> Markdown version of [/videos/1766-devs-vs-marketers-cobol-and-copilot-make-live-coding-easy-and-more-the-best-of-live-2025-part-3?t=520](https://www.wearedevelopers.com/videos/1766-devs-vs-marketers-cobol-and-copilot-make-live-coding-easy-and-more-the-best-of-live-2025-part-3?t=520). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

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

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.

- **Speakers:** [Chris Heilmann](https://www.wearedevelopers.com/@chris-heilmann), [Daniel Cranney](https://www.wearedevelopers.com/@daniel-cranney), [Raphael De Lio](https://www.wearedevelopers.com/@raphael-de-lio), [Tim Cadenbach](https://www.wearedevelopers.com/@tim-cadenbach), Julie Kordick, [Jan Moser](https://www.wearedevelopers.com/@jan-moser), Elio Struyf, [Johanna Pirker](https://www.wearedevelopers.com/@johanna-pirker), Marc Duiker, Raymond Camden
- **Event:** WeAreDevelopers LIVE
- **Published:** November 25, 2025
- **Duration:** 1:01:48
- **URL:** https://www.wearedevelopers.com/videos/1766-devs-vs-marketers-cobol-and-copilot-make-live-coding-easy-and-more-the-best-of-live-2025-part-3

## Summary

The Best of LIVE 2025 episode reflects on the evolving role of developers in the age of AI, open-source visibility, and advanced productivity tooling. A major theme is the value of showing your work in public spaces—whether through community contributions, blogging, or conference participation—as a powerful strategy for career advancement and organic hiring in developer advocacy. This transparency extends to product marketing, where technical advocates build trust by honestly acknowledging the strengths and weaknesses of their own APIs compared to competitors, rather than relying on empty hype. Technological shifts dominate the technical discussions, particularly the complex reality of legacy modernization. Attempting to migrate decades-old COBOL infrastructure to modern cloud environments using LLMs reveals that single-prompt magic generation falls short. Instead, engineers must leverage sophisticated multi-agent frameworks, like Semantic Kernel, to iteratively reverse-engineer business logic from undocumented legacy systems. On the front-end, the rise of vibe coding—generating entire applications via raw AI prompts with minimal logic oversight—is creating a lucrative but frustrating wave of cleanup contracting. Fixing these chaotic codebases is comparable to a skilled artist performing a difficult tattoo cover-up; it reinforces that avoiding the initial architectural heavy lifting only magnifies technical debt later. The conversation also highlights practical software productivity and the nuanced integration of AI in user experiences. Tools like Demo Time, a Visual Studio Code extension, allow speakers to script live coding presentations seamlessly to avoid typos and live distractions. Meanwhile, the integration of generative capabilities directly into endpoints—spanning local Chrome AI APIs for targeted browser text processing to deeply integrated LLMs for open-story gaming narratives—demonstrates a shift toward localized, context-aware artificial intelligence. The overarching insight is that while AI vastly accelerates code and content creation, sustainable software still demands rigorous architectural foresight, ethical data practices, and the deep contextual knowledge that only experienced professionals provide.

**Keywords:** open-source visibility, developer advocacy, cobol cloud migration, github copilot, semantic kernel, multi-agent frameworks, legacy codebase refactoring, vibe coding cleanup, visual studio code extensions, live coding automation, procedural content generation, ai game mechanics, chrome on-device ai, generative ai integration

## Chapters

1. **How open source contributions act as real-world job interviews** (00:46) — Hiring candidates directly from open source communities validates expertise and cultural fit before formal interviews begin.
1. **Building technical visibility by sharing knowledge and asking questions** (02:00) — Sharing knowledge consistently and engaging deeply with the community uncovers unexpected opportunities for developer advocacy roles.
1. **Honest developer advocacy and acknowledging competing products** (05:41) — Effective technical marketing requires product honesty and explicitly acknowledging when competitor solutions offer better performance.
1. **Migrating legacy COBOL systems using generative AI tools** (08:40) — Using large language models to modernize mainframe banking software exposes critical limitations in context windows and non-deterministic outputs.
1. **Testing multi-agent artificial intelligence frameworks for code translation** (12:03) — Translating undocumented legacy business logic requires multi-agent setups because single agents fail at complex end-to-end refactoring.
1. **Managing software technical debt and risky code coverups** (15:08) — Updating neglected frontend libraries often unravels nested dependencies that vastly exceed initial development budget estimates.
1. **Balancing client expectations and scope in software consulting** (18:56) — Consultants must establish strict project boundaries and functional scopes to avoid unstructured maintenance requests from clients.
1. **Eliminating live coding risks with visual studio code extensions** (22:35) — Custom editor extensions can perfectly automate typing and environment configurations to prevent standard demonstration failures on stage.
1. **Scripting interactive technical presentations inside the editor environment** (28:19) — Presenters can bundle markdown slides, terminal setups, and copilot prompts into reproducible repositories for audiences to reuse locally.
1. **Training foundational artificial intelligence models inside closed video games** (36:49) — Complex games with huge branching factors provide essential virtual environments for teaching autonomous agents through reinforcement learning.
1. **Applying machine learning to automate game balancing and moderation** (40:43) — Game developers utilize predictive machine learning algorithms to dynamically adjust difficulty and preemptively identify toxic player behavior.
1. **Client versus server artificial intelligence calculations for hardware limitations** (43:09) — Developers must decide whether to run resource-intensive predictive systems locally or server-side depending on their users' hardware capabilities.
1. **Evolving from procedural generation to generative artificial intelligence storytelling** (44:23) — Shifting from algorithmically generated worlds to language model-driven narratives creates uniquely tailored gameplay experiences while complicating authorial control.
1. **Vibe coding creates lucrative cleanup roles for senior developers** (50:55) — The proliferation of rushed code generation necessitates hiring experienced consultants to repair unmaintainable and fragile application architectures.
1. **Integrating native generative artificial intelligence APIs into browser engines** (54:51) — Exposing text summarization and writing assistance models directly inside the browser eliminates developer reliance on expensive third-party server calls.
1. **Verifying auto-generated information and improving interface source citations** (60:39) — Auto-generated summaries remain untrustworthy until user interfaces consistently prioritize clear attribution and transparent referencing to primary sources.

## Related Moments

- [Shifting developer workloads and realistic AI productivity gains](https://www.wearedevelopers.com/videos/1830-wearedevelopers-live-speculaitions) (from "WeAreDevelopers LIVE - SpeculAItions")
- [Overcoming initial skepticism of AI code generation](https://www.wearedevelopers.com/videos/100119-it-s-not-vibe-coding-if-you-know-what-you-re-doing) (from "It's Not Vibe Coding If You Know What You're Doing")
- [Preserving the joy and curiosity of human coding](https://www.wearedevelopers.com/videos/1764-wearedevelopers-live-web-scraping-agents-actors-and-more) (from "WeAreDevelopers LIVE – Web Scraping, Agents, Actors and more")
- [Introduction to AI code generation and developer habits](https://www.wearedevelopers.com/videos/600-stack-overflow-community-and-ai) (from "Stack Overflow: Community and AI")
- [Motivations for adopting AI to enhance developer productivity](https://www.wearedevelopers.com/videos/1266-navigating-the-ai-revolution-in-software-development) (from "Navigating the AI Revolution in Software Development")
- [Impact of current generative AI tools on developer velocity](https://www.wearedevelopers.com/videos/1107-the-future-of-developer-experience-with-genai-driving-engineering-excellence) (from "The Future of Developer Experience with GenAI: Driving Engineering Excellence")

## Related Articles

- [Devs vs. Marketers, COBOL and Copilot, Make Live Coding Easy and more - The Best of LIVE 2025 - Part 3](https://www.wearedevelopers.com/magazine/663-devs-vs-marketers-cobol-and-copilot-make-live-coding-easy-and-more-the-best-of-live-2025-part-3)
- [Slopquatting, API Keys, Fun with Fonts, Recruiters vs AI and more - The Best of LIVE 2025 - Part 2](https://www.wearedevelopers.com/magazine/662-slopquatting-api-keys-fun-with-fonts-recruiters-vs-ai-and-more-the-best-of-live-2025-part-2)
- [Developers vs Scammers, Bad Design, AI is Pointless, AJAX is 20 and more - The Best of LIVE 2025 - Part 1](https://www.wearedevelopers.com/magazine/661-developers-vs-scammers-bad-design-ai-is-pointless-ajax-is-20-and-more-the-best-of-live-2025-part-1)
- [Exploring AI: Opportunities and Risks for Developers](https://www.wearedevelopers.com/magazine/522-exploring-ai-opportunities-and-risks-for-developers)

## Related Jobs

- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [Staff Developer Advocate, GitHub Security Lab](https://www.wearedevelopers.com/jobs/ext/1921051-staff-developer-advocate-github-security-lab) at **GitHub**
- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**
- [Principal Product Manager, Agent Platform](https://www.wearedevelopers.com/jobs/ext/277541-principal-product-manager-agent-platform) at **GitHub**
- [Tribe Lead - ( Software) Engineering Centre of Excllence](https://www.wearedevelopers.com/jobs/ext/1475530-tribe-lead-software-engineering-centre-of-excllence) at **SD Worx**