How?

No code. Just words.

The Vibe Coding advantage.

Ian H Smith

The process.

At Being Guided we work in four steps for digital innovation: Think; Simplify; Value; and Build.

Think is Design Thinking: based on the Stanford d.school1 method. It is five iterative stages to create a solid foundation for digital innovation. Simplify means stripping away of needless steps for user experience with Web apps. Applying Fierce Reduction until only the shortest path from intent to outcome remains - following The Laws of Simplicity by John Maeda2.

When we apply Design Thinking to maximise human receptivity, we must also Value. This means applying the financial rigour of Value Engineering. Originally conceived by Lawrence D. Miles3, Value Engineering eliminates waste and determines value over price. With digital innovation this means generating a Return On Investment (ROI) Model for creating a new Web app.

The fourth step is Build: Vibe Coding your Web app. The term Vibe Coding was popularised by Andrej Karpathy4 to describe a conversational, high-level way of programming with AI models, where you specify the intent, style, or 'vibe' of what you want and let the model draft most of the implementation details of a Web app.

Section image

The platform.

At Being Guided our technology is powered by an AI Agent: Abacus.ai5.or Lovable6 The AI Agent is underpinned by Anthropic Claude7 Large Language Model (LLM).

The AI Agent serves as Vibe Coding platform for Salesforce and full stack Web app infrastructure (Supabase) by enabling designers to build, automate, and deploy complex Web apps and workflows using natural language intent, rather than manual software coding.

Vibe Coding transforms the Salesforce and the full stack Web app development lifecycle from a traditional 'code-first' approach to an 'intent-first' generative process.

Natural Language Specification.
The user provides a high-level prompt, such as: "Build me a custom Salesforce dashboard that predicts deal slippage and automatically pings Slack when say, a high-value Opportunity hasn't been touched in three days."

Architectural Reasoning.
The AI Agent uses its internal Large Language Model (LLM) to plan the necessary components: identifying required Salesforce (or full stack Web app) Objects (Opportunities, Tasks, etc.). This will define the business logic. and selecting appropriate integration points.

Autonomous Code Generation.
The AI Agent leverages a Salesforce Connector to read schema and metadata or integrates with the Salesforce or full stack infrastructure. It generates the necessary backend logic and frontend UI components, often previewing them in a Sandbox/Test environment before finalisation.

Agentic Execution.
The AI Agent acts as an active layer over Salesforce or full stack infrastructure. It can perform multi-step reasoning, such as analysing historical trend data to identify patterns, and then execute actions like updating records or sending notifications.

Task Automation.
The AI Agent is a powerful toolset for automating everyday tasks: finding potential opportunities and running outreach campaigns on LinkedIn and running email campaigns on either Google Workspace or Microsoft Office 365. .

References.

  1. The Hasso Plattner Institute of Design. (2004) Stanford d.school. https://dschool.stanford.edu/about
  2. Maeda, J. (2006). The Laws of Simplicity. Design, Technology, Business, Life. Cambridge, Great Britain: MIT Press.
    https://mitpress.mit.edu/9780262539470/the-laws-of-simplicity/
  3. Miles, L.D. (1947). The Lawrence D. Miles Value Engineering Reference Center Collection.
    https://minds.wiscon.edu/handle/1793/301
  4. Karpathy, A. [@karpathy]. (2025, February 2). There’s a new kind of coding I call “vibe coding”, where you fully give in to vibes, embrace exponentials, and forget that code even exists. X. https://x.com/karpathy/status/1753472166197080428
  5. Abacus.ai. (2025). Abacus AI Deep Agent: The world's first super assistant. https://deepagent.abacus.ai/
  6. Lovable.dev (2026). Integrate backend with Supabase.
    https://lovable.dev/supabase-integration
  7. Anthropic. (2026). Claude Code.
    https://code.claude.com/docs/en/overview