Eric Provencher, founder of Repo Prompt and XR engineer at Unity, unveils the secret AI tool transforming Silicon Valley’s coding landscape. He discusses the limitations of 'vibe coding' and how Repo Prompt enhances context management for complex tasks. Eric demonstrates features like context builders and codemaps, emphasizing their role in empowering developers. The conversation dives into AI's implications for future engineering, the importance of coding education, and the balance between AI dependence and skill maintenance in an evolving tech world.
38:07
forum Ask episode
web_stories AI Snips
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
insights INSIGHT
Vibe Coding Limitations
Vibe coding fails for complex coding tasks due to lack of proper context. - Providing targeted context to AI models greatly improves coding accuracy and results.
question_answer ANECDOTE
Nathan’s RepoPrompt Discovery
Nathan shares his experience where Cursor failed on complex projects. - RepoPrompt succeeded by managing context and worked better with advanced models like O1 Pro.
volunteer_activism ADVICE
Selective Context Building
Select relevant files selectively to build effective context instead of dumping entire codebase. - Use RepoPrompt's Code Maps to index and prioritize relevant files for AI prompts.
Get the Snipd Podcast app to discover more snips from this episode
Episode 57: Can simply "Vibe coding" with AI really replace the need for deep code context when building real applications? Nathan Lands (https://x.com/NathanLands) is joined by Eric Provencher (https://x.com/pvncher), founder of Repo Prompt and an XR engineer at Unity, to reveal the secret AI prompt tool quietly powering Silicon Valley’s top engineers.
This episode dives deep into why the current trend of "Vibe coding" with tools like Cursor often falls apart for complex tasks — and how Repo Prompt closes the gap by letting you build effective, highly targeted context for AI coding. Eric breaks down the philosophy behind contextual prompting, gives a live demo, and shares how Repo Prompt’s unique features like the context builder and codemaps give power-users real control over LLMs like Gemini and Claude. Beyond coding, they discuss implications for the future of engineering, learning, and the evolution of dev tools in the age of AI.
Check out The Next Wave YouTube Channel if you want to see Matt and Nathan on screen: https://lnk.to/thenextwavepd