables exact syntax generation verified against cited internal documentation.

#13 about 1 min

Analyzing generated code locally using intelligent developer assistants

Extending integrated development environments with workspace-aware tools streamlines contextual syntax explanation and localized security auditing.

#14 about 4 min

Integrating secure connectivity and responsible artificial intelligence practices

Routing inference traffic exclusively through private virtual networks guarantees data compliance while limiting scoped programmatic access.

Matching moments

1:34 min

Mitigating the inherent challenges of generative AI tools

Mary Grygleski Mary Grygleski · LIVE

3:17 min

Balancing AI regulation with technological innovation in human resources

Rudi Bauer Rudi Bauer +1 · Cappuccino with HR

2:42 min

Navigating generative AI adoption in enterprises

Chris Heilmann +2 · LIVE

3:22 min

Evaluating advanced artificial intelligence platforms for daily recruitment

Rudi Bauer Rudi Bauer +1 · Cappuccino with HR

2:52 min

Scaling generative AI use cases across large enterprises

Mike Butcher Mike Butcher +3 · WWC 2024

3:13 min

Embedding generative AI in enterprise software platforms

Mike Butcher Mike Butcher +3 · WWC 2024

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

The Broken Rung: How AI is Rebuilding Software Development from the Ground Up

Tomislav Tipurić

Chief Technology Officer, Nephos

Tomislav Tipurić
Open session

World Congress 2026 North America

Who Tests the AI? Building Trustworthy AI Systems at Enterprise Scale

Him Raj Singh

PayPal, Manager, Software Engineer

Him Raj Singh
Open session

World Congress 2026 North America

SecurePrompt: Building a Pre-Flight Security Layer for Agentic AI

Ravi Sastry Kadali

AI/ML Engineer at General Motors

Ravi Sastry Kadali
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

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan