- Developers
- Learn about the shift to intent-based coding and practical agent implementation challenges.
- Business
- Understand how AI is changing software development workflows and the tools needed for success.
This interview provides a practical look at current AI agent capabilities and the challenges of building AI-native development tools from a company's perspective.
Vibe Coding's Uncanny Valley with Alexandre Pesant - #752
Audio streams from Sam Charrington. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Alexandre Pesant, AI lead at Lovable, discusses "vibe coding" on The TWIML AI Podcast. He explains how AI shifts software development from typing to expressing intent, creating a new abstraction layer. The episode covers coding agent capabilities, context engineering, and Lovable's technical journey, including scaling challenges and the need for robust evaluations and better user interfaces for AI-native tools.
Imagine telling a computer what you want it to build, instead of typing every single instruction. This episode explores how AI is making that possible, changing how software is made. It's like having a super-smart assistant that understands your ideas to help create code.
This episode offers insights into the evolving landscape of AI-powered software development, specifically "vibe coding." It's for developers and product managers interested in the practical application of AI agents and the challenges of building AI-native tools. The discussion on agent architectures, scaling, and the need for better evaluation directly relates to current efforts by frontier labs like Google Gemini and OpenAI to improve agent capabilities and developer experiences.
- HostSam Charrington
- GuestAlexandre PesantAI lead, Lovable
- Guest: Alexandre Pesant, AI lead at Lovable
- Episode Title: Vibe Coding's Uncanny Valley with Alexandre Pesant - #752
- Show: The TWIML AI Podcast
- Length: 73 minutes
- Technical Journey: Lovable shifted from a complex agent architecture to a simpler workflow system, then back to an agentic approach as foundation models improved.
- Scaling Challenge: Lovable experienced massive scaling challenges, including accidentally taking down GitHub.
Today, we're joined by Alexandre Pesant, AI lead at Lovable, who joins us to discuss the evolution and practice of vibe coding. Alex shares his take on how AI is enabling a shift in software development from typing characters to expressing intent, creating a new layer of abstraction similar to how high-level code compiles to machine code. We explore the current capabilities and limitations of coding agents, the importance of context engineering, and the practices that separate successful vibe coders from frustrated ones. Alex also shares Lovable’s technical journey, from an early, complex agent architecture that failed, to a simpler workflow-based system, and back again to an agentic approach as foundation models improved. He also details the company's massive scaling challenges—like accidentally taking down GitHub—and makes the case for why robust evaluations and more expressive user interfaces are the most critical components for AI-native development tools to succeed in the near future.
The complete show notes for this episode can be found at https://twimlai.com/go/752.
- vibe coding
- Alexandre Pesant
- A way of coding where you express your intent to the AI, rather than typing exact commands.
- coding agents
- Alexandre Pesant
- AI programs designed to help write or manage computer code.
- context engineering
- Alexandre Pesant
- The practice of providing AI agents with the right background information to perform tasks effectively.
- foundation models
- Alexandre Pesant
- Large, general-purpose AI models that can be adapted for various specific tasks.
Why Jev Is Changing How We Build With AI with Diogo Almeida - #779
WithDiogo Almeida
From Voice Agents to AI Avatars with Alexander Smola - #777
WithAlexander Smola
Questions people ask
- What is vibe coding?
- Vibe coding describes a shift in software development where AI enables users to express intent rather than typing specific characters, creating a new layer of abstraction.
- What are the key challenges for AI-native development tools?
- According to Alexandre Pesant, robust evaluations and more expressive user interfaces are the most critical components for AI-native development tools to succeed.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Sam Charrington.

