beitdin.dev

Vanilla JS · Web APIs · Sep 2026

If you want to supercharge your planning phase using AI, this is the ultimate tool to thoroughly interrogate your plans before acting. beitdin.dev lets you run multiple LLMs together, bringing three distinct perspectives toward one single goal.

Three specialists read your brief at the same time and hand you one document with all three outputs. Each lane holds a model and a role: a title and a system prompt. The same brief reaches lane one as a technical architect and lane two as a security expert, so the answers diverge because the framing differs.

This is not a model comparison tool. The lanes ask different questions of the same brief, and every run appends to the same markdown document, so the angles stack up into a comprehensive file you can hand onward rather than three versions of the same paragraph.

It's live at beitdin.dev.

How it works

There is no server, no account, and no queue. The app is a fully static HTML/JS page. Your brief, data, and API keys go directly from your browser to your chosen AI provider (OpenAI, Google Gemini, Mistral, or a local Ollama).

Bring your own key: API keys are stored only in the browser's sessionStorage. They disappear completely as soon as you close the tab and are never written to disk.

Zero tracking & safety: The app has no analytics, cookies, third-party scripts, or telemetry. It enforces a strict Content Security Policy (CSP) and uses textContent to prevent the AI from injecting executable code.