WeAreDevelopers LIVE • Nov 25, 2025

Devs vs. Marketers, COBOL and Copilot, Make Live Coding Easy and more - The Best of LIVE 2025 - Part 3

Chris Heilmann , Daniel Cranney , Raphael De Lio , Tim Cadenbach , Julie Kordick , Jan Moser , Elio Struyf , Johanna Pirker , Marc Duiker , Raymond Camden

Can an LLM instantly migrate decades-old COBOL infrastructure? Discover why single-prompt magic fails and how engineers are cleaning up the chaotic technical debt of AI vibe coding.

Pause
Mute Enter Fullscreen
#1 about 2 min

How open source contributions act as real-world job interviews

Hiring candidates directly from open source communities validates expertise and cultural fit before formal interviews begin.

#2 about 4 min

Building technical visibility by sharing knowledge and asking questions

Sharing knowledge consistently and engaging deeply with the community uncovers unexpected opportunities for developer advocacy roles.

#3 about 3 min

Honest developer advocacy and acknowledging competing products

Effective technical marketing requires product honesty and explicitly acknowledging when competitor solutions offer better performance.

#4 about 4 min

Migrating legacy COBOL systems using generative AI tools

Using large language models to modernize mainframe banking software exposes critical limitations in context windows and non-deterministic outputs.

#5 about 4 min

Testing multi-agent artificial intelligence frameworks for code translation

Translating undocumented legacy business logic requires multi-agent setups because single agents fail at complex end-to-end refactoring.

#6 about 4 min

Managing software technical debt and risky code coverups

Updating neglected frontend libraries often unravels nested dependencies that vastly exceed initial development budget estimates.

#7 about 4 min

Balancing client expectations and scope in software consulting

Consultants must establish strict project boundaries and functional scopes to avoid unstructured maintenance requests from clients.

#8 about 6 min

Eliminating live coding risks with visual studio code extensions

Custom editor extensions can perfectly automate typing and environment configurations to prevent standard demonstration failures on stage.

#9 about 9 min

Scripting interactive technical presentations inside the editor environment

Presenters can bundle markdown slides, terminal setups, and copilot prompts into reproducible repositories for audiences to reuse locally.

#10 about 4 min

Training foundational artificial intelligence models inside closed video games

Complex games with huge branching factors provide essential virtual environments for teaching autonomous agents through reinforcement learning.

#11 about 3 min

Applying machine learning to automate game balancing and moderation

Game developers utilize predictive machine learning algorithms to dynamically adjust difficulty and preemptively identify toxic player behavior.

#12 about 2 min

Client versus server artificial intelligence calculations for hardware limitations

Developers must decide whether to run resource-intensive predictive systems locally or server-side depending on their users' hardware capabilities.

#13 about 7 min

Evolving from procedural generation to generative artificial intelligence storytelling

Shifting from algorithmically generated worlds to language model-driven narratives creates uniquely tailored gameplay experiences while complicating authorial control.

#14 about 4 min

Vibe coding creates lucrative cleanup roles for senior developers

The proliferation of rushed code generation necessitates hiring experienced consultants to repair unmaintainable and fragile application architectures.

#15 about 6 min

Integrating native generative artificial intelligence APIs into browser engines

Exposing text summarization and writing assistance models directly inside the browser eliminates developer reliance on expensive third-party server calls.

#16 about 2 min

Verifying auto-generated information and improving interface source citations

Auto-generated summaries remain untrustworthy until user interfaces consistently prioritize clear attribution and transparent referencing to primary sources.

Matching moments

1:55 min

Shifting developer workloads and realistic AI productivity gains

Chris Heilmann Chris Heilmann +2 · LIVE

1:22 min

Overcoming initial skepticism of AI code generation

Jeff Blankenburg Jeff Blankenburg · World Congress 2026 Europe

3:32 min

Preserving the joy and curiosity of human coding

Chris Heilmann Chris Heilmann +4 · LIVE

1:46 min

Introduction to AI code generation and developer habits

Prashanth Chandrasekar Prashanth Chandrasekar · World Congress 2023

5:16 min

Motivations for adopting AI to enhance developer productivity

2:37 min

Impact of current generative AI tools on developer velocity

Daniel Tao +3 · World Congress 2024