vibe-coding
An AI-native development approach where builders use AI tools to rapidly create software. The newsletter treats it as a growth and product-building methodology.
Key Highlights
- Vibe-coding is an AI-native way to build software by iterating through prompts, UI edits, and generated code.
- For AI PMs, it reduces the gap between product ideas and working prototypes across design, specs, and implementation.
- Google AI Studio emerged as a major vibe-coding platform with full-stack development, collaboration, and deployment features.
- Teams at Notion used tools like Cloud Code and CodeEx to help designers and PMs prototype AI features directly in code.
- The newsletter also frames vibe-coding as something that needs clear plans and success criteria to avoid unfocused experimentation.
vibe-coding
Overview
Vibe-coding is an AI-native development approach where builders use generative AI tools to rapidly create software by describing intent, iterating through prompts, and refining working prototypes in code and UI simultaneously. In the newsletter, it appears both as a hands-on product-building methodology and as a broader growth tactic: teams use AI to move from idea to prototype to launch faster, often with fewer specialized engineering bottlenecks.For AI Product Managers, vibe-coding matters because it compresses the distance between product thinking and product execution. PMs, designers, and founders can test product concepts, flows, onboarding, and even monetization mechanics directly in AI-powered environments like Google AI Studio, Claude Code, Lovable, Cloud Code, and CodeEx. At the same time, the term carries an important caution: without a clear plan, success criteria, and disciplined iteration, “vibe-coding” can become unfocused experimentation rather than effective product development.
Key Developments
- 2026-02-09: Lenny Rachitsky highlighted Lazar Jovanovic as the first full-time “vibe coder,” describing workflows such as AI-aligned markdown files, a 4×4 debugging method, and running 4–5 parallel prototypes without writing code.
- 2026-03-08: Tal Raviv shared a detailed account of “vibe coding” a landing page for Familiar, pushing back on the idea that AI-first building is always quick and effortless.
- 2026-03-10: Simon Willison reflected on how LLMs may bias technology choices toward tools that are better represented in training data, a relevant concern for teams adopting AI-driven coding workflows.
- 2026-03-20: Google AI launched a full-stack vibe-coding environment in Google AI Studio for end-to-end app development across UI, back-end logic, and data pipelines.
- 2026-03-21: Google AI expanded that vision with a fuller “vibe coding” experience in AI Studio, adding smarter agents, multiplayer collaboration, secure login and storage, real-world integrations, and introducing Stitch as an AI-native design canvas.
- 2026-03-23: Santiago argued that agentic coding workflows need a clear plan; otherwise they devolve into “vibe-coding” with unnecessary extra steps.
- 2026-03-24: Philipp Schmid published a beginner-friendly guide to vibe-coding in Google AI Studio, covering prompting through deployment, private-by-default apps, Firebase auth/database setup, in-UI drawing feedback, and Cloud Run publishing.
- 2026-05-04: At Notion, designers and PMs used tools like Cloud Code and CodeEx to prototype AI features directly in code, reducing terminal intimidation and speeding up iteration.
- 2026-05-06: Logan Kilpatrick rolled out edit mode in AI Studio Vibe Coding, enabling component-level edits, pen-based UI annotations, image swaps via Nano Banana, and custom asset uploads.
- 2026-06-16: George Lampropoulos used AI-first development with Vibe Coding’s Oracles and RevenueCat to build and scale WrestleAI, focusing on a single “gotcha feature” and an Instagram influencer funnel to surpass 100K downloads and approach $200K in revenue.
Relevance to AI PMs
1. Prototype product ideas without waiting on full engineering cycles. AI PMs can use vibe-coding tools to turn PRDs, user stories, and rough UI concepts into testable prototypes quickly, which is especially useful for validating onboarding, AI copilots, chat flows, and internal tools.2. Shorten the design-to-code loop. Examples from Notion and Google AI Studio show that PMs and designers can work directly in AI-native coding environments, annotate interfaces, swap assets, and iterate on live functionality instead of handing off static mocks.
3. Balance speed with product discipline. The Santiago and Tal Raviv mentions highlight a core operating lesson: vibe-coding works best when paired with clear goals, constraints, and evaluation criteria. PMs should define the user problem, success metric, and scope before prompting AI to build.
Related
- Google AI Studio / AI Studio / google-ai-studio: One of the clearest platform examples of vibe-coding, offering full-stack AI-assisted app creation and deployment.
- Claude Code, Cloud Code, CodeEx: Developer tools that support AI-assisted coding and prototyping workflows used by PMs, designers, and builders.
- Lovable and ChatPRD: Tools associated with rapid prototyping, product specification, and AI-native product development.
- Stitch: Google’s AI-native design canvas, connected to vibe-coding through natural-language UI generation and design-to-build workflows.
- Lazar Jovanovic: Early exemplar of the “vibe coder” role and workflow.
- Tal Raviv and Familiar: A grounded case study showing that vibe-coding still requires effort, judgment, and iteration.
- Simon Willison: Provides an ecosystem-level critique around how LLMs can influence tool selection.
- Santiago: Adds the operational caveat that agentic coding needs planning to avoid turning into aimless vibe-coding.
- WrestleAI, Oracles, RevenueCat, George Lampropoulos: A concrete growth case where AI-first building, focused feature strategy, and distribution combined into measurable business results.
- CLI and Notion: Illustrate how even non-engineering teams can adopt code-adjacent, AI-assisted workflows to prototype product ideas faster.
Newsletter Mentions (11)
“George Lampropoulos built and scaled WrestleAI using AI-first development with Vibe Coding’s Oracles and RevenueCat, focusing on a single "gotcha feature" and an Instagram influencer funnel to reach 100K+ downloads and nearly $200K in revenue.”
#13 ▶️ How a TJ Maxx Cashier Built a $200K App With AI Greg Isenberg George Lampropoulos built and scaled WrestleAI using AI-first development with Vibe Coding’s Oracles and RevenueCat, focusing on a single "gotcha feature" and an Instagram influencer funnel to reach 100K+ downloads and nearly $200K in revenue.
“Logan Kilpatrick rolled out edit mode in AI Studio Vibe Coding, letting you select components for quick edits, draw annotations directly on the UI with a pen, swap image assets via Nano Banana, or upload your own content.”
#5 𝕏 Logan Kilpatrick rolled out edit mode in AI Studio Vibe Coding, letting you select components for quick edits, draw annotations directly on the UI with a pen, swap image assets via Nano Banana, or upload your own content.
“Using vibe coding tools such as Cloud Code and CodeEx, designers and PMs at Notion prototype AI features in code, reducing terminal intimidation and accelerating iteration.”
#8 ▶️ Why cultivating agency matters more than cultivating skills in the AI era | Max Schoening (Notion) Lennys Podcast Notion’s design team built a minimal LLM-friendly terminal playground to prototype AI chat interfaces, moving initial design work from Figma into code. The playground consists of a small codebase created by two designers and Max Schoening, optimized for one-shot interactions with LLMs and operated entirely via the terminal. Using vibe coding tools such as Cloud Code and CodeEx, designers and PMs at Notion prototype AI features in code, reducing terminal intimidation and accelerating iteration.
“Philipp Schmid shares a beginner-friendly guide to vibe-coding in Google AI Studio, walking through prompts to deployment.”
#10 𝕏 Philipp Schmid shares a beginner-friendly guide to vibe-coding in Google AI Studio, walking through prompts to deployment. He highlights private-by-default apps, one-click Firebase databases with auth, in-UI drawing for feedback, and instant Cloud Run publishing. #18 in Claire Vo argues leaders must ditch “I’m blocked” and instead use AI tools like Claude Code, Devin, Lovable, and ChatPRD to prototype, design, and spec in minutes.
“Santiago argues that AI agentic coding workflows require a clear plan—or they just become “vibe-coding” with needless extra steps.”
#10 𝕏 Santiago argues that AI agentic coding workflows require a clear plan—or they just become “vibe-coding” with needless extra steps.
“Google AI rolled out a full-stack “vibe coding” experience in AI Studio—complete with smarter agents, multiplayer collaboration, secure login/storage and real-world service integrations—and unveiled Stitch, an AI-native design canvas that turns natural-language prompts into p...”
#1 𝕏 Google AI rolled out a full-stack “vibe coding” experience in AI Studio—complete with smarter agents, multiplayer collaboration, secure login/storage and real-world service integrations—and unveiled Stitch, an AI-native design canvas that turns natural-language prompts into p...
“Google AI launched a full-stack Vibe coding environment in Google AI Studio. It enables end-to-end app development—UI, back-end logic, and data pipelines—through AI-powered code generation.”
#3 𝕏 Google AI launched a full-stack Vibe coding environment in Google AI Studio. It enables end-to-end app development—UI, back-end logic, and data pipelines—through AI-powered code generation. #4 𝕏 LlamaIndex 🦙 just open-sourced LiteParse, a zero-Python CLI & TypeScript-native library for layout-aware parsing of PDFs, Office docs, and images—preserving columns, tables, and alignment with built-in OCR, built for agent and LLM pipelines.
“#15 📝 Simon Willison Perhaps not Boring Technology after all - Reflection on the concern that LLMs might bias technology choices toward well-represented tools in their training data, making it harder for new tools to gain traction.”
This item is not explicitly about vibe coding, but it is about how LLMs shape technology selection and adoption. It is relevant to PMs thinking about AI-driven tooling choices and ecosystem effects.
“in Tal Raviv Tal Raviv spent significant time “vibe coding” a landing page for Familiar and shares a theater-free, detailed account to challenge the industry’s obsession with framing “quick and easy” as the hallmark of AI-forward work.”
in Tal Raviv Tal Raviv spent significant time “vibe coding” a landing page for Familiar and shares a theater-free, detailed account to challenge the industry’s obsession with framing “quick and easy” as the hallmark of AI-forward work.
“𝕏 Lenny Rachitsky spotlights Lazar Jovanovic’s role as the first full-time “vibe coder,” using an AI-aligned markdown file system, a 4×4 debugging workflow and 4-5 parallel prototypes to rapidly build products without writing code.”
#16 𝕏 Lenny Rachitsky spotlights Lazar Jovanovic’s role as the first full-time “vibe coder,” using an AI-aligned markdown file system, a 4×4 debugging workflow and 4-5 parallel prototypes to rapidly build products without writing code.
Related
Anthropic’s coding agent. It is relevant to AI PMs as a coding workflow product competing in enterprise and community adoption.
Person mentioned sharing a tutorial and a set of product principles in the newsletter. He is presented as a creator/commentator in AI product content.
A prominent AI blogger and commentator referenced in connection with an article on token reselling and fraud. He is cited as the source of the newsletter item discussing the marketplace and API-key abuse.
An AI engineering voice in the newsletter, sharing practical systems and workflows for agents and specialized intelligence. He is cited on model selection, evals, serving, and agent setup.
Google’s AI application builder and workflow environment. Here it is noted for GitHub repository import and bidirectional sync, which matters for AI product workflows and developer experience.
An AI practitioner mentioned sharing an experiment evaluating Claude Code on a Raspberry Pi. The post is about agent capability testing with physical hardware.
Cloud Code appears to be a coding agent or coding workflow used to generate launch videos from websites. The newsletter describes it as working with Fable 5 and HyperFrames.
A workspace tool used as part of the Claude Cowork PM workflow for weekly planning, context files, and task management.
An AI-first product management tool or startup referenced by Claire Vo. The newsletter uses it in a discussion of shipping an AI-first version of an app without traditional PM tooling.
Google’s environment for building and testing AI features, mentioned in the context of developer program redemption. It is relevant for AI prototyping and developer onboarding.
A no-code AI app builder referenced here as the platform used to build a production-grade SaaS product. For PMs, it illustrates how agentic coding is changing build-vs-buy and software creation economics.
A coding and research tool used here for optimizing order execution latency. Relevant to PMs as part of an AI-assisted quantitative workflow.
A Google DeepMind skill or interface for AI-assisted history analysis. It integrates Gemini with expert models to help translate and study ancient texts using plain English.
An image asset swapping tool or capability referenced in AI Studio editing workflows. Useful for PMs building multimodal UI-editing experiences.
An offline, local, open-source, free, model-agnostic screen-history tool. In this newsletter it is presented as the comparison point for OpenAI’s Computer History.
A Google Labs AI product for design. It is positioned as a creative product-making tool in Google’s experimental portfolio.
Stay updated on vibe-coding
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free